Article(id=1297211729251951126, tenantId=1146029695717560320, journalId=1296125453100220459, issueId=1297211624738284246, articleNumber=null, orderNo=null, doi=10.11975/j.issn.1002-6819.202512200, pmid=null, cstr=null, oa=null, hot=null, price=null, onlineType=0, articleFormat=0, articleType=null, articleTypeStr=null, receivedDate=1766419200000, receivedDateStr=2025-12-23, revisedDate=1779984000000, revisedDateStr=2026-05-29, acceptedDate=null, acceptedDateStr=null, onlineDate=1787208977282, onlineDateStr=2026-08-20, pubDate=1782748800000, pubDateStr=2026-06-30, doiRegisterDate=null, doiRegisterDateStr=null, onlineIssueDate=1787208977282, onlineIssueDateStr=2026-08-20, onlineJustAcceptDate=null, onlineJustAcceptDateStr=null, onlineFirstDate=null, onlineFirstDateStr=null, sourceXml=null, magXml=null, createTime=1787208977282, creator=13701087609, updateTime=1787208977282, updator=13701087609, issue=Issue{id=1297211624738284246, tenantId=1146029695717560320, journalId=1296125453100220459, year='2026', volume='42', issue='12', pageStart='1', pageEnd='396', issueExtLink='null', onlineDate='null', pubDate='1782748800000', pubDateStr='2026-06-30', beforeIssueId=null, nextIssueId=null, price=null, status=1, issueComplete=1, articleOrder=1, issueType=1, specialIssue=null, createTime=1787208952364, creator='13701087609', updateTime=1787212261177, updator='13701087609', preIssue=null, nextIssue=null, articleTotal=null, ext={EN=IssueExt(id=1297225503002357852, tenantId=1146029695717560320, journalId=1296125453100220459, issueId=1297211624738284246, language=EN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=), CN=IssueExt(id=1297225503002357853, tenantId=1146029695717560320, journalId=1296125453100220459, issueId=1297211624738284246, language=CN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=)}, issueFiles=null, downloadFileDto=null}, startPage=73, endPage=82, ext={EN=ArticleExt(id=1297211729461666327, articleId=1297211729251951126, tenantId=1146029695717560320, journalId=1296125453100220459, language=EN, title=Temperature prediction models for meat duck breeding environment using CNN-BiLSTM-DQN, columnId=1297211670816907294, journalTitle=Transactions of the Chinese Society of Agricultural Engineering, columnName=Special Topics on Smart Animal-raising Technologies and Livestock Equipment(2): Smart Equipment and Environmental Engineering, runingTitle=null, highlight=null, articleAbstract=

The meat duck industry in China has contributed over 82% of the total slaughter volume worldwide. Therefore, an optimal air temperature is often required for the comfort and survival of meat ducks during breeding. However, the air temperature is susceptible to multiple factors, such as relative humidity and illumination intensity. It is a high demand to timely and accurately predict air temperature for the high-density healthy breeding. However, conventional temperature prediction has been limited to low accuracy, robustness, and generalization. In this study, a hybrid 1DCNN-BiLSTM-DQN model was proposed to integrate with a one-dimensional convolutional neural network (1DCNN), a bidirectional long short-term memory network (BiLSTM), and a deep Q-network (DQN). Duck-house temperature was accurately predicted after model construction. The temperature time-series signal was also decomposed into high- and low-frequency components via the discrete Fourier transform (DFT). Given that the high-frequency component represented short-term fluctuations, the 1DCNN was used to extract local features from the high-frequency component; whereas the low-frequency component represented long-term fluctuations, the BiLSTM was used to extract long-sequence dependency features from the low-frequency component. Subsequently, the two sets of features were fused using a concatenation model. And finally, the temperature prediction value was obtained after the mapping of a fully connected layer. Furthermore, the DQN algorithm was introduced to construct an agent for iterative optimization of the hyperparameters. An adaptive mechanism was optimized with an 8-dimensional state space and a 12-dimensional action space, enabling dynamic optimization of key hyperparameters, such as the learning rate, number of hidden layers, dropout rate, and network architecture. Thereby, the prediction robustness of the model was improved under scenarios of seasonal transitions and extreme weather. The indoor and outdoor temperature data of net-raised duck houses were collected in Gaoyou City, Yangzhou City, Jiangsu Province, from March 22, 2025, to March 22, 2026. The results demonstrated that the 1DCNN-BiLSTM-DQN model achieved a coefficient of determination (R2) of 0.993 with an optimal input step size of 48. The MAE and RMSE were superior to the conventional models, such as the Temporal Convolutional Network and Transformer. Specifically, the 1DCNN-BiLSTM-DQN model exhibited the following improvements under different weather conditions: On cloudy days, the MAE and RMSE decreased from 0.29 °C to 0.18 °C, and from 0.36 °C to 0.23 °C, whereas the R2 increased from 0.77 to 0.91; On sunny days, the MAE and RMSE decreased from 0.48 °C to 0.23 °C, and from 0.59 °C to 0.31 °C, whereas the R2 increased from 0.79 to 0.94; On rainy days, the MAE and RMSE decreased from 0.54 °C to 0.33 °C, and from 0.70 °C to 0.46 °C, whereas the R2 increased from 0.72 to 0.89. The combined 1DCNN-BiLSTM prediction model achieved better prediction performance compared with the conventional models, such as BiLSTM, 1DCNN, TCN, and Transformer. In summary, the 1DCNN-BiLSTM-DQN model can be expected to predict the temperature in duck houses. The findings can also provide data support for early environmental regulation, thereby reducing the risk of environmental stress in meat ducks.

, authors=Honglong LU1, Junjie YUAN1, Hulin LI1, Qi RONG1, Ben HUA1, Shijia YING2, Jizhang WANG1, *, authorsList=Honglong LU, Junjie YUAN, Hulin LI, Qi RONG, Ben HUA, Shijia YING, Jizhang WANG, authorCompany=null, correspAuthors=Jizhang WANG, authorNote=null, correspAuthorsNote=null, copyrightStatement=Copyright © 2026 Transactions of the Chinese Society of Agricultural Engineering., copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=null, magXml=null, pdfUrl=null, pdf=null, pdfFileSize=null, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=null, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=null, mapNumber=null, fund=null), CN=ArticleExt(id=1297211730740929058, articleId=1297211729251951126, tenantId=1146029695717560320, journalId=1296125453100220459, language=CN, title=基于1DCNN-BiLSTM-DQN的肉鸭养殖环境温度预测模型, columnId=1297211670993068064, journalTitle=农业工程学报, columnName=智慧养殖技术与智能畜牧装备专题(2):智能装备与环境工程, runingTitle=null, highlight=null, articleAbstract=

针对传统温度预测方法难以充分捕捉温度序列中的局部特征与长期趋势,进而造成模型预测性能不佳的问题,该研究提出一种融合一维卷积神经网络(one-dimensional convolutional neural network,1DCNN)、双向长短记忆神经网络(bidirectional long short-term memory,BiLSTM)与深度Q网络(deep Q-network,DQN)的1DCNN-BiLSTM-DQN温度预测模型。针对鸭舍温度时序信号蕴含的多尺度变化特征,通过离散傅里叶变换将温度时序信号分解为高频分量和低频分量,利用1DCNN提取高频分量中的短期波动特征,利用BiLSTM提取低频分量中长期波动的时序依赖特征。随后,采用拼接模型将两部分特征融合,通过全连接层映射得出温度预测值。在此基础上,引入DQN智能体实现预测模型超参数的迭代优化,DQN智能体以8维状态空间、12维动作空间构建自适应优化机制,以实现对学习率、隐藏层数量、Dropout率等关键超参数动态寻优,提升模型在季节交替、极端天气场景下的预测鲁棒性。利用网养鸭舍采集的舍内外温度数据对模型进行验证试验,结果表明,该模型的决定系数R2为0.99,最优输入步长为48,平均绝对误差、均方根误差指标优于时间卷积网络(temporal convolutional network,TCN)、Transformer等传统模型,说明该研究提出的1DCNN-BiLSTM-DQN模型可实现鸭舍温度的精准预测,为降低肉鸭的环境应激风险提供数据支撑。

, authors=卢洪龙1, 袁俊杰1, 李虎林1, 荣琪1, 花犇1, 应诗家2, 王纪章1, *, authorsList=卢洪龙, 袁俊杰, 李虎林, 荣琪, 花犇, 应诗家, 王纪章, authorCompany=null, correspAuthors=王纪章, authorNote=

卢洪龙,研究方向为禽舍环境预测与分析。Email:

, correspAuthorsNote=
王纪章,博士,教授,博士生导师,研究方向农业信息技术。Email:
, copyrightStatement=版权所有 © 2026 农业工程学报编辑部, copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=hbScBMtF2Rs6LHsOt5Bv2g==, magXml=/r7FrLZ8w4AS2Zx1ZgTX2w==, pdfUrl=null, pdf=lst8r7nJuePdZu8W3QBNtQ==, pdfFileSize=1479800, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=ihjt3XeO/6tH3akMt8SRoA==, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=RcU2hIMYg2W5XLxOaNq1sw==, mapNumber=null, fund=null)}, authors=[Author(id=1300032408280133935, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729251951126, orderNo=0, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=1847732401@qq.com, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1300032408347242801, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729251951126, authorId=1300032408280133935, language=EN, stringName=Honglong LU, firstName=Honglong, middleName=null, lastName=LU, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1College of Agricultural Engineering, Jiangsu University, Zhenjiang 212013, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1300032408414351666, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729251951126, authorId=1300032408280133935, language=CN, stringName=卢洪龙, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1江苏大学农业工程学院,镇江 212013, bio={"content":"

卢洪龙,研究方向为禽舍环境预测与分析。Email:

"}, bioImg=null, bioContent=

卢洪龙,研究方向为禽舍环境预测与分析。Email:

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1300032408103973160, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729251951126, xref=1, ext=[AuthorCompanyExt(id=1300032408112361769, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729251951126, companyId=1300032408103973160, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1College of Agricultural Engineering, Jiangsu University, Zhenjiang 212013, China), AuthorCompanyExt(id=1300032408124944682, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729251951126, companyId=1300032408103973160, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1江苏大学农业工程学院,镇江 212013)])]), Author(id=1300032408498237748, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729251951126, orderNo=1, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1300032408577929526, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729251951126, authorId=1300032408498237748, language=EN, stringName=Junjie YUAN, firstName=Junjie, middleName=null, lastName=YUAN, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1College of Agricultural Engineering, Jiangsu University, Zhenjiang 212013, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1300032408649232695, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729251951126, authorId=1300032408498237748, language=CN, stringName=袁俊杰, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1江苏大学农业工程学院,镇江 212013, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1300032408103973160, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729251951126, xref=1, ext=[AuthorCompanyExt(id=1300032408112361769, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729251951126, companyId=1300032408103973160, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1College of Agricultural Engineering, Jiangsu University, Zhenjiang 212013, China), AuthorCompanyExt(id=1300032408124944682, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729251951126, companyId=1300032408103973160, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1江苏大学农业工程学院,镇江 212013)])]), Author(id=1300032408716341561, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729251951126, orderNo=2, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1300032408787644731, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729251951126, authorId=1300032408716341561, language=EN, stringName=Hulin LI, firstName=Hulin, middleName=null, lastName=LI, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1College of Agricultural Engineering, Jiangsu University, Zhenjiang 212013, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1300032408854753596, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729251951126, authorId=1300032408716341561, language=CN, stringName=李虎林, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1江苏大学农业工程学院,镇江 212013, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1300032408103973160, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729251951126, xref=1, ext=[AuthorCompanyExt(id=1300032408112361769, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729251951126, companyId=1300032408103973160, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1College of Agricultural Engineering, Jiangsu University, Zhenjiang 212013, China), AuthorCompanyExt(id=1300032408124944682, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729251951126, companyId=1300032408103973160, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1江苏大学农业工程学院,镇江 212013)])]), Author(id=1300032408926056766, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729251951126, orderNo=3, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1300032408997359936, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729251951126, authorId=1300032408926056766, language=EN, stringName=Qi RONG, firstName=Qi, middleName=null, lastName=RONG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1College of Agricultural Engineering, Jiangsu University, Zhenjiang 212013, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1300032409064468801, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729251951126, authorId=1300032408926056766, language=CN, stringName=荣琪, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1江苏大学农业工程学院,镇江 212013, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1300032408103973160, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729251951126, xref=1, ext=[AuthorCompanyExt(id=1300032408112361769, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729251951126, companyId=1300032408103973160, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1College of Agricultural Engineering, Jiangsu University, Zhenjiang 212013, China), AuthorCompanyExt(id=1300032408124944682, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729251951126, companyId=1300032408103973160, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1江苏大学农业工程学院,镇江 212013)])]), Author(id=1300032409144160579, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729251951126, orderNo=4, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1300032409223852357, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729251951126, authorId=1300032409144160579, language=EN, stringName=Ben HUA, firstName=Ben, middleName=null, lastName=HUA, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1College of Agricultural Engineering, Jiangsu University, Zhenjiang 212013, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1300032409286766918, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729251951126, authorId=1300032409144160579, language=CN, stringName=花犇, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1江苏大学农业工程学院,镇江 212013, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1300032408103973160, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729251951126, xref=1, ext=[AuthorCompanyExt(id=1300032408112361769, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729251951126, companyId=1300032408103973160, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1College of Agricultural Engineering, Jiangsu University, Zhenjiang 212013, China), AuthorCompanyExt(id=1300032408124944682, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729251951126, companyId=1300032408103973160, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1江苏大学农业工程学院,镇江 212013)])]), Author(id=1300032409349681480, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729251951126, orderNo=5, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1300032409433567562, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729251951126, authorId=1300032409349681480, language=EN, stringName=Shijia YING, firstName=Shijia, middleName=null, lastName=YING, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2Institute of Animal Husbandry, Jiangsu Academy of Agricultural Sciences, Nanjing 210014, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1300032409500676427, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729251951126, authorId=1300032409349681480, language=CN, stringName=应诗家, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2江苏省农业科学院畜牧研究所,南京 210014, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1300032408200442155, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729251951126, xref=2, ext=[AuthorCompanyExt(id=1300032408208830764, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729251951126, companyId=1300032408200442155, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2Institute of Animal Husbandry, Jiangsu Academy of Agricultural Sciences, Nanjing 210014, China), AuthorCompanyExt(id=1300032408213025069, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729251951126, companyId=1300032408200442155, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2江苏省农业科学院畜牧研究所,南京 210014)])]), Author(id=1300032409576173901, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729251951126, orderNo=6, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=whxh@ujs.edu.cn, emailSecond=null, emailThird=null, correspondingAuthor=1, authorType=1, ext={EN=AuthorExt(id=1300032409672642895, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729251951126, authorId=1300032409576173901, language=EN, stringName=Jizhang WANG, firstName=Jizhang, middleName=null, lastName=WANG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, *, address=1College of Agricultural Engineering, Jiangsu University, Zhenjiang 212013, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1300032409777500496, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729251951126, authorId=1300032409576173901, language=CN, stringName=王纪章, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, *, address=1江苏大学农业工程学院,镇江 212013, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1300032408103973160, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729251951126, xref=1, ext=[AuthorCompanyExt(id=1300032408112361769, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729251951126, companyId=1300032408103973160, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1College of Agricultural Engineering, Jiangsu University, Zhenjiang 212013, China), AuthorCompanyExt(id=1300032408124944682, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729251951126, companyId=1300032408103973160, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1江苏大学农业工程学院,镇江 212013)])])], keywords=[Keyword(id=1300032409945272657, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729251951126, language=EN, orderNo=1, keyword=meat ducks), Keyword(id=1300032410024964434, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729251951126, language=EN, orderNo=2, keyword=temperature prediction), Keyword(id=1300032410121433427, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729251951126, language=EN, orderNo=3, keyword=deep Q-network), Keyword(id=1300032410201125204, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729251951126, language=EN, orderNo=4, keyword=long short-term memory neural network), Keyword(id=1300032410272428373, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729251951126, language=EN, orderNo=5, keyword=convolutional neural network), Keyword(id=1300032410343731542, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729251951126, language=CN, orderNo=1, keyword=肉鸭), Keyword(id=1300032410419229015, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729251951126, language=CN, orderNo=2, keyword=温度预测), Keyword(id=1300032410503115096, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729251951126, language=CN, orderNo=3, keyword=深度Q网络), Keyword(id=1300032410582806873, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729251951126, language=CN, orderNo=4, keyword=长短记忆神经网络), Keyword(id=1300032410649915738, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729251951126, language=CN, orderNo=5, keyword=卷积神经网络)], refs=[Reference(id=1300032413015503223, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729251951126, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=1, rfOrder=0, authorNames=null, journalName=null, refType=null, unstructuredReference=侯水生, 刘灵芝. 2024年水禽产业与技术发展报告[J]. 中国畜牧杂志, 2025, 61(3): 383-387., articleTitle=null, refAbstract=null), Reference(id=1300032413070029176, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729251951126, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=2, rfOrder=1, authorNames=null, journalName=null, refType=null, unstructuredReference=包旭梅, 谢芳宇, 刘灵芝. 我国肉鸭产业养殖效率及影响因素分析[J]. 饲料研究, 2025, 48(5): 175-180., articleTitle=null, refAbstract=null), Reference(id=1300032413141332345, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729251951126, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=2, rfOrder=2, authorNames=null, journalName=null, refType=null, unstructuredReference=BAO Xumei, XIE Fangyu, LIU Lingzhi. Analysis on breeding efficiency and influencing factors of meat duck industry in China[J]. Feed Research, 2025, 48(5): 175-180. (in Chinese with English abstract), articleTitle=null, refAbstract=null), Reference(id=1300032413216829818, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729251951126, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=3, rfOrder=3, authorNames=null, journalName=null, refType=null, unstructuredReference=管清苗, 丁为民, 郭彬彬, 等. 山东夏冬季节层叠式笼养肉鸭舍环境参数测定[J]. 农业工程学报, 2020, 36(20): 246-253., articleTitle=null, refAbstract=null), Reference(id=1300032413279744379, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729251951126, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=3, rfOrder=4, authorNames=null, journalName=null, refType=null, unstructuredReference=GUAN Qingmiao, DING Weimin, GUO Binbin, et al. Measurement of environmental parameters of cascading caged-rearing duck houses in Shandong of China in summer and winter[J]. Transactions of the Chinese Society of Agricultural Engineering (Transactions of the CSAE), 2020, 36(20): 246-253. (in Chinese with English abstract), articleTitle=null, refAbstract=null), Reference(id=1300032413351047548, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729251951126, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=4, rfOrder=5, authorNames=null, journalName=null, refType=null, unstructuredReference=邢伟杰, 金波, 石诗影, 等. 家禽养殖环境调控关键技术与设施设备研究进展[J]. 中国家禽, 2025, 47(3): 149-156., articleTitle=null, refAbstract=null), Reference(id=1300032413426545021, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729251951126, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=4, rfOrder=6, authorNames=null, journalName=null, refType=null, unstructuredReference=XING Weijie, JIN Bo, SHI Shiying, et al. Research progress on key technologies and facilities for poultry breeding environment regulation[J]. China Poultry, 2025, 47(3): 149-156. (in Chinese with English abstract), articleTitle=null, refAbstract=null), Reference(id=1300032413497848190, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729251951126, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=5, rfOrder=7, authorNames=null, journalName=null, refType=null, unstructuredReference=王生雨, 亓丽红, 杨小华, 等. 当前肉鸭饲养存在的问题及对策[J]. 农业工程学报, 2006, 22(14): 142-145., articleTitle=null, refAbstract=null), Reference(id=1300032413564957055, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729251951126, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=5, rfOrder=8, authorNames=null, journalName=null, refType=null, unstructuredReference=WANG Shengyu, QI Lihong, YANG Xiaohua, et al. Problems in currently raising broiler duck and the counterstrategy[J]. Transactions of the Chinese Society of Agricultural Engineering (Transactions of the CSAE), 2006, 22(14): 142-145. (in Chinese with English abstract), articleTitle=null, refAbstract=null), Reference(id=1300032413627871616, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729251951126, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=6, rfOrder=9, authorNames=null, journalName=null, refType=null, unstructuredReference=WANG Y, ZHENG W, LI B. Application of a novel grey model for forecasting indoor air temperature in poultry houses: Control strategy[J]. Journal of the ASABE, 2022, 65(3): 505-513., articleTitle=null, refAbstract=null), Reference(id=1300032413699174785, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729251951126, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=7, rfOrder=10, authorNames=null, journalName=null, refType=null, unstructuredReference=钱东平, 王建新, 隋美丽, 等. 畜禽舍环境温度监控系统模糊控制算法的实现[J]. 农业机械学报, 2005, 36(12): 95-98., articleTitle=null, refAbstract=null), Reference(id=1300032413783060866, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729251951126, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=7, rfOrder=11, authorNames=null, journalName=null, refType=null, unstructuredReference=QIAN Dongping, WANG Jianxin, SUI Meili, et al. Implementation of fuzzy control algorithm for environmental temperature monitoring system in livestock and poultry houses[J]. Transactions of the Chinese Society for Agricultural Machinery, 2005, 36(12): 95-98. (in Chinese with English abstract), articleTitle=null, refAbstract=null), Reference(id=1300032413904695683, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729251951126, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=8, rfOrder=12, authorNames=null, journalName=null, refType=null, unstructuredReference=谢秋菊, 郑萍, 包军, 等. 基于深度学习的密闭式猪舍内温湿度预测模型[J]. 农业机械学报, 2020, 51(10): 353-361., articleTitle=null, refAbstract=null), Reference(id=1300032413980193156, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729251951126, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=8, rfOrder=13, authorNames=null, journalName=null, refType=null, unstructuredReference=XIE Qiuju, ZHENG Ping, BAO Jun, et al. Temperature and humidity prediction model inside enclosed pig houses based on deep learning[J]. Transactions of the Chinese Society for Agricultural Machinery, 2020, 51(10): 353-361. (in Chinese with English abstract), articleTitle=null, refAbstract=null), Reference(id=1300032414047302021, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729251951126, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=9, rfOrder=14, authorNames=null, journalName=null, refType=null, unstructuredReference=贺琳, 李响, 杜继兵, 等. 双向时序数据驱动的玻璃温室环境变量预测模型[J]. 农业工程学报, 2026, 42(9): 302-310., articleTitle=null, refAbstract=null), Reference(id=1300032414126993798, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729251951126, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=9, rfOrder=15, authorNames=null, journalName=null, refType=null, unstructuredReference=HE Lin, LI Xiang, DU Jibin, et al. Predicting environmental variables in a greenhouse using a bidirectional temporal data-driven model[J]. Transactions of the Chinese Society of Agricultural Engineering (Transactions of the CSAE), 2026, 42(9): 302-310. (in Chinese with English abstract), articleTitle=null, refAbstract=null), Reference(id=1300032414198296967, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729251951126, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=10, rfOrder=16, authorNames=null, journalName=null, refType=null, unstructuredReference=胡瑾, 雷文晔, 卢有琦, 等. 基于1DCNN-GRU的日光温室温度预测模型研究[J]. 农业机械学报, 2023, 54(8): 339-346., articleTitle=null, refAbstract=null), Reference(id=1300032414286377352, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729251951126, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=10, rfOrder=17, authorNames=null, journalName=null, refType=null, unstructuredReference=HU Jin, LEI Wenye, LU Youqi, et al. Research on temperature prediction model of solar greenhouse based on 1D CNN-GRU[J]. Transactions of the Chinese Society for Agricultural Machinery, 2023, 54(8): 339-346. (in Chinese with English abstract), articleTitle=null, refAbstract=null), Reference(id=1300032414361874825, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729251951126, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=11, rfOrder=18, authorNames=null, journalName=null, refType=null, unstructuredReference=郝璇, 任守纲, 舒欣, 等. 基于TimesTransformer的农业设施环境预测与调控研究[J]. 南京农业大学学报, 2026, 49(3):653-664., articleTitle=null, refAbstract=null), Reference(id=1300032414437372298, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729251951126, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=11, rfOrder=19, authorNames=null, journalName=null, refType=null, unstructuredReference=HAO Xuan, REN Shougang, SHU Xin, et al. Research on environmental prediction and regulation of agricultural facility environment based on TimesTransformer [J].Journal of Nanjing Agricultural University, 2026, 49( 3) : 653-664. (in Chinese with English abstract), articleTitle=null, refAbstract=null), Reference(id=1300032414496092555, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729251951126, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=12, rfOrder=20, authorNames=null, journalName=null, refType=null, unstructuredReference=钟宁帆, 高鲁宁, 贺凯迅, 等. 基于PCA-LM-NARX的禽舍室温预测模型[J]. 农业工程学报, 2025, 41(2): 261-270., articleTitle=null, refAbstract=null), Reference(id=1300032414563201420, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729251951126, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=12, rfOrder=21, authorNames=null, journalName=null, refType=null, unstructuredReference=ZHONG Ningfan, GAO Luning, HE Kaixun, et al. Poultry house room temperature prediction model based on PCA-LM-NARX[J]. Transactions of the Chinese Society of Agricultural Engineering (Transactions of the CSAE), 2025, 41(2): 261-270. (in Chinese with English abstract), articleTitle=null, refAbstract=null), Reference(id=1300032414642893197, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729251951126, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=13, rfOrder=22, authorNames=null, journalName=null, refType=null, unstructuredReference=刘双印, 黄建德, 徐龙琴, 等. 基于PCA-SVR-ARMA的狮头鹅养殖禽舍气温组合预测模型[J]. 农业工程学报, 2020, 36(11): 225-233., articleTitle=null, refAbstract=null), Reference(id=1300032414735167886, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729251951126, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=13, rfOrder=23, authorNames=null, journalName=null, refType=null, unstructuredReference=LIU Shuangyin, HUANG Jiande, XU Longqin,. et al. Combined model for prediction of air temperature in poultry house for lion-head goose breeding based on PCA-SVR-ARMA[J]. Transactions of the Chinese Society of Agricultural Engineering (Transactions of the CSAE), 2020, 36(11): 225-233. (in Chinese with English abstract), articleTitle=null, refAbstract=null), Reference(id=1300032414806471055, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729251951126, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=14, rfOrder=24, authorNames=null, journalName=null, refType=null, unstructuredReference=YANG S, LI F, HAZRA A. Iterative optimization of the maximum directional distance function model for Chinese airline transportation efficiency evaluations[J]. Journal of Engineering, 2026(1):6103732, articleTitle=null, refAbstract=null), Reference(id=1300032414886162832, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729251951126, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=15, rfOrder=25, authorNames=null, journalName=null, refType=null, unstructuredReference=左志宇, 牟晋东, 毛罕平, 等. 基于深度强化学习的温室环境协调控制系统设计[J]. 农机化研究, 2025, 47(5): 22-27., articleTitle=null, refAbstract=null), Reference(id=1300032414957466001, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729251951126, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=15, rfOrder=26, authorNames=null, journalName=null, refType=null, unstructuredReference=ZUO Zhiyu, MOU Jindong, MAO Hanping, et al. Design of greenhouse environment coordinated control system based on deep reinforcement learning[J]. Agricultural Mechanization Research, 2025, 47(5): 22-27. (in Chinese with English abstract), articleTitle=null, refAbstract=null), Reference(id=1300032415020380562, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729251951126, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=16, rfOrder=27, authorNames=null, journalName=null, refType=null, unstructuredReference=OKADA J, HASHIMOTO F, MORI N. Reduction of order of device hamiltonian with adaptive moment estimation[J]. Japanese Journal of Applied Physics, 2021, 60: SBBH08, articleTitle=null, refAbstract=null), Reference(id=1300032415087489427, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729251951126, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=17, rfOrder=28, authorNames=null, journalName=null, refType=null, unstructuredReference=黄铝文, 刘宇航, 屈昆仪, 等. LSTM与Informer融合预测冠层区域温度[J]. 农业工程学报, 2025, 41(8): 222-232., articleTitle=null, refAbstract=null), Reference(id=1300032415188152724, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729251951126, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=17, rfOrder=29, authorNames=null, journalName=null, refType=null, unstructuredReference=HUANG Lyuwen, LIU Yuhang, QU Kunyi, et al. Canopy area temperature prediction with fusion of LSTM and Informer[J]. Transactions of the Chinese Society of Agricultural Engineering (Transactions of the CSAE), 2025, 41(8): 222-232. (in Chinese with English abstract), articleTitle=null, refAbstract=null), Reference(id=1300032415251067285, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729251951126, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=18, rfOrder=30, authorNames=null, journalName=null, refType=null, unstructuredReference=PEREA G R, POYATO C E, DIAZ RJ. Attention is all water need: Multistep time series irrigation water demand forecasting in irrigation disctrics[J]. Computers and Electronics in Agriculture, 2024, 218: 108723., articleTitle=null, refAbstract=null), Reference(id=1300032415322370454, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729251951126, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=19, rfOrder=31, authorNames=null, journalName=null, refType=null, unstructuredReference=吴佳, 陈森朋, 陈修云, 等. 基于强化学习的模型选择和超参数优化[J]. 电子科技大学学报, 2020, 49(2): 255-261., articleTitle=null, refAbstract=null), Reference(id=1300032415393673623, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729251951126, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=19, rfOrder=32, authorNames=null, journalName=null, refType=null, unstructuredReference=WU Jia, CHEN Senpeng, CHEN Xiuyun, et al. Model selection and hyperparameter optimization based on reinforcement learning[J]. Journal of University of Electronic Science and Technology of China, 2020, 49(2): 255-261. (in Chinese with English abstract), articleTitle=null, refAbstract=null), Reference(id=1300032415469171096, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729251951126, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=20, rfOrder=33, authorNames=null, journalName=null, refType=null, unstructuredReference=YANG K, WANG T, MIAO J, et al. Asymmetric spring–summer responses of interannual dry–wet transitions in eastern asia and north america under global warming[J]. Geophysical Research Letters, 2026, 53(10): e2026GL122510-e2026GL122510., articleTitle=null, refAbstract=null), Reference(id=1300032415548862873, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729251951126, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=21, rfOrder=34, authorNames=null, journalName=null, refType=null, unstructuredReference=LECUN Y, BOTTOU L. Gradient-based learning applied to document recognition[J]. Proceedings of the IEEE, 1998, 86(11): 2278-2324., articleTitle=null, refAbstract=null), Reference(id=1300032415632748954, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729251951126, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=22, rfOrder=35, authorNames=null, journalName=null, refType=null, unstructuredReference=祖林禄, 柳平增, 赵妍平, 等. 基于SSA-LSTM的日光温室环境预测模型研究[J]. 农业机械学报, 2023, 54(2): 351-358., articleTitle=null, refAbstract=null), Reference(id=1300032415716635035, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729251951126, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=22, rfOrder=36, authorNames=null, journalName=null, refType=null, unstructuredReference=ZU Linlu, LIU Pingzeng, ZHAO Yanping, et al. Solar greenhouse environment prediction model based on SSA-LSTM[J]. Transactions of the Chinese Society for Agricultural Machinery, 2023, 54(2): 351-358. (in Chinese with English abstract), articleTitle=null, refAbstract=null), Reference(id=1300032415821492636, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729251951126, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=23, rfOrder=37, authorNames=null, journalName=null, refType=null, unstructuredReference=张观山, 丁小明, 何芬, 等. 基于LSTM-AT的温室空气温度预测模型构建[J]. 农业工程学报, 2024, 40(18): 194-201., articleTitle=null, refAbstract=null), Reference(id=1300032415905378717, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729251951126, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=23, rfOrder=38, authorNames=null, journalName=null, refType=null, unstructuredReference=ZHANG Guanshan, DING Xiaoming, HE Fen, et al. Predicting greenhouse air temperature using LSTM-AT[J]. Transactions of the Chinese Society of Agricultural Engineering (Transactions of the CSAE), 2024, 40(18): 194-201. (in Chinese with English abstract), articleTitle=null, refAbstract=null), Reference(id=1300032416006042014, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729251951126, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=24, rfOrder=39, authorNames=null, journalName=null, refType=null, unstructuredReference=PENG F P, XUE G, YA L Z. Multi-uavs task allocation method based on MPSO-SA-DQN[J]. Measurement and Control, 2025, 58(8): 963-978., articleTitle=null, refAbstract=null), Reference(id=1300032416089928095, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729251951126, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=25, rfOrder=40, authorNames=null, journalName=null, refType=null, unstructuredReference=李潇宇, 张君华, 郭晓光, 等. 基于强化学习的机器人底盘能量管理与路径规划优化算法[J]. 农业工程学报, 2024, 40(21): 175-183., articleTitle=null, refAbstract=null), Reference(id=1300032416165425568, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729251951126, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=25, rfOrder=41, authorNames=null, journalName=null, refType=null, unstructuredReference=LI Xiaoyu, ZHANG Junhua, GUO Xiaoguang, et al. Reinforcement learning-based optimization algorithm for energy management and path planning of robot chassis[J]. Transactions of the Chinese Society of Agricultural Engineering (Transactions of the CSAE), 2024, 40(21): 175-183. (in Chinese with English abstract), articleTitle=null, refAbstract=null), Reference(id=1300032416253505953, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729251951126, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=26, rfOrder=42, authorNames=null, journalName=null, refType=null, unstructuredReference=WU J, CHENG L, CHU S S, et al. An autonomous coverage path planning algorithm for maritime search and rescue of persons-in-water based on deep reinforcement learning[J]. Ocean Engineering, 2024, 291(c): 116403.1-116403.21., articleTitle=null, refAbstract=null), Reference(id=1300032416329003426, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729251951126, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=27, rfOrder=43, authorNames=null, journalName=null, refType=null, unstructuredReference=KLOTZ D F, RIBEIRO R, ENEMBRECK F, et al. Estimating and tuning adaptive action plans for the control of smart interconnected poultry condominiums[J]. Expert Systems with Application, 2022, 187: 115876., articleTitle=null, refAbstract=null), Reference(id=1300032416412889507, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729251951126, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=28, rfOrder=44, authorNames=null, journalName=null, refType=null, unstructuredReference=胡洁, 张亚莉, 王团, 等. 基于深度强化学习的农田节点数据无人机采集方法[J]. 农业工程学报, 2022, 38(22): 41-51., articleTitle=null, refAbstract=null), Reference(id=1300032416479998372, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729251951126, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=28, rfOrder=45, authorNames=null, journalName=null, refType=null, unstructuredReference=HU Jie, ZHANG Yali, WANG Tuan, et al. UAV collection methods for the farmland nodes data based on deep reinforcement learning[J]. Transactions of the Chinese Society of Agricultural Engineering (Transactions of the CSAE), 2022, 38(22): 41-51. (in Chinese with English abstract), articleTitle=null, refAbstract=null), Reference(id=1300032416555495845, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729251951126, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=29, rfOrder=46, authorNames=null, journalName=null, refType=null, unstructuredReference=秦立峰, 周馨怡, 高延年, 等. 基于CNN与Transformer混合模型的自然场景奶牛身份重识别[J]. 农业工程学报, 2026, 42(5): 299-311., articleTitle=null, refAbstract=null), Reference(id=1300032416639381926, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729251951126, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=29, rfOrder=47, authorNames=null, journalName=null, refType=null, unstructuredReference=QIN Lifeng, ZHOU Xinyi, GAO Yannian, et al. Cow re-identification in natural scenes using a CNN-transformer hybrid model[J]. Transactions of the Chinese Society of Agricultural Engineering (Transactions of the CSAE), 2026, 42(5): 299-311. (in Chinese with English abstract), articleTitle=null, refAbstract=null), Reference(id=1300032416710685095, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729251951126, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=30, rfOrder=48, authorNames=null, journalName=null, refType=null, unstructuredReference=QIAO B, WANG Y, YAO L, et al. Attention mechanism fusion neural network for typhoon path prediction[J]. Applied Intelligence, 2024, 55(3): 244-244., articleTitle=null, refAbstract=null), Reference(id=1300032416777793960, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729251951126, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=31, rfOrder=49, authorNames=null, journalName=null, refType=null, unstructuredReference=KAI S, YONG F Z. Dual-branch adaptive feature fusion network[J]. Neurocomputing, 2026, 669: 132410., articleTitle=null, refAbstract=null)], funds=null, companyList=[AuthorCompany(id=1300032408103973160, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729251951126, xref=1, ext=[AuthorCompanyExt(id=1300032408112361769, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729251951126, companyId=1300032408103973160, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1College of Agricultural Engineering, Jiangsu University, Zhenjiang 212013, China), AuthorCompanyExt(id=1300032408124944682, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729251951126, companyId=1300032408103973160, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1江苏大学农业工程学院,镇江 212013)]), AuthorCompany(id=1300032408200442155, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729251951126, xref=2, ext=[AuthorCompanyExt(id=1300032408208830764, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729251951126, companyId=1300032408200442155, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2Institute of Animal Husbandry, Jiangsu Academy of Agricultural Sciences, Nanjing 210014, China), AuthorCompanyExt(id=1300032408213025069, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729251951126, companyId=1300032408200442155, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2江苏省农业科学院畜牧研究所,南京 210014)])], figs=[ArticleFig(id=1300032410821882203, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729251951126, language=EN, label=Fig.1, caption=Annual temperature variation inside and outside the duck house, figureFileSmall=h70A0a1smh9B6rtyJtjIVw==, figureFileBig=Sw1Pe2Bd8EpPh3pHJ3ACDQ==, tableContent=null), ArticleFig(id=1300032410893185372, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729251951126, language=CN, label=图1, caption=鸭舍内外温度周年变化, figureFileSmall=h70A0a1smh9B6rtyJtjIVw==, figureFileBig=Sw1Pe2Bd8EpPh3pHJ3ACDQ==, tableContent=null), ArticleFig(id=1300032411010625885, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729251951126, language=EN, label=Fig.2, caption=Overall structure diagram of the 1DCNN-BiLSTM-DQN model, figureFileSmall=N6GYxKgpPjlq96MnCSy//A==, figureFileBig=l6U+IilHLzkr8fAGU9wM0A==, tableContent=null), ArticleFig(id=1300032411069346142, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729251951126, language=CN, label=图2, caption=1DCNN-BiLSTM-DQN模型整体结构图

注:1DCNN是一维卷积神经网络,BiLSTM是双向长短记忆神经网络,DQN是深度Q网络

, figureFileSmall=N6GYxKgpPjlq96MnCSy//A==, figureFileBig=l6U+IilHLzkr8fAGU9wM0A==, tableContent=null), ArticleFig(id=1300032411144843615, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729251951126, language=EN, label=Fig.3, caption=Structure of bidirectional long short-term memory (BiLSTM), figureFileSmall=3s0PxG9272FS+W15FZMMHg==, figureFileBig=BF1kVaAXfNLWOVRqfa5pJQ==, tableContent=null), ArticleFig(id=1300032411216146784, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729251951126, language=CN, label=图3, caption=双向长短记忆神经网络结构

注:X1, X2, ..., Xt为时序输入序列的第1, 2, ..., t个时间步的输入向量;h1(f), h2(f), ..., ht(f)为前向LSTM在第1, 2, ..., t个时间步输出的隐藏状态向量;h1(b), h2(b), ..., ht(b)为后向LSTM在第1, 2, ..., t个时间步输出的隐藏状态向量;O1, O2 ,..., Ot为BiLSTM在第1, 2, ..., t个时间步的最终输出向量。

, figureFileSmall=3s0PxG9272FS+W15FZMMHg==, figureFileBig=BF1kVaAXfNLWOVRqfa5pJQ==, tableContent=null), ArticleFig(id=1300032411287449953, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729251951126, language=EN, label=Fig.4, caption=Flowchart of feature fusion and prediction, figureFileSmall=hf2vc9bwQurs7rt7/DHOiQ==, figureFileBig=/FXqRP6JtnQ8zJHX5RQhvw==, tableContent=null), ArticleFig(id=1300032411358753122, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729251951126, language=CN, label=图4, caption=特征融合与预测流程图

注:[b,128]中b为批次大小,128为特征维数,下同;StandardScaler 逆变换为标准化反处理,将单维数转为温度值。

, figureFileSmall=hf2vc9bwQurs7rt7/DHOiQ==, figureFileBig=/FXqRP6JtnQ8zJHX5RQhvw==, tableContent=null), ArticleFig(id=1300032411438444899, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729251951126, language=EN, label=Fig.5, caption=Structure of the DQN agent, figureFileSmall=pO2mkC6jPQ9jld9ijtGY6A==, figureFileBig=au3BAknFed994U1AaRqBAQ==, tableContent=null), ArticleFig(id=1300032411509748068, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729251951126, language=CN, label=图5, caption=DQN智能体结构图, figureFileSmall=pO2mkC6jPQ9jld9ijtGY6A==, figureFileBig=au3BAknFed994U1AaRqBAQ==, tableContent=null), ArticleFig(id=1300032411602022757, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729251951126, language=EN, label=Tab.1, caption=

Model parameter settings

, figureFileSmall=null, figureFileBig=null, tableContent=
模型参数
Model parameter
1DCNNBiLSTMDQN agent
注:“\”表示模型没有该参数。
Note:“\”indicates that the model does not have this parameter.
层数Number of layers32\
优化器OptimizerSGDSGDAdam
学习率Learning rate0.0050.0050.005
权重衰减Weight decay\\ $ 1\times {10}^{-5} $
激活函数Activation functionReLUReLUReLU
), ArticleFig(id=1300032411685908838, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729251951126, language=CN, label=表1, caption=

模型参数设置

, figureFileSmall=null, figureFileBig=null, tableContent=
模型参数
Model parameter
1DCNNBiLSTMDQN agent
注:“\”表示模型没有该参数。
Note:“\”indicates that the model does not have this parameter.
层数Number of layers32\
优化器OptimizerSGDSGDAdam
学习率Learning rate0.0050.0050.005
权重衰减Weight decay\\ $ 1\times {10}^{-5} $
激活函数Activation functionReLUReLUReLU
), ArticleFig(id=1300032411769794919, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729251951126, language=EN, label=Tab.2, caption=

Comparison of temperature prediction results friom different models

, figureFileSmall=null, figureFileBig=null, tableContent=
预测模型
Predictionmodel
MAE/℃RMSE/℃R2
注:MAE为平均绝对误差,RMSE为均方根误差,R²为决定系数。
Note: MAE stands for mean absolute error, RMSE stands forroot mean square error, and R2 represents the coefficient of determination.
TCN0.961.100.98
Transformer0.601.100.99
BiLSTM0.410.830.96
1DCNN0.330.410.95
1DCNN-BiLSTM0.150.220.99
), ArticleFig(id=1300032411832709480, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729251951126, language=CN, label=表2, caption=

不同模型温度预测结果对比

, figureFileSmall=null, figureFileBig=null, tableContent=
预测模型
Predictionmodel
MAE/℃RMSE/℃R2
注:MAE为平均绝对误差,RMSE为均方根误差,R²为决定系数。
Note: MAE stands for mean absolute error, RMSE stands forroot mean square error, and R2 represents the coefficient of determination.
TCN0.961.100.98
Transformer0.601.100.99
BiLSTM0.410.830.96
1DCNN0.330.410.95
1DCNN-BiLSTM0.150.220.99
), ArticleFig(id=1300032411912401257, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729251951126, language=EN, label=Tab.3, caption=

Temperature prediction results of fixed-parameter model and optimized-parameter model

, figureFileSmall=null, figureFileBig=null, tableContent=
天气类型
Weather type
固定模型参数模型
(1DCNN-BiLSTM)
DQN优化参数模型
(1DCNN-BiLSTM-DQN)
MAE/℃RMSE/℃R2MAE/℃RMSE/℃R2
阴天Cloudy0.290.360.770.180.230.91
晴天Sunny0.480.590.790.230.310.94
雨天Rainy0.540.700.720.330.460.89
), ArticleFig(id=1300032411996287338, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729251951126, language=CN, label=表3, caption=

固定参数模型和DQN优化参数模型的温度预测结果

, figureFileSmall=null, figureFileBig=null, tableContent=
天气类型
Weather type
固定模型参数模型
(1DCNN-BiLSTM)
DQN优化参数模型
(1DCNN-BiLSTM-DQN)
MAE/℃RMSE/℃R2MAE/℃RMSE/℃R2
阴天Cloudy0.290.360.770.180.230.91
晴天Sunny0.480.590.790.230.310.94
雨天Rainy0.540.700.720.330.460.89
), ArticleFig(id=1300032412075979115, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729251951126, language=EN, label=Tab.4, caption=

Statistical results of the impact of different input step sizes on temperature prediction performance

, figureFileSmall=null, figureFileBig=null, tableContent=
数据集
Dataset
步长
Stride
1DCNN-LSTM1DCNN-BiLSTM1DCNN-BiLSTM-DQN
MAE/℃RMSE/℃MAE/℃RMSE/℃MAE/℃RMSE/℃
注:*表示显著(P<0.05);**表示极显著(P<0.01);***极极显著(P<0.001)。
Note: * indicates significant difference (P<0.05); ** indicates highly significant difference (P<0.01); *** indicates extremely significant difference (P<0.001).
冬末春初
Late winter and
early spring
240.600.720.650.800.15**0.21**
480.470.600.620.910.10**0.17**
720.650.880.490.670.14**0.19**
春末夏初
Late spring and
early summer
240.600.770.310.390.14**0.25**
480.730.980.250.320.20**0.28**
720.580.780.280.350.12*0.16*
夏季
Summer
240.610.800.500.620.42*0.82*
480.720.980.580.780.13**0.25**
720.600.770.620.840.150.18
秋末冬初
Late autumn and
early winter
240.851.000.871.200.74*1.34*
481.101.300.881.100.37**0.48**
721.101.401.101.400.51**0.72**
一年
Whole year
240.660.800.770.810.40**0.52**
480.751.000.550.770.21**0.29**
720.710.950.630.800.44**0.53**
), ArticleFig(id=1300032412164059500, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729251951126, language=CN, label=表4, caption=

不同输入步长的对温度预测性能影响统计结果

, figureFileSmall=null, figureFileBig=null, tableContent=
数据集
Dataset
步长
Stride
1DCNN-LSTM1DCNN-BiLSTM1DCNN-BiLSTM-DQN
MAE/℃RMSE/℃MAE/℃RMSE/℃MAE/℃RMSE/℃
注:*表示显著(P<0.05);**表示极显著(P<0.01);***极极显著(P<0.001)。
Note: * indicates significant difference (P<0.05); ** indicates highly significant difference (P<0.01); *** indicates extremely significant difference (P<0.001).
冬末春初
Late winter and
early spring
240.600.720.650.800.15**0.21**
480.470.600.620.910.10**0.17**
720.650.880.490.670.14**0.19**
春末夏初
Late spring and
early summer
240.600.770.310.390.14**0.25**
480.730.980.250.320.20**0.28**
720.580.780.280.350.12*0.16*
夏季
Summer
240.610.800.500.620.42*0.82*
480.720.980.580.780.13**0.25**
720.600.770.620.840.150.18
秋末冬初
Late autumn and
early winter
240.851.000.871.200.74*1.34*
481.101.300.881.100.37**0.48**
721.101.401.101.400.51**0.72**
一年
Whole year
240.660.800.770.810.40**0.52**
480.751.000.550.770.21**0.29**
720.710.950.630.800.44**0.53**
), ArticleFig(id=1300032412256334189, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729251951126, language=EN, label=Tab.5, caption=

Model parameter complexity experiment

, figureFileSmall=null, figureFileBig=null, tableContent=
预测模型
Prediction model
MAE/℃训练时长
Training duration/s
参数量
Params/K
BiLSTM0.41152.75725.0
1DCNN0.3319.8536.0
基础1DCNN-BiLSTM0.3786.30380.5
改进1DCNN-BiLSTM0.1549.58194.0
), ArticleFig(id=1300032412327637358, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729251951126, language=CN, label=表5, caption=

模型参数复杂度试验

, figureFileSmall=null, figureFileBig=null, tableContent=
预测模型
Prediction model
MAE/℃训练时长
Training duration/s
参数量
Params/K
BiLSTM0.41152.75725.0
1DCNN0.3319.8536.0
基础1DCNN-BiLSTM0.3786.30380.5
改进1DCNN-BiLSTM0.1549.58194.0
), ArticleFig(id=1300032412403134831, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729251951126, language=EN, label=Tab.6, caption=

Temperature prediction results of different discrete Fourier transforms frequency

, figureFileSmall=null, figureFileBig=null, tableContent=
低频分量
Low-frequency
component
高频分量
High-frequency
component
MAE/℃RMSE/℃R²
23650.801.000.99
7300.800.990.99
14600.580.720.99
43650.660.820.99
7300.710.880.99
14600.560.690.99
523650.600.760.99
7300.891.170.98
14600.740.910.99
), ArticleFig(id=1300032412461855088, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729251951126, language=CN, label=表6, caption=

不同离散傅里叶变换频率的温度预测结果

, figureFileSmall=null, figureFileBig=null, tableContent=
低频分量
Low-frequency
component
高频分量
High-frequency
component
MAE/℃RMSE/℃R²
23650.801.000.99
7300.800.990.99
14600.580.720.99
43650.660.820.99
7300.710.880.99
14600.560.690.99
523650.600.760.99
7300.891.170.98
14600.740.910.99
), ArticleFig(id=1300032412533158257, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729251951126, language=EN, label=Tab.7, caption=

Comparison of temperature prediction results with different fusion stitching strategies

, figureFileSmall=null, figureFileBig=null, tableContent=
融合策略
Fusion Strategy
RMSE/℃R2训练时间
Training time/s
Attention Fusion0.980.9921.46
Weighted Fusion0.990.9851.85
Direct Concat0.740.9926.38
), ArticleFig(id=1300032412591878514, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729251951126, language=CN, label=表7, caption=

不同融合拼接策略的温度预测结果对比

, figureFileSmall=null, figureFileBig=null, tableContent=
融合策略
Fusion Strategy
RMSE/℃R2训练时间
Training time/s
Attention Fusion0.980.9921.46
Weighted Fusion0.990.9851.85
Direct Concat0.740.9926.38
), ArticleFig(id=1300032412650598771, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729251951126, language=EN, label=Tab.8, caption=

Temperature prediction results of different model parameters optimization strategies

, figureFileSmall=null, figureFileBig=null, tableContent=
优化器
Optimizer
RMSE/
R²训练时长
Training time/ s
试验次数
Number of experiments
DQN智能体DQN agent0.610.99209.515
网格搜索Grid search0.620.97163.525
随机搜索Random search0.660.96406.025
), ArticleFig(id=1300032412742873460, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729251951126, language=CN, label=表8, caption=

不同模型优化策略的温度预测结果

, figureFileSmall=null, figureFileBig=null, tableContent=
优化器
Optimizer
RMSE/
R²训练时长
Training time/ s
试验次数
Number of experiments
DQN智能体DQN agent0.610.99209.515
网格搜索Grid search0.620.97163.525
随机搜索Random search0.660.96406.025
), ArticleFig(id=1300032412818370933, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729251951126, language=EN, label=Tab.9, caption=

Temperature prediction results of different reward weights

, figureFileSmall=null, figureFileBig=null, tableContent=
试验分组
Experimental
group
奖励权重
Reward weight
MAE/℃RMSE/℃收敛迭代次数
Convergence iterations
1 $ 1:1 $1.101.3039
2 $ 5:10 $0.490.6226
3 $ 10:5 $0.440.5725
4 $ 15:5 $0.470.5832
), ArticleFig(id=1300032412877091190, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729251951126, language=CN, label=表9, caption=

不同奖励权重的温度预测结果

, figureFileSmall=null, figureFileBig=null, tableContent=
试验分组
Experimental
group
奖励权重
Reward weight
MAE/℃RMSE/℃收敛迭代次数
Convergence iterations
1 $ 1:1 $1.101.3039
2 $ 5:10 $0.490.6226
3 $ 10:5 $0.440.5725
4 $ 15:5 $0.470.5832
)], attaches=null, journal=Journal(id=1296123985890738214, delFlag=0, nameCn=农业工程学报, nameEn=Transactions of the Chinese Society of Agricultural Engineering, nameHistory1=null, nameHistory2=null, issn=1002-6819, eissn=null, cn=11-2047/S, coden=null, periodic=3, language=CN, oaType=null, ccby=null, superviseOffice=null, ownerOffice=null, pubOffice=null, editorOffice=null, officeType=null, aims=null, clcCode=null, officeProv=null, officeCity=null, officeAddr=null, officeZip=null, officeEmail=null, officePhone=null, editDirector=null, officeDirector=null, officeDirectorPhone=null, officeStaffNum=null, officeEmpNum=null, coverPicUrl=+90GfMrDOo0sGnhM27IfIQ==, journalPrice=null, startedYear=null, abbrevIsoEn=Transactions of the Chinese Society of Agricultural Engineering, journalRemark=null, publicationField=null, createdTime=1786949639057, updatedTime=1788949514636, createdBy=18614031015, updatedBy=13041195026, firstLetterCn=N, firstLetterEn=N, subjectCode=Agriculture, subjectName=null, subjectCodeEn=Agriculture, subjectNameEn=null, picCn=+90GfMrDOo0sGnhM27IfIQ==, picEn=+UrL7Qgb+cjoX8OpJtziCA==, jcr=null, cjcr=null, exts=[JournalExt(id=1304512072117678568, language=CN, name=农业工程学报, nameHistory1=null, nameHistory2=null, managedBy=, sponsoredBy=, publishedBy=, editorOffice=, officeProv=null, officeCity=null, officeAddr=, officeZip=, editDirector=, officeDirector=null, officePhone=null, coverPicUrl=null, journalRemark=, submitArticleUrl=null, websiteUrl=, createdTime=1788949514655, updatedTime=1788949514655, createdBy=13041195026, updatedBy=13041195026, submissionGuidelinesUrl=, submissionAuthorUrl=http://tsg.tcsae.org/nygcxb/author/login, submissionEditorUrl=https://nygcxb.ijournals.cn/nygcxb/editor/login, submissionReviewUrl=http://tsg.tcsae.org/nygcxb/reviewer/login, submissionCeEditorUrl=, submissionAeEditorUrl=, option={"copyright":""}), JournalExt(id=1304512072168010217, language=EN, name=Transactions of the Chinese Society of Agricultural Engineering, nameHistory1=null, nameHistory2=null, managedBy=, sponsoredBy=, publishedBy=, editorOffice=, officeProv=null, officeCity=null, officeAddr=, officeZip=, editDirector=, officeDirector=null, officePhone=null, coverPicUrl=null, journalRemark=, submitArticleUrl=null, websiteUrl=, createdTime=1788949514667, updatedTime=1788949514667, createdBy=13041195026, updatedBy=13041195026, submissionGuidelinesUrl=, submissionAuthorUrl=http://tsg.tcsae.org/nygcxb/author/login, submissionEditorUrl=https://nygcxb.ijournals.cn/nygcxb/editor/login, submissionReviewUrl=http://tsg.tcsae.org/nygcxb/reviewer/login, submissionCeEditorUrl=, submissionAeEditorUrl=, option={"copyright":""})], databaseList=null, tenantJournalId=1296125453100220459, websiteList=[Website(id=1296128922534564555, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1296125453100220459, journalNameCn=null, journalNameEn=null, grayFlag=null, tenantId=1146029695717560320, platformId=null, journalGroupId=null, journalGroupNameCn=null, journalGroupNameEn=null, type=1, domain=https://castjournals.cast.org.cn/joweb/nygcxb/CN, language=CN, createTime=1786950816043, createBy=18614031015, updateTime=1786950989293, updateBy=18614031015, name=农业工程学报-中文, tplId=1146099689490845704, title=农业工程学报, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1296129761215009609, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1296128922534564555, code=articleTextType, value=kx, createTime=1786951016000, updateTime=1786951016000, creator=18614031015, updator=18614031015), WebsiteProps(id=1296129761194038086, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1296128922534564555, code=banner, value=null, createTime=1786951015995, updateTime=1786951015995, creator=18614031015, updator=18614031015), WebsiteProps(id=1296129761231786828, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1296128922534564555, code=grayFlag, value=0, createTime=1786951016004, updateTime=1786951016004, creator=18614031015, updator=18614031015), WebsiteProps(id=1296129761185649477, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1296128922534564555, code=logo, value=https://castjournals.cast.org.cn/joweb/nygcxb/CN/file/pic?fileId=6wW+hIE4oBGmmFvGgEb5JQ==, createTime=1786951015993, updateTime=1786951015993, creator=18614031015, updator=18614031015), WebsiteProps(id=1296129761244369742, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1296128922534564555, code=minRunFlag, value=0, createTime=1786951016007, updateTime=1786951016007, creator=18614031015, updator=18614031015), WebsiteProps(id=1296129761206621000, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1296128922534564555, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/nygcxb/CN/file/pic, createTime=1786951015998, updateTime=1786951015998, creator=18614031015, updator=18614031015), WebsiteProps(id=1296129761240175437, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1296128922534564555, code=silenceFlag, value=0, createTime=1786951016006, updateTime=1786951016006, creator=18614031015, updator=18614031015), WebsiteProps(id=1296129761202426695, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1296128922534564555, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_cn_619/, createTime=1786951015997, updateTime=1786951015997, creator=18614031015, updator=18614031015), WebsiteProps(id=1296129761219203914, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1296128922534564555, code=themeColor, value=null, createTime=1786951016001, updateTime=1786951016001, creator=18614031015, updator=18614031015), WebsiteProps(id=1296129761227592523, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1296128922534564555, code=themeStyle, value=null, createTime=1786951016003, updateTime=1786951016003, creator=18614031015, updator=18614031015)]), Website(id=1296128922677170905, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1296125453100220459, journalNameCn=null, journalNameEn=null, grayFlag=null, tenantId=1146029695717560320, platformId=null, journalGroupId=null, journalGroupNameCn=null, journalGroupNameEn=null, type=1, domain=https://castjournals.cast.org.cn/joweb/nygcxb/EN, language=EN, createTime=1786950816077, createBy=18614031015, updateTime=1786950985772, updateBy=18614031015, name=农业工程学报-英文, tplId=1146101810881728533, title=Transactions of the Chinese Society of Agricultural Engineering, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1296129731049575225, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1296128922677170905, code=articleTextType, value=kx, createTime=1786951008808, updateTime=1786951008808, creator=18614031015, updator=18614031015), WebsiteProps(id=1296129731028603702, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1296128922677170905, code=banner, value=null, createTime=1786951008803, updateTime=1786951008803, creator=18614031015, updator=18614031015), WebsiteProps(id=1296129731070546748, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1296128922677170905, code=grayFlag, value=0, createTime=1786951008813, updateTime=1786951008813, creator=18614031015, updator=18614031015), WebsiteProps(id=1296129731016020789, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1296128922677170905, code=logo, value=https://castjournals.cast.org.cn/joweb/nygcxb/EN/file/pic?fileId=6wW+hIE4oBGmmFvGgEb5JQ==, createTime=1786951008800, updateTime=1786951008800, creator=18614031015, updator=18614031015), WebsiteProps(id=1296129731087323966, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1296128922677170905, code=minRunFlag, value=0, createTime=1786951008817, updateTime=1786951008817, creator=18614031015, updator=18614031015), WebsiteProps(id=1296129731041186616, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1296128922677170905, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/nygcxb/EN/file/pic, createTime=1786951008806, updateTime=1786951008806, creator=18614031015, updator=18614031015), WebsiteProps(id=1296129731078935357, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1296128922677170905, code=silenceFlag, value=0, createTime=1786951008815, updateTime=1786951008815, creator=18614031015, updator=18614031015), WebsiteProps(id=1296129731032798007, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1296128922677170905, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_en_623/, createTime=1786951008804, updateTime=1786951008804, creator=18614031015, updator=18614031015), WebsiteProps(id=1296129731053769530, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1296128922677170905, code=themeColor, value=null, createTime=1786951008809, updateTime=1786951008809, creator=18614031015, updator=18614031015), WebsiteProps(id=1296129731062158139, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1296128922677170905, code=themeStyle, value=null, createTime=1786951008811, updateTime=1786951008811, creator=18614031015, updator=18614031015)])], journalTitle=农业工程学报, weixinUrl=null, journalUrl=http://www.tcsae.org/, iacademicId=null, status=1, seqNo=null, journalTitleEn=Transactions of the Chinese Society of Agricultural Engineering, journalPhotoCn=+90GfMrDOo0sGnhM27IfIQ==, journalPhotoEn=+UrL7Qgb+cjoX8OpJtziCA==, journalFirstLetter=N, journalRecommend=null, journalNew=null, journalCollection=null, jcrJf=null, cjcrJf=null, jcrJfStr=null, cjcrJfStr=null, submissionFirstDecision=null, sciSubjectClassification=null, casSubjectClassification=null, citeScore=null, totalCitationFrequency=null, icpCode=null, psCode=null, advertisingLicenseCode=null, copyrightInformation=null, country=null, option=, provinceCode=null, provinceName=null, collectFlag=false, interPubPlatform=, interPubPlatformUrl=null), detailUrlCn=https://castjournals.cast.org.cn/joweb/nygcxb/CN/10.11975/j.issn.1002-6819.202512200, detailUrlEn=https://castjournals.cast.org.cn/joweb/nygcxb/EN/10.11975/j.issn.1002-6819.202512200, pdfUrlCn=https://castjournals.cast.org.cn/joweb/nygcxb/CN/PDF/10.11975/j.issn.1002-6819.202512200, pdfUrlEn=https://castjournals.cast.org.cn/joweb/nygcxb/EN/PDF/10.11975/j.issn.1002-6819.202512200, aliStartDate=0, aliEndDate=0, collectionFlag=false, citedCount=null, citedUrl=null, previewStatus=0, delFlag=0, hasFullText=1, orderTime=1782748800000, fullTextJson=null, articleText=null, reference=null)
收藏切换
基于1DCNN-BiLSTM-DQN的肉鸭养殖环境温度预测模型
收藏切换
PDF下载
卢洪龙 1 , 袁俊杰 1 , 李虎林 1 , 荣琪 1 , 花犇 1 , 应诗家 2 , 王纪章 1, *
农业工程学报 | 智慧养殖技术与智能畜牧装备专题(2):智能装备与环境工程 2026,42(12): 73-82
收起
收藏切换
农业工程学报 |智慧养殖技术与智能畜牧装备专题(2):智能装备与环境工程 2026 , 42 (12) : 73 -82
基于1DCNN-BiLSTM-DQN的肉鸭养殖环境温度预测模型
全屏
[Author(id=1300032408280133935, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729251951126, orderNo=0, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=1847732401@qq.com, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1300032408347242801, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729251951126, authorId=1300032408280133935, language=EN, stringName=Honglong LU, firstName=Honglong, middleName=null, lastName=LU, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1College of Agricultural Engineering, Jiangsu University, Zhenjiang 212013, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1300032408414351666, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729251951126, authorId=1300032408280133935, language=CN, stringName=卢洪龙, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1江苏大学农业工程学院,镇江 212013, bio={"content":"

卢洪龙,研究方向为禽舍环境预测与分析。Email:

"}, bioImg=null, bioContent=

卢洪龙,研究方向为禽舍环境预测与分析。Email:

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1300032408103973160, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729251951126, xref=1, ext=[AuthorCompanyExt(id=1300032408112361769, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729251951126, companyId=1300032408103973160, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1College of Agricultural Engineering, Jiangsu University, Zhenjiang 212013, China), AuthorCompanyExt(id=1300032408124944682, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729251951126, companyId=1300032408103973160, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1江苏大学农业工程学院,镇江 212013)])]), Author(id=1300032408498237748, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729251951126, orderNo=1, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1300032408577929526, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729251951126, authorId=1300032408498237748, language=EN, stringName=Junjie YUAN, firstName=Junjie, middleName=null, lastName=YUAN, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1College of Agricultural Engineering, Jiangsu University, Zhenjiang 212013, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1300032408649232695, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729251951126, authorId=1300032408498237748, language=CN, stringName=袁俊杰, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1江苏大学农业工程学院,镇江 212013, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1300032408103973160, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729251951126, xref=1, ext=[AuthorCompanyExt(id=1300032408112361769, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729251951126, companyId=1300032408103973160, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1College of Agricultural Engineering, Jiangsu University, Zhenjiang 212013, China), AuthorCompanyExt(id=1300032408124944682, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729251951126, companyId=1300032408103973160, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1江苏大学农业工程学院,镇江 212013)])]), Author(id=1300032408716341561, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729251951126, orderNo=2, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1300032408787644731, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729251951126, authorId=1300032408716341561, language=EN, stringName=Hulin LI, firstName=Hulin, middleName=null, lastName=LI, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1College of Agricultural Engineering, Jiangsu University, Zhenjiang 212013, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1300032408854753596, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729251951126, authorId=1300032408716341561, language=CN, stringName=李虎林, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1江苏大学农业工程学院,镇江 212013, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1300032408103973160, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729251951126, xref=1, ext=[AuthorCompanyExt(id=1300032408112361769, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729251951126, companyId=1300032408103973160, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1College of Agricultural Engineering, Jiangsu University, Zhenjiang 212013, China), AuthorCompanyExt(id=1300032408124944682, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729251951126, companyId=1300032408103973160, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1江苏大学农业工程学院,镇江 212013)])]), Author(id=1300032408926056766, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729251951126, orderNo=3, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1300032408997359936, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729251951126, authorId=1300032408926056766, language=EN, stringName=Qi RONG, firstName=Qi, middleName=null, lastName=RONG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1College of Agricultural Engineering, Jiangsu University, Zhenjiang 212013, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1300032409064468801, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729251951126, authorId=1300032408926056766, language=CN, stringName=荣琪, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1江苏大学农业工程学院,镇江 212013, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1300032408103973160, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729251951126, xref=1, ext=[AuthorCompanyExt(id=1300032408112361769, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729251951126, companyId=1300032408103973160, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1College of Agricultural Engineering, Jiangsu University, Zhenjiang 212013, China), AuthorCompanyExt(id=1300032408124944682, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729251951126, companyId=1300032408103973160, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1江苏大学农业工程学院,镇江 212013)])]), Author(id=1300032409144160579, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729251951126, orderNo=4, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1300032409223852357, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729251951126, authorId=1300032409144160579, language=EN, stringName=Ben HUA, firstName=Ben, middleName=null, lastName=HUA, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1College of Agricultural Engineering, Jiangsu University, Zhenjiang 212013, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1300032409286766918, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729251951126, authorId=1300032409144160579, language=CN, stringName=花犇, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1江苏大学农业工程学院,镇江 212013, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1300032408103973160, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729251951126, xref=1, ext=[AuthorCompanyExt(id=1300032408112361769, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729251951126, companyId=1300032408103973160, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1College of Agricultural Engineering, Jiangsu University, Zhenjiang 212013, China), AuthorCompanyExt(id=1300032408124944682, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729251951126, companyId=1300032408103973160, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1江苏大学农业工程学院,镇江 212013)])]), Author(id=1300032409349681480, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729251951126, orderNo=5, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1300032409433567562, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729251951126, authorId=1300032409349681480, language=EN, stringName=Shijia YING, firstName=Shijia, middleName=null, lastName=YING, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2Institute of Animal Husbandry, Jiangsu Academy of Agricultural Sciences, Nanjing 210014, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1300032409500676427, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729251951126, authorId=1300032409349681480, language=CN, stringName=应诗家, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2江苏省农业科学院畜牧研究所,南京 210014, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1300032408200442155, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729251951126, xref=2, ext=[AuthorCompanyExt(id=1300032408208830764, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729251951126, companyId=1300032408200442155, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2Institute of Animal Husbandry, Jiangsu Academy of Agricultural Sciences, Nanjing 210014, China), AuthorCompanyExt(id=1300032408213025069, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729251951126, companyId=1300032408200442155, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2江苏省农业科学院畜牧研究所,南京 210014)])]), Author(id=1300032409576173901, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729251951126, orderNo=6, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=whxh@ujs.edu.cn, emailSecond=null, emailThird=null, correspondingAuthor=1, authorType=1, ext={EN=AuthorExt(id=1300032409672642895, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729251951126, authorId=1300032409576173901, language=EN, stringName=Jizhang WANG, firstName=Jizhang, middleName=null, lastName=WANG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, *, address=1College of Agricultural Engineering, Jiangsu University, Zhenjiang 212013, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1300032409777500496, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729251951126, authorId=1300032409576173901, language=CN, stringName=王纪章, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, *, address=1江苏大学农业工程学院,镇江 212013, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1300032408103973160, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729251951126, xref=1, ext=[AuthorCompanyExt(id=1300032408112361769, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729251951126, companyId=1300032408103973160, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1College of Agricultural Engineering, Jiangsu University, Zhenjiang 212013, China), AuthorCompanyExt(id=1300032408124944682, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729251951126, companyId=1300032408103973160, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1江苏大学农业工程学院,镇江 212013)])])]
卢洪龙1 , 袁俊杰1, 李虎林1, 荣琪1, 花犇1, 应诗家2, 王纪章1, *
作者信息
  • 1江苏大学农业工程学院,镇江 212013
  • 2江苏省农业科学院畜牧研究所,南京 210014
通讯作者:
王纪章,博士,教授,博士生导师,研究方向农业信息技术。Email:
作者简介:

卢洪龙,研究方向为禽舍环境预测与分析。Email:

Temperature prediction models for meat duck breeding environment using CNN-BiLSTM-DQN
Honglong LU1 , Junjie YUAN1, Hulin LI1, Qi RONG1, Ben HUA1, Shijia YING2, Jizhang WANG1, *
Affiliations
  • 1College of Agricultural Engineering, Jiangsu University, Zhenjiang 212013, China
  • 2Institute of Animal Husbandry, Jiangsu Academy of Agricultural Sciences, Nanjing 210014, China
出版时间: 2026-06-30 doi: 10.11975/j.issn.1002-6819.202512200
文章导航
收藏切换

针对传统温度预测方法难以充分捕捉温度序列中的局部特征与长期趋势,进而造成模型预测性能不佳的问题,该研究提出一种融合一维卷积神经网络(one-dimensional convolutional neural network,1DCNN)、双向长短记忆神经网络(bidirectional long short-term memory,BiLSTM)与深度Q网络(deep Q-network,DQN)的1DCNN-BiLSTM-DQN温度预测模型。针对鸭舍温度时序信号蕴含的多尺度变化特征,通过离散傅里叶变换将温度时序信号分解为高频分量和低频分量,利用1DCNN提取高频分量中的短期波动特征,利用BiLSTM提取低频分量中长期波动的时序依赖特征。随后,采用拼接模型将两部分特征融合,通过全连接层映射得出温度预测值。在此基础上,引入DQN智能体实现预测模型超参数的迭代优化,DQN智能体以8维状态空间、12维动作空间构建自适应优化机制,以实现对学习率、隐藏层数量、Dropout率等关键超参数动态寻优,提升模型在季节交替、极端天气场景下的预测鲁棒性。利用网养鸭舍采集的舍内外温度数据对模型进行验证试验,结果表明,该模型的决定系数R2为0.99,最优输入步长为48,平均绝对误差、均方根误差指标优于时间卷积网络(temporal convolutional network,TCN)、Transformer等传统模型,说明该研究提出的1DCNN-BiLSTM-DQN模型可实现鸭舍温度的精准预测,为降低肉鸭的环境应激风险提供数据支撑。

肉鸭  /  温度预测  /  深度Q网络  /  长短记忆神经网络  /  卷积神经网络

The meat duck industry in China has contributed over 82% of the total slaughter volume worldwide. Therefore, an optimal air temperature is often required for the comfort and survival of meat ducks during breeding. However, the air temperature is susceptible to multiple factors, such as relative humidity and illumination intensity. It is a high demand to timely and accurately predict air temperature for the high-density healthy breeding. However, conventional temperature prediction has been limited to low accuracy, robustness, and generalization. In this study, a hybrid 1DCNN-BiLSTM-DQN model was proposed to integrate with a one-dimensional convolutional neural network (1DCNN), a bidirectional long short-term memory network (BiLSTM), and a deep Q-network (DQN). Duck-house temperature was accurately predicted after model construction. The temperature time-series signal was also decomposed into high- and low-frequency components via the discrete Fourier transform (DFT). Given that the high-frequency component represented short-term fluctuations, the 1DCNN was used to extract local features from the high-frequency component; whereas the low-frequency component represented long-term fluctuations, the BiLSTM was used to extract long-sequence dependency features from the low-frequency component. Subsequently, the two sets of features were fused using a concatenation model. And finally, the temperature prediction value was obtained after the mapping of a fully connected layer. Furthermore, the DQN algorithm was introduced to construct an agent for iterative optimization of the hyperparameters. An adaptive mechanism was optimized with an 8-dimensional state space and a 12-dimensional action space, enabling dynamic optimization of key hyperparameters, such as the learning rate, number of hidden layers, dropout rate, and network architecture. Thereby, the prediction robustness of the model was improved under scenarios of seasonal transitions and extreme weather. The indoor and outdoor temperature data of net-raised duck houses were collected in Gaoyou City, Yangzhou City, Jiangsu Province, from March 22, 2025, to March 22, 2026. The results demonstrated that the 1DCNN-BiLSTM-DQN model achieved a coefficient of determination (R2) of 0.993 with an optimal input step size of 48. The MAE and RMSE were superior to the conventional models, such as the Temporal Convolutional Network and Transformer. Specifically, the 1DCNN-BiLSTM-DQN model exhibited the following improvements under different weather conditions: On cloudy days, the MAE and RMSE decreased from 0.29 °C to 0.18 °C, and from 0.36 °C to 0.23 °C, whereas the R2 increased from 0.77 to 0.91; On sunny days, the MAE and RMSE decreased from 0.48 °C to 0.23 °C, and from 0.59 °C to 0.31 °C, whereas the R2 increased from 0.79 to 0.94; On rainy days, the MAE and RMSE decreased from 0.54 °C to 0.33 °C, and from 0.70 °C to 0.46 °C, whereas the R2 increased from 0.72 to 0.89. The combined 1DCNN-BiLSTM prediction model achieved better prediction performance compared with the conventional models, such as BiLSTM, 1DCNN, TCN, and Transformer. In summary, the 1DCNN-BiLSTM-DQN model can be expected to predict the temperature in duck houses. The findings can also provide data support for early environmental regulation, thereby reducing the risk of environmental stress in meat ducks.

meat ducks  /  temperature prediction  /  deep Q-network  /  long short-term memory neural network  /  convolutional neural network
卢洪龙, 袁俊杰, 李虎林, 荣琪, 花犇, 应诗家, 王纪章. 基于1DCNN-BiLSTM-DQN的肉鸭养殖环境温度预测模型. 农业工程学报, 2026 , 42 (12) : 73 -82 . DOI: 10.11975/j.issn.1002-6819.202512200
Honglong LU, Junjie YUAN, Hulin LI, Qi RONG, Ben HUA, Shijia YING, Jizhang WANG. Temperature prediction models for meat duck breeding environment using CNN-BiLSTM-DQN[J]. Transactions of the Chinese Society of Agricultural Engineering, 2026 , 42 (12) : 73 -82 . DOI: 10.11975/j.issn.1002-6819.202512200
2024年,中国肉鸭出栏总量达42.2亿只,产肉量约1000万t,产业总产值达1284亿元,同期国内肉鸭出栏量占全球总出栏量超82%[1]。随着市场消费需求持续扩大,中国肉鸭养殖产业正逐步向规模化、集约化方向转变[2]。在集约化养殖场景,鸭舍温度调控滞后会诱发鸭群产生环境应激反应,损害肉鸭生理健康,极端情况下甚至会引发鸭群大规模死亡[2-3]。传统肉鸭养殖多依赖人工经验进行环境管理,缺乏科学的数据支撑与精准的调控依据,难以提前捕捉温度变化趋势,容易错过环境调控的最佳时机[4-5]。因此,开展禽舍养殖环境温度预测相关研究,准确掌握舍内温度变化规律,是实现环境智能化、精细化调控,减少鸭群环境应激造成的养殖损失的关键举措,对提升肉鸭品质与经济效益,具有重要的理论意义与实际应用价值。
为提升禽舍与温室等农业建筑环境温度预测的准确性,国内外学者针对不同场景下的时间序列特征,构建了多种预测模型。早期研究采用灰色模型、模糊理论等方法,通过时间序列窗口滚动机制处理小样本序列的非线性问题[6-7],此类方法对长时序依赖关系的挖掘能力不足。随着数据驱动技术的发展,循环神经网络及其变体被引入,用以捕获温度序列的时间依赖。谢秋菊等[8]使用长短记忆神经网络(long short-term memory,LSTM)对猪舍温湿度变化进行预测,通过冬夏两季的季节特征建模,实现猪舍温度分季节预测,决定系数冬季为0.938,夏季为0.703。贺琳等[9]针对温室环境中时序数据存在的噪声干扰和时序依赖信息挖掘不充分的问题,将双向神经网络模型和注意力机制进行结合,建立温室温度预测模型。胡瑾等[10]将一维卷积神经网络(one-dimensional convolutional neural network,1DCNN)和门控循环单元(gated recurrent unit,GRU)结合构建温室温度预测模型,使用GRU对历史温度数据进行特征提取,模型对1~4 h的温度进行预测,其决定系数为0.970,均方根误差为1.358 ℃,优于1DCNN与GRU模型。郝璇等[11]针对农业设施内温度数据存在不同周期重叠问题,在Transformer架构的基础上,添加傅里叶变换提取多个时序周期特征,实现环境温度的预测,模型的决定系数达到0.918,平均绝对误差0.501 ℃。钟宁帆等[12]针对禽舍内温度数据非线性特点,结合主成分分析法(principal component analysis,PCA)、莱温伯格-马夸特算法(Levenberg-Marquardt,LM)和带外部输入的非线性自回归模型(nonlinear autoregressive with exogenous input,NARX),提出PCA-LM-NARX模型,实现了舍内温度在线预测。刘双印等[13]为提高禽舍温度预测精度,利用主成分分析消除变量之间的冗余信息,构建支持向量回归(support vector regression,SVR)和自回归滑动平均模型(autoregressive moving average,ARMA),使用SVR对气温进行预测,再由ARMA模型的残差预测值修正空气温度预测结果,该模型平均绝对误差为0.1832 ℃,均方根误差为0.4540 ℃。上述模型可以实现农业建筑内的温度的预测,但是模型的超参数在训练后无法随外界环境变化动态调整,模型的环境适应性较差,尤其是在季节交替或极端天气场景下,模型的自适应能力不足,预测精度下降。因此,亟需探索能够根据环境动态变化实时优化超参数的温度预测方法。
为弥补传统时间序列预测模型动态适配性差,提升模型的预测精准性和稳定性,研究者从模型参数迭代优化方面进行改进[14-16]。黄铝文等[17]利用网格搜索方法对基于Informer架构和长短记忆神经网络的温度预测模型进行超参数优化,以提升模型对冠层温度预测精度,模型的决定系数达到0.978,与基础Informer相比,均方根误差降低了0.448 ℃;PEREA等[18]将遗传算法和Transformer结合,进行未来一周的灌水量预测,结果表明和基准TNN(transform neural network)模型相比,所建立模型的预测准确率提高了89.8%;吴佳等[19]利用长短期记忆网络构建智能体自动选择机器学习算法模型及对应的超参数组合。采用两种标准机器学习数据集进行测试,结果表明通过搭建智能体筛选的模型分类准确度达到0.9875,标准差为0.00936。上述研究表明,通过模型参数迭代优化可以提升模型动态适应性和预测的准确性。因此,将参数迭代优化模型引入到禽舍养殖环境温度的预测,可以提升模型对环境动态变化的适应性。
基于此,针对鸭舍温度时序信号强非线性、多周期叠加以及现有模型超参数固定导致突变环境下预测精度不足的问题,提出一种1DCNN-BiLSTM-DQN组合预测模型。考虑到温度序列中高频分量主要包含局部特征、低频分量包含长时间依赖特征,通过离散傅里叶变换将时序数据分解为高、低频分量。使用1DCNN提取高频分量的局部特征,使用BiLSTM(bidirectional long short-term memory)提取低频分量的长时序依赖特征,并将两类特征拼接后经全连接层映射得到温度预测值。针对1DCNN-BiLSTM模型在面对突变环境下预测精度不足问题,通过深度Q网络(deep Q-Network,DQN)搭建智能体实现预测模型的超参数迭代优化,以提升模型在面对复杂天气下的预测精度与鲁棒性,为鸭舍养殖环境智能调控提供技术支撑。
本研究数据来源于江苏省扬州市高邮市高邮鸭集团14号网养鸭舍,试验鸭舍长度101 m,宽度12 m,夏季通过侧窗通风和湿帘风机降温,冬季通过侧窗和风机通风保证室内空气质量。通过在鸭舍内部署温度传感器(搜博SM2110B、温度测量范围−30~85 ℃,测量精度为± 0.5 ℃,通讯方式为RS485 MODBUS-RTU标准协议格式),采集时间为2025年3月22日—2026年3月22日,采样间隔设定为5 min,累计采集数据105408组。按照$ 8:1:1 $划分为训练集、验证集、测试集。
针对采集的环境数据量纲不同,本研究对环境数据进行数据归一化处理。
$ {x}^{\text{,}}=\frac{x-\overline{x}}{\sqrt{\text{var}(x)}} $
式中$ x $是原始变量,$ \overline{x} $是平均值,$ \text{var}\left(x\right) $是方差,$ {x}^{,} $是标准化值。
图1为网养鸭舍舍内外的周年温度变化曲线,鸭舍全年舍内外温度呈现明显季节波动,舍内温度变化趋势与舍外变化相似。本研究按3个月为一个季节进行时段划分,春季起始于3月下旬[20],往后顺延依次划定夏季、秋季与冬季。春季舍外温度呈上升趋势,相对于舍外温度变化,舍内温度回升较为平缓;夏季受高温影响,舍外温度升高,此时舍内启动湿帘风机进行降温增湿,有效抑制了舍内温度升高,舍内温度虽有上升但峰值明显低于舍外;秋季舍内外温度同步回落,舍内降温过程更为平缓;冬季舍外温度持续降低,此时鸭舍通过关闭侧窗并减少风机运行数量加强保温,使得舍内温度明显高于舍外。
针对传统温度预测方法难以充分捕捉多尺度信息,导致模型预测精度下降的问题,本文提出基于频域分解的双通道特征提取架构。如图2所示,模型由1DCNN-BiLSTM和DQN模块组成,采用离散傅里叶变换将温度数据分解为高频分量和低频分量,其中,高频分量为日内短周期的波动特征,低频分量为季节性波动特征,由此将周期重叠的时序特征转化为可独立建模的两类信号。在此基础上,利用1DCNN提取高频分量中的局部特征,利用BiLSTM提取低频分量中的长时序依赖特征,将两类特征通过拼接策略实现多尺度融合,经全连接层映射得出温度预测结果。针对模型的超参数依赖人工调试、极端天气适应性差的问题,将深度Q网络引入鸭舍温度预测模型,构建DQN智能体实现模型参数优化调整。DQN智能体以预测误差为反馈信号,通过与环境交互,自动搜索学习率、隐藏层数、Dropout率等关键超参数的最优组合,提升模型的预测精度。
由于鸭舍温度序列中存在多重周期相互叠加与影响,导致时序建模难度增加。因此,充分提取温度数据中的多周期特征对精确预测鸭舍温度至关重要。本研究利用离散傅里叶变换分析鸭舍内温度时序数据中蕴含的周期叠加情况,将温度分解为高频分量($ {X}_{\text{high}} $)和低频分量($ {X}_{\text{low}} $)。温度信号$ S\left(k\right) $的离散傅里叶变换(discrete Fourier transform,DFT)可以表示为
$ \text{S}\left(k\right)=\sum\limits_{n=0}^{N-1}x\left(n{T}_{s}\right){e}^{-{\mathrm{j}}\frac{\text{2π}}{N}kn} $
式中$ S\left(k\right) $为离散傅里叶变换输出序列;$ x $为离散采样值,℃;$ {T}_{s} $为采用周期,min;N为总采样点数(N=8760),$ \mathrm{j} $为虚数单位;k为频率分量;$ n $为采样索引。
频率分量k对应的离散周期$ {T}_{k} $(min)定义为
$ {T}_{k}=\frac{N}{k}(k=1,2,\cdots ,N\slash 2 ) $
卷积神经网络(convolutional neural network,CNN)最早由LECUN等[21]在1998年提出。CNN深度学习模型的核心构件为卷积层与池化层。卷积层借助卷积运算提取数据中的局部关键特征,池化层在保留重要信息的前提下完成特征降维,二者配合实现高效的特征提取与特征压缩。针对离散傅里叶变换的高频分量数据,使用1DCNN的卷积核在时间维度滑动,提取时序数据的局部特征。
1DCNN由3层一维卷积堆叠构成,卷积核大小分别为5、3、3,通道数依次为32、64、128,其中,第1层采用大卷积核以快速扩大感受野、捕捉较宽范围的趋势变化,后2层采用较小卷积核,在第1层感受野基础上提取更具判别力的局部特征。为加速网络收敛,增强非线性表达能力,在每层卷积后接入批归一化与ReLU激活函数。沿时间维度做操作卷积,最终通过全局自适应平均池化将整个时序维压缩为单一表示,输出b个样本128维的特征向量$ [b,128] $
在时序数据处理中,1DCNN模块通过卷积核在时间维度滑动,有效提取局部空间特征,其固定感受视野的特性难以有效捕捉长时序依赖关系[22-23]。针对这个问题,引入LSTM模型作为补充机制,考虑到单向LSTM仅基于历史数据$ ({t}_{0}\rightarrow t) $生成隐藏状态$ {h}_{t} $,无法访问未来时刻$ (t\rightarrow {t}_{n}) $的信息。本文采用2个独立的LSTM进行叠加,构建双向LSTM结构,同时捕获温度序列的前向与后向时序依赖关系。BiLSTM结构如图3所示。前向LSTM层处理序列$ [{x}_{1},{x}_{2}\cdots {x}_{t}] $,输出前向隐藏状态$ \overrightarrow{{{h}_{t}}} $,后向LSTM层处理序列$ [{x}_{t},{x}_{t-1}\cdots {x}_{0}] $,输出后向隐藏状态$ \overleftarrow{ h_t} $,将前向LSTM和后向LSTM输出的特征结果进行叠加,输出b个样本256维的特征向量$ [b,256] $
图4为特征融合与预测过程,将1DCNN模块提取的高频分量的128维特征向量和BiLSTM模块提取的低频分量的256维特征向量进行拼接,得到384维的特征向量,拼接后的向量经过三层全连接层网络逐级降维,最终实现温度预测。
1)为了防止过拟合,融合后的特征向量先经Dropout正则化层处理后送入全连接层1。全连接层1对融合后的向量中每一个元素$ {f}_{i} $,分别乘以对应的权重$ w_{pi}^{1} $,求和并加上偏置$ b_{p}^{1} $后,通过ReLU激活函数进行非线性映射,得到64维的特征向量$ {{\boldsymbol{h}}_p^1} $。计算如式(4)。
$ {\boldsymbol{h}}_{p}^{1}=\text{ReLU}\left(\sum\limits_{i=1}^{384}w_{pi}^{1}{f}_{i}+b_{p}^{1}\right) $
2)全连接层2对全连接层1输出的向量$ {\boldsymbol{h}}_{p}^{1} $中每一个元素分别乘以对应的权重$ w_{qp}^{2} $,求和并加上偏置$ b_{q}^{2} $后,激活ReLU激活函数进行非线性映射,得到32维的特征向量。计算如式(5)所示。
$ {\boldsymbol{h}}_{q}^{2}=ReLU\left(\sum\limits_{p}^{64}w_{qp}^{1}h_{p}^{1}+b_{q}^{2}\right) $
3)全连接层2输出的32维特征向量送入全连接层3,对向量$ {\boldsymbol{h}}_q^2 $中每一个元素分别乘以对应的权重$ w_{q}^{3} $,求和并加上偏置$ b_{\text{stand}}^{3} $,得到降维后的输出$ y_{\text{stand}} $,计算如式(6)所示。
$ {y}_{\text{stand}}=\sum\limits_{q}^{1}w_{q}^{3}h_{q}^{2}+b_{\text{stand}}^{3} $
最终将$ {y}_{\text{stand}} $通过StandardScaler逆变换得到鸭舍实际温度预测值$ {T}_{\text{Actual}} $。逆变换计算式如下:
$ {T}_{\text{Actual}}={y}_{\text{stand}}\sigma +\mu $
式中$ \sigma $$ \mu $为训练集目标温度的均值与标准差。
强化学习的核心是构建智能体,使其在与环境不断交互的过程中,通过试错迭代学习最优策略,以实现收益最大化。强化学习智能体主要是基于值函数或者梯度策略的学习方法,分为Q学习和深度Q网络[24]。针对1DCNN-BiLSTM模型在外界极端天气环境变化下预测精度低的问题,本文使用深度Q网络搭建智能体对1DCNN-BiLSTM的超参数进行迭代优化,提高温度预测精度。图5为DQN智能体的结构图,DQN智能体采用双网络结构,其中主网络通过贪婪选择机制在动作序列中进行动作选择,通过损失函数完成参数更新;为提高智能体的稳定性,模型定期将主网络的参数复制到目标网络中并完成更新,确保目标网络与主网络参数保持同步[25]。此外,为了维持样本数据的时效性,提高数据利用率,引入经验回放机制,通过在经验存储缓冲区中存储大量样本数据,使智能体在与环境交互过程中能够随机抽取多组数据进行训练[26]。该机制要求在训练开始前预先存储充足的数据样本作为训练集。因此,在模型训练阶段会持续采集新样本并缓存至经验存储缓冲区,一旦缓存容量达到预设阈值,系统会采用先进先出原则,通过新样本更替历史旧样本,始终维持样本数据的时效性。
智能体建立过程如下:
1)建立状态矩阵,状态空间S定义为8维连续空间,在时刻t的状态向量包含当前超参数配置、训练进度和模型性能信息。
$ \boldsymbol{S}=\left[{\boldsymbol{S}}_{\mathbf{1}}\right.\text{,}{\boldsymbol{S}}_{2},...,\left.{\boldsymbol{S}}_{8}\right] $
式中$ \boldsymbol{S} $为状态矩阵;$ {\boldsymbol{S}}_{\mathbf{1}}\sim {\boldsymbol{S}}_{\mathbf{8}} $为8维状态分量。
超参数状态分量$ {\boldsymbol{S}}_1 $通过归一化处理确保数值稳定;学习率状态分量$ \boldsymbol{S}_2 $通过归一化计算映射到0$ \sim $2范围;隐藏层大小状态分量$ {\boldsymbol{S}}_3 $以128为基准进行归一化;网络层数状态分量$ {\boldsymbol{S}}_4 $反应网络深度;正则化状态分量$ {\boldsymbol{S}}_5 $使用原始值;优化器类型状态分量$ {\boldsymbol{S}}_6 $采用二进制编码,其中Adam优化[27]器为1,其余优化器为0;训练进度状态分量$ {\boldsymbol{S}}_7 $反应当前训练进展,帮助智能体平衡探索和效率;模型性能状态$ S_8 $通过归一化误差指标提供性能反馈。
2)生成动作序列,智能体动作空间A包含12个离散动作,分为连续参数调整和离散参数切换两类。连续参数调整对学习率、隐藏层大小、网络层数、Dropout率大小等参数进行调整,通过逐步优化确定最优参数配置[28]。所有连续参数调整都包含有边界条件限制,确保参数在合理范围内。离散参数切换动作用于优化器类型选择,优化器选择直接改变优化算法,采用二进制编码在状态空间表示,动作遵循对称原则,每个连续参数调整都有增减两个动作,确保调整的灵活性和可逆性。
3)状态转移,状态转移遵循确定参数的更新机制,对于连续的参数调整动作计算如下:
$ {\boldsymbol{S}}_{\boldsymbol{t}+\mathbf{1}}={\boldsymbol{S}}_{\boldsymbol{t}}+{\boldsymbol{e}}_{\left({S}_{i}\right)}\Delta {a}_{t}+{e}_{perf}{\Delta }_{perf\left({a}_{t}\right)} $
式中St+1为下一个状态矩阵,St为当前状态矩阵,$ {\boldsymbol{e}}_{\left(S_i\right)} $为参数Si的单位基向量,$ \Delta\mathit{{a}_{{t}}} $为对应向量在状态空间的参数调整量,eperf为性能状态选择量,$ \Delta $perf(at)为性能状态变化量。
4)损失函数与奖罚机制,建立损失函数如下:
$ L\left(\theta \right)=\frac{1}{N}\sum\limits_{i=1}^{N}\left({Q}_{\max }\left({s}_{t},{a}_{t},{\theta }_{\max }\right)-{Q}_{\text{tar}}\left({s}_{t},{a}_{t},{\theta }_{\text{tar}}\right)\right)_{i}^{2} $
式中$ L\left(\theta \right) $为网络参数的损失函数,N为样本容量,$ i $为选取的样本,$ {Q}_{\max }\left({s}_{t},{a}_{t},{\theta }_{\max }\right) $为在$ \boldsymbol{S} $状态下的最大$ Q $值。针对简单奖励机制的不足,本研究设计了复合奖励机制,主要包括:1)RMSE改善奖励,当模型拟合的RMSE降低时奖励值为正值,反之为负值;2)R2改善奖励机制,当模型拟合度提升时奖励值为正值,反之为负值。惩罚项主要是学习率惩罚和网络规模惩罚。同时为了激励寻找到最优参数组合,添加突破性激励机制。
5)动作选择,智能体依据当前状态与$ Q $值所对应的动作状态,以及$ \varepsilon $-贪婪机制进行动作选择,选择机制如下:
$ {a}_{s}=\begin{cases} {a}_{\text{random}}p\geq \varepsilon \\\mathrm{argmax}Q\left(s,a,\theta \right)p< \varepsilon\end{cases} $
式中$ \text{argmax}Q\left(s,a,\theta \right) $为能获得的最大$ Q $值的动作,$ {a}_{\text{random}} $为随机挑选一个动作。为平衡探索与利用,引入了动态调整探索率$ \varepsilon $$ \varepsilon $会随着训练进程t按指数衰减。
$ { \varepsilon }({t})=\max \left(0.01,1\times {{{d}_{t}}}^{t}\right) $
式中$ {d}_{t} $为衰减因子,设置为0.995。
6)Q值计算,智能体通过当前动作对应的奖励和衰减后未来奖励的最大值计算下一Q值,计算如下:
$ {Q}_{\left({s}_{t},{a}_{t},{\theta }_{\text{tar}}\right)}={r}_{t+1}+\gamma {Q}_{\text{tar}}\left({s}_{t+1},{a}_{t}\left({s}_{t+1},{\theta }_{\max }\right);{\theta }_{\text{tar}}\right){d}_{t} $
式中$ \gamma $为折扣因子,表示未来动作所获得Q值在本次计算中占据的比例;$ {r}_{t+1} $为下一状态获得的奖励值;$ {\theta }_{\text{tar}} $为目标网络中的参数。
本研究模型训练环境使用python3.14.0,pytorch2.9.1框架实现,处理器为AMD Ryzen 54600U。
研究采用搭建的DQN智能体,经多次试验动态调整模型的超参数,1DCNN-BiLSTM和DQN智能体采用表1所示模型参数,批处理大小Batcn_size=64,Dropout正则化层比例设置为0.2。
为评价网养鸭舍温度预测模型性能,选取平均绝对误差(mean absolute error,MAE)、均方根误差(root mean square error,RMSE)和决定系数(coefficient of determination,R2)。具体计算表达式分别如下。
$ \text{MAE=}\frac{1}{n}\sum\limits_{i=1}^{n}\left| {y}_{i}-{\acute{y}}_{i}\right| $
$ \text{RMSE=}\sqrt{\frac{1}{n}\sum\limits_{i=1}^{n}{\left({y}_{i}-{\acute{y}}_{i}\right)}^{2}} $
$ {R}^{2}=1-\frac{\displaystyle\sum\nolimits_{i=1}^{n}{\left({y}_{i}-{\acute{y}}_{i}\right)}^{2}}{\displaystyle\sum\nolimits_{i=1}^{n}{\left({y}_{i}-\overline{y}\right)}^{2}} $
式中$ {y}_{i} $为实际值,$ {\acute{y}}_{i} $为预测值,$ \overline{y} $为实际值的均值,n为观测的个数。
为了验证1DCNN-BiLSTM-DQN温度预测模型的性能,使用采集的网养鸭舍温度数据,选取近年主流算法BiLSTM、1DCNN、TCN、Transformer等4类模型[29]进行比较。表2为不同模型的预测结果对比,从表中可以看出,1DCNN模型性能优于TCN、Transformer和BiLSTM等模型。
而1DCNN模型在引入BiLSTM后,MAE降低为0.15,RMSE降低为0.22,R2提高到0.99,模型性能得到明显的提升。
为验证搭建的DQN智能体在环境突变情况下对预测模型的优化效果,在不同天气条件下,对固定参数(1DCNN-BiLSTM)模型与DQN智能体优化参数(1DCNN-BiLSTM-DQN)模型的温度预测性能进行了对比分析,结果如表3所示。固定参数模型在面对不同天气时预测精度差异明显,在阴天情况下,由于舍外温度和光照变化较为平缓,模型预测精度高;晴天情况下,由于光照变化导致温度变化幅度较大,模型预测精度变差;在雨天情况下,由于天气发生突变,导致模型的预测误差变大。经过DQN智能体迭代优化模型超参数后,3种天气下的R2均明显增加,MAE和RMSE降低。表明搭建的DQN智能体能根据外界环境变化自适应调整模型的学习率、Dropout率等关键超参数,有效提升模型在复杂气象条件下的预测精度与鲁棒性。
为进一步验证所提出的模型在不同输入步长下的性能,本研究设置在不同输入步长(24、48、72)下,对比了1DCNN-LSTM、1DCNN-BiLSTM、1DCNN-BiLSTM-DQN 3个模型在不同季节的预测性能,结果如表4所示。
由于全年温度呈现季节性过渡的波动,当步长从24扩展至48时,1DCNN-BiLSTM和1DCNN-BiLSTM-DQN模型的MAE和RMSE均明显降低,体现了BiLSTM提取的长时序依赖特征对季节过渡特征的捕捉能力;而步长增加到72步时,由于对短期波动的局部特征捕捉能力变弱,模型的MAE和RMSE又增加。
夏季由于白天持续高温,鸭舍会进行湿帘风机降温,温度会出现明显的短期波动。1DCNN-LSTM和1DCNN-BiLSTM模型MAE和RMSE随着步长的增加而增加,表明模型对环境调控导致短期波动的局部特征提取能力变差。而1DCNN-BiLSTM-DQN模型随着步长的增加,RMSE均降低,MAE在从步长从48增加到72时略有增加。表明通过DQN的参数优化,模型对环境短期波动变化适应能力得到明显增强。
秋末冬初,在48步长时,1DCNN-BiLSTM-DQN的MAE和RMSE较1DCNN-LSTM降低65.4%和64.3%;较1DCNN-BiLSTM降低57.8%和56.8%,进一步说明通过DQN强化学习后模型能够适应秋冬季气温骤变的情况。
显著性t检验表明,1DCNN-BiLSTM-DQN在24、48、72步长的预测误差均显著低于对照组模型(P<0.05),在48步长下模型预测性能最佳。表明输入步长的扩展可以提升模型对长程依赖的捕捉能力,但是过长的步长由于丢失了局部特征,又会影响模型的预测性能。
为验证离散傅里叶变换高低频分量分解对模型的复杂度的影响,本文选择 1DCNN 模型、 BiLSTM 模型、未引入离散傅里叶变换的基础1DCNN-BiLSTM 模型,以及经离散傅里叶变换对输入温度数据进行高低频分量分解的改进 1DCNN-BiLSTM 模型4组模型开展试验,结果如表5所示。单一1DCNN模型训练时长和参数量较小,但是模型精度不高。1DCNN-BiLSTM 模型训练时长和参数量均较大,但在引入离散傅里叶变换高低频分量分解的改进后,MAE 降至0.15 ℃,训练时长缩短至49.58 s,参数量减少至194 K,模型的预测精度得到明显改善。表明通过离散傅里叶变换预处理能够有效增强温度序列的特征可分性,实现更高的预测精度,同时降低模型的训练成本与计算复杂度。
为确定离散傅里叶变换最优频率分量组合,本文设计DFT频率分量选择消融试验,分别选取k=2、4、52为低频分量,k=365、730、1460为高频分量,结果如表6所示。
试验结果表明,当低频分量分解周期为4(6 h),高频分量周期为1460(30 d)时,模型的预测误差最小,高低频分量计算式如下:
$ \begin{cases} {X}_{\text{high}}=\displaystyle\sum\limits_{n=0}^{8759}x\left(n\right){e}^{-\text{j}\frac{2960n\text{π}}{8760}}\\{X}_{\text{low}}=\displaystyle\sum\limits_{n=0}^{8759}x\left(n\right){e}^{-\text{j}\frac{8n\text{π}}{8760}}\end{cases} $
式中$ {X}_{\text{high}} $为高频分量,℃;$ {X}_{\text{low}} $为低频分量,℃;$ x(n) $为温度时序采样值,℃。
为验证特征拼接模型对长短时序特征融合的有效性,分别使用注意力机制融合[30](attention fusion)、加权自适应融合策略[31](weighted fusion)替换原始模型的直接拼接模型,采用相同数据集下测试,模型预测结果如表7所示。直接拼接策略的RMSE为0.74,低于注意力机制融合与加权自适应融合方法;直接拼接策略的R2达0.99,模型拟合效果最佳;直接拼接策略的训练时间为26.38 s,只高于注意力机制4.92 s,因此本研究中选择直接拼接模型可以保证特征融合拼接的有效性和时效性。
为验证搭建的DQN智能体在模型超参数优化中的优势,使用网格搜索、随机搜索两类传统优化方法[26]替换原始模型中的DQN智能体,试验结果如表8所示。
在模型预测精度方面,经过DQN智能体优化参数模型的RMSE为0.61 ℃,低于网格搜索的0.62 ℃和随机搜索的0.66 ℃;DQN智能体优化模型的R2为0.99,高于网格搜索的0.97与随机搜索的0.96,模型拟合效果最优。
在搜索效率方面,DQN智能体优化仅用15次试验即完成优化,少于网格搜索与随机搜索的25次;DQN智能体的训练时长为209.5 s,高于网格搜索的163.5 s,但显著低于随机搜索的406.0 s。综合精度与效率来看,DQN智能体能够以更少的试验次数达到更优的模型性能,在模型超参数优化中具有较高的能力。
为验证奖励函数权重设置的合理性,试验中保持状态维度为8、动作维度为12不变,对奖励函数权重进行消融试验。试验中设置RMSE与R2奖励函数的权重比例为1:1 、5:10、10:5 和 15:5 ,试验结果如表9所示。1:1权重比例下MAE、RMSE和迭代次数均最高;5:10与15:5两组收敛迭代次数较低,但预测误差高于10:5;权重比例为10:5时各项预测指标表现优异,因此确定RMSE与R2奖励权重比例10:5为本模型的最佳配置。
本文提出一种肉鸭养殖环境温度预测模型,该模型采用离散傅里叶变换分解温度时序数据为高频与低频分量,分别利用一维卷积神经网络提取局部特征、双向长短时记忆网络提取长时序依赖特征,并经深度Q网络动态优化超参数实现鸭舍温度预测。利用全年实测数据对模型进行了验证,得出以下结论。
1)本文将离散傅里叶变换引入到鸭舍温度预测,构建了“频域分解—双通道特征提取”的预测框架,解决了时序数据中多尺度信息难以充分捕捉的问题。
2)DQN智能体通过动态优化模型的学习率、Dropout率等关键超参数,弥补了传统预测方法在环境突变场景下自适应能力不足的缺陷。
3)所提出的1DCNN-BiLSTM-DQN模型相较于时间卷积神经网络,Transformer等预测方法具有更低的预测误差,可为鸭舍环境智能调控提供精准的数据支撑,并具备推广至其他畜禽养殖场景的潜力。
4)模型预测性能依赖历史数据的完整性与代表性,尤其是极端天气事件样本不足时误差可能增大。此外,在DQN强化学习中,奖励函数权重虽在当前数据集下最优,但在不同气候区或不同养殖模式下可能需要重新校准。后续研究可引入多种环境变量(湿度、光照等)和养殖密度作为辅助输入,并结合迁移学习或元学习策略,提升模型在数据稀缺场景下的适应能力。

参考文献 引证文献
排序方式:
1
侯水生, 刘灵芝. 2024年水禽产业与技术发展报告[J]. 中国畜牧杂志, 2025, 61(3): 383-387.
2
包旭梅, 谢芳宇, 刘灵芝. 我国肉鸭产业养殖效率及影响因素分析[J]. 饲料研究, 2025, 48(5): 175-180.
BAO Xumei, XIE Fangyu, LIU Lingzhi. Analysis on breeding efficiency and influencing factors of meat duck industry in China[J]. Feed Research, 2025, 48(5): 175-180. (in Chinese with English abstract)
3
管清苗, 丁为民, 郭彬彬, 等. 山东夏冬季节层叠式笼养肉鸭舍环境参数测定[J]. 农业工程学报, 2020, 36(20): 246-253.
GUAN Qingmiao, DING Weimin, GUO Binbin, et al. Measurement of environmental parameters of cascading caged-rearing duck houses in Shandong of China in summer and winter[J]. Transactions of the Chinese Society of Agricultural Engineering (Transactions of the CSAE), 2020, 36(20): 246-253. (in Chinese with English abstract)
4
邢伟杰, 金波, 石诗影, 等. 家禽养殖环境调控关键技术与设施设备研究进展[J]. 中国家禽, 2025, 47(3): 149-156.
XING Weijie, JIN Bo, SHI Shiying, et al. Research progress on key technologies and facilities for poultry breeding environment regulation[J]. China Poultry, 2025, 47(3): 149-156. (in Chinese with English abstract)
5
王生雨, 亓丽红, 杨小华, 等. 当前肉鸭饲养存在的问题及对策[J]. 农业工程学报, 2006, 22(14): 142-145.
WANG Shengyu, QI Lihong, YANG Xiaohua, et al. Problems in currently raising broiler duck and the counterstrategy[J]. Transactions of the Chinese Society of Agricultural Engineering (Transactions of the CSAE), 2006, 22(14): 142-145. (in Chinese with English abstract)
6
WANG Y, ZHENG W, LI B. Application of a novel grey model for forecasting indoor air temperature in poultry houses: Control strategy[J]. Journal of the ASABE, 2022, 65(3): 505-513.
7
钱东平, 王建新, 隋美丽, 等. 畜禽舍环境温度监控系统模糊控制算法的实现[J]. 农业机械学报, 2005, 36(12): 95-98.
QIAN Dongping, WANG Jianxin, SUI Meili, et al. Implementation of fuzzy control algorithm for environmental temperature monitoring system in livestock and poultry houses[J]. Transactions of the Chinese Society for Agricultural Machinery, 2005, 36(12): 95-98. (in Chinese with English abstract)
8
谢秋菊, 郑萍, 包军, 等. 基于深度学习的密闭式猪舍内温湿度预测模型[J]. 农业机械学报, 2020, 51(10): 353-361.
XIE Qiuju, ZHENG Ping, BAO Jun, et al. Temperature and humidity prediction model inside enclosed pig houses based on deep learning[J]. Transactions of the Chinese Society for Agricultural Machinery, 2020, 51(10): 353-361. (in Chinese with English abstract)
9
贺琳, 李响, 杜继兵, 等. 双向时序数据驱动的玻璃温室环境变量预测模型[J]. 农业工程学报, 2026, 42(9): 302-310.
HE Lin, LI Xiang, DU Jibin, et al. Predicting environmental variables in a greenhouse using a bidirectional temporal data-driven model[J]. Transactions of the Chinese Society of Agricultural Engineering (Transactions of the CSAE), 2026, 42(9): 302-310. (in Chinese with English abstract)
10
胡瑾, 雷文晔, 卢有琦, 等. 基于1DCNN-GRU的日光温室温度预测模型研究[J]. 农业机械学报, 2023, 54(8): 339-346.
HU Jin, LEI Wenye, LU Youqi, et al. Research on temperature prediction model of solar greenhouse based on 1D CNN-GRU[J]. Transactions of the Chinese Society for Agricultural Machinery, 2023, 54(8): 339-346. (in Chinese with English abstract)
11
郝璇, 任守纲, 舒欣, 等. 基于TimesTransformer的农业设施环境预测与调控研究[J]. 南京农业大学学报, 2026, 49(3):653-664.
HAO Xuan, REN Shougang, SHU Xin, et al. Research on environmental prediction and regulation of agricultural facility environment based on TimesTransformer [J].Journal of Nanjing Agricultural University, 2026, 49( 3) : 653-664. (in Chinese with English abstract)
12
钟宁帆, 高鲁宁, 贺凯迅, 等. 基于PCA-LM-NARX的禽舍室温预测模型[J]. 农业工程学报, 2025, 41(2): 261-270.
ZHONG Ningfan, GAO Luning, HE Kaixun, et al. Poultry house room temperature prediction model based on PCA-LM-NARX[J]. Transactions of the Chinese Society of Agricultural Engineering (Transactions of the CSAE), 2025, 41(2): 261-270. (in Chinese with English abstract)
13
刘双印, 黄建德, 徐龙琴, 等. 基于PCA-SVR-ARMA的狮头鹅养殖禽舍气温组合预测模型[J]. 农业工程学报, 2020, 36(11): 225-233.
LIU Shuangyin, HUANG Jiande, XU Longqin,. et al. Combined model for prediction of air temperature in poultry house for lion-head goose breeding based on PCA-SVR-ARMA[J]. Transactions of the Chinese Society of Agricultural Engineering (Transactions of the CSAE), 2020, 36(11): 225-233. (in Chinese with English abstract)
14
YANG S, LI F, HAZRA A. Iterative optimization of the maximum directional distance function model for Chinese airline transportation efficiency evaluations[J]. Journal of Engineering, 2026(1):6103732
15
左志宇, 牟晋东, 毛罕平, 等. 基于深度强化学习的温室环境协调控制系统设计[J]. 农机化研究, 2025, 47(5): 22-27.
ZUO Zhiyu, MOU Jindong, MAO Hanping, et al. Design of greenhouse environment coordinated control system based on deep reinforcement learning[J]. Agricultural Mechanization Research, 2025, 47(5): 22-27. (in Chinese with English abstract)
16
OKADA J, HASHIMOTO F, MORI N. Reduction of order of device hamiltonian with adaptive moment estimation[J]. Japanese Journal of Applied Physics, 2021, 60: SBBH08
17
黄铝文, 刘宇航, 屈昆仪, 等. LSTM与Informer融合预测冠层区域温度[J]. 农业工程学报, 2025, 41(8): 222-232.
HUANG Lyuwen, LIU Yuhang, QU Kunyi, et al. Canopy area temperature prediction with fusion of LSTM and Informer[J]. Transactions of the Chinese Society of Agricultural Engineering (Transactions of the CSAE), 2025, 41(8): 222-232. (in Chinese with English abstract)
18
PEREA G R, POYATO C E, DIAZ RJ. Attention is all water need: Multistep time series irrigation water demand forecasting in irrigation disctrics[J]. Computers and Electronics in Agriculture, 2024, 218: 108723.
19
吴佳, 陈森朋, 陈修云, 等. 基于强化学习的模型选择和超参数优化[J]. 电子科技大学学报, 2020, 49(2): 255-261.
WU Jia, CHEN Senpeng, CHEN Xiuyun, et al. Model selection and hyperparameter optimization based on reinforcement learning[J]. Journal of University of Electronic Science and Technology of China, 2020, 49(2): 255-261. (in Chinese with English abstract)
20
YANG K, WANG T, MIAO J, et al. Asymmetric spring–summer responses of interannual dry–wet transitions in eastern asia and north america under global warming[J]. Geophysical Research Letters, 2026, 53(10): e2026GL122510-e2026GL122510.
21
LECUN Y, BOTTOU L. Gradient-based learning applied to document recognition[J]. Proceedings of the IEEE, 1998, 86(11): 2278-2324.
22
祖林禄, 柳平增, 赵妍平, 等. 基于SSA-LSTM的日光温室环境预测模型研究[J]. 农业机械学报, 2023, 54(2): 351-358.
ZU Linlu, LIU Pingzeng, ZHAO Yanping, et al. Solar greenhouse environment prediction model based on SSA-LSTM[J]. Transactions of the Chinese Society for Agricultural Machinery, 2023, 54(2): 351-358. (in Chinese with English abstract)
23
张观山, 丁小明, 何芬, 等. 基于LSTM-AT的温室空气温度预测模型构建[J]. 农业工程学报, 2024, 40(18): 194-201.
ZHANG Guanshan, DING Xiaoming, HE Fen, et al. Predicting greenhouse air temperature using LSTM-AT[J]. Transactions of the Chinese Society of Agricultural Engineering (Transactions of the CSAE), 2024, 40(18): 194-201. (in Chinese with English abstract)
24
PENG F P, XUE G, YA L Z. Multi-uavs task allocation method based on MPSO-SA-DQN[J]. Measurement and Control, 2025, 58(8): 963-978.
25
李潇宇, 张君华, 郭晓光, 等. 基于强化学习的机器人底盘能量管理与路径规划优化算法[J]. 农业工程学报, 2024, 40(21): 175-183.
LI Xiaoyu, ZHANG Junhua, GUO Xiaoguang, et al. Reinforcement learning-based optimization algorithm for energy management and path planning of robot chassis[J]. Transactions of the Chinese Society of Agricultural Engineering (Transactions of the CSAE), 2024, 40(21): 175-183. (in Chinese with English abstract)
26
WU J, CHENG L, CHU S S, et al. An autonomous coverage path planning algorithm for maritime search and rescue of persons-in-water based on deep reinforcement learning[J]. Ocean Engineering, 2024, 291(c): 116403.1-116403.21.
27
KLOTZ D F, RIBEIRO R, ENEMBRECK F, et al. Estimating and tuning adaptive action plans for the control of smart interconnected poultry condominiums[J]. Expert Systems with Application, 2022, 187: 115876.
28
胡洁, 张亚莉, 王团, 等. 基于深度强化学习的农田节点数据无人机采集方法[J]. 农业工程学报, 2022, 38(22): 41-51.
HU Jie, ZHANG Yali, WANG Tuan, et al. UAV collection methods for the farmland nodes data based on deep reinforcement learning[J]. Transactions of the Chinese Society of Agricultural Engineering (Transactions of the CSAE), 2022, 38(22): 41-51. (in Chinese with English abstract)
29
秦立峰, 周馨怡, 高延年, 等. 基于CNN与Transformer混合模型的自然场景奶牛身份重识别[J]. 农业工程学报, 2026, 42(5): 299-311.
QIN Lifeng, ZHOU Xinyi, GAO Yannian, et al. Cow re-identification in natural scenes using a CNN-transformer hybrid model[J]. Transactions of the Chinese Society of Agricultural Engineering (Transactions of the CSAE), 2026, 42(5): 299-311. (in Chinese with English abstract)
30
QIAO B, WANG Y, YAO L, et al. Attention mechanism fusion neural network for typhoon path prediction[J]. Applied Intelligence, 2024, 55(3): 244-244.
31
KAI S, YONG F Z. Dual-branch adaptive feature fusion network[J]. Neurocomputing, 2026, 669: 132410.
2026年第42卷第12期
PDF下载
226
79
引用本文
BibTeX
文章信息
doi: 10.11975/j.issn.1002-6819.202512200
  • 接收时间:2025-12-23
  • 首发时间:2026-08-20
  • 出版时间:2026-06-30
补充材料
相关文章
文章信息
作者
出版历史
  • 收稿日期:2025-12-23
  • 修回日期:2026-05-29
基金
作者信息
    1江苏大学农业工程学院,镇江 212013
    2江苏省农业科学院畜牧研究所,南京 210014

通讯作者:

王纪章,博士,教授,博士生导师,研究方向农业信息技术。Email:
参考文献
分享链接
https://castjournals.cast.org.cn/joweb/nygcxb/CN/10.11975/j.issn.1002-6819.202512200
分享至
全文二维码

扫描看全文

引用本文
BibTeX
本文的引用情况
2种不同金属材料的力学参数

Family
属数
Number of
genus
种数
Number of
species
占总种数比例
Percentage of
total species (%)

Genus
种数
Number of
species
占总种数比例
Percentage of total
species (%)
鹅膏菌科Amanitaceae 2 11 5.26 鹅膏菌属 Amanita 10 4.78
小菇科 Mycenaceae 2 12 5.74 丝盖伞属 Inocybe 5 2.39
多孔菌科 Polyporaceae 8 14 6.70 蜡蘑属 Laccaria 5 2.39
红菇科 Russulaceae 3 23 11.00 小皮伞属 Marasmius 6 2.87
小菇属 Mycena 11 5.26
光柄菇属 Pluteus 5 2.39
红菇属 Russula 17 8.13
栓菌属 Trametes 5 2.39
关闭全屏