Article(id=1245407859740095214, tenantId=1146029695717560320, journalId=1146123166801305609, issueId=1156262727438951343, articleNumber=null, orderNo=null, doi=10.12404/j.issn.1671-1815.2402625, pmid=null, cstr=null, oa=null, hot=null, price=null, onlineType=0, articleFormat=0, articleType=null, articleTypeStr=research-article, receivedDate=1712764800000, receivedDateStr=2024-04-11, revisedDate=1721923200000, revisedDateStr=2024-07-26, acceptedDate=null, acceptedDateStr=null, onlineDate=1774857972321, onlineDateStr=2026-03-30, pubDate=1741363200000, pubDateStr=2025-03-08, doiRegisterDate=null, doiRegisterDateStr=null, onlineIssueDate=1774857972321, onlineIssueDateStr=2026-03-30, onlineJustAcceptDate=null, onlineJustAcceptDateStr=null, onlineFirstDate=null, onlineFirstDateStr=null, sourceXml=null, magXml=null, createTime=1774857972321, creator=13701087609, updateTime=1774857972321, updator=13701087609, issue=Issue{id=1156262727438951343, tenantId=1146029695717560320, journalId=1146123166801305609, year='2025', volume='25', issue='7', pageStart='2193', pageEnd='3077', issueExtLink='null', onlineDate='null', pubDate='null', beforeIssueId=null, nextIssueId=null, price=null, status=1, issueComplete=1, articleOrder=1, issueType=-1, specialIssue=0, createTime=1753604116544, creator=13701087609, updateTime=1753771263994, updator=13701087609, preIssue=null, nextIssue=null, ext={EN=IssueExt(id=1156963794699248405, tenantId=1146029695717560320, journalId=1146123166801305609, issueId=1156262727438951343, language=EN, specialIssueTitle=, coverIllustrator=, specialIssueEditor=, specialIssueAbout=), CN=IssueExt(id=1156963794699248406, tenantId=1146029695717560320, journalId=1146123166801305609, issueId=1156262727438951343, language=CN, specialIssueTitle=, coverIllustrator=, specialIssueEditor=, specialIssueAbout=)}, issueFiles=null}, startPage=2748, endPage=2759, ext={EN=ArticleExt(id=1245407860381823735, articleId=1245407859740095214, tenantId=1146029695717560320, journalId=1146123166801305609, language=EN, title=Enhanced Whale Optimization Algorithm for Constructing a Back Propagation Neural Network Model for Predicting Grain Yield and Its Effectiveness Analysis, columnId=1156262738117649382, journalTitle=Science Technology and Engineering, columnName=Papers·Agricultural Science, runingTitle=null, highlight=null, articleAbstract=

A hybrid algorithm (IWOA-BP) combining the improved whale optimization algorithm (IWOA) and backpropagation neural network (BP) was proposed to offer theoretical support for the formulation of grain strategies in the agriculture sector and its related industries. By introducing an improved convergence factor, nonlinear inertia weight, and optimal neighborhood disturbance strategy into the modified whale optimization algorithm, the optimal solution of the algorithm was obtained. This solution was then utilized as the initial weights and thresholds of the BP neural network, thereby enhancing the convergence speed and accuracy of the IWOA-BP hybrid algorithm. Subsequently, a grain yield prediction model based on the improved whale optimization algorithm was established using data from China’s grain yield over 45 years and seven influencing factors including effective irrigation area, chemical fertilizer application, rural electricity consumption, total power of agricultural machinery, sowing area of grain crops, disaster-affected area, and per capita consumption expenditure in rural areas. Through extensive experiments on a test set, it was found that the IWOA-BP model consistently outperformed other prediction models such as long short-term memory (LSTM), extreme learning machine (ELM), BP neural network with whale optimization algorithm (WOA-BP), and BP neural network with particle swarm optimization (PSO-BP). Compared to the ELM model, the root mean square error (RMSE) and mean absolute percentage error (MAPE) of the IWOA-BP model were reduced by 77.12% and 88.18% respectively. When compared to the LSTM model, the RMSE and MAPE of the IWOA-BP model were reduced by 69.11% and 47.36% respectively. Furthermore, in comparison to the WOA-BP model, the mean absolute error (MAE), RMSE, and MAPE of the IWOA-BP model were reduced by 43.78%, 43.22% and 45.96% respectively. Additionally, when compared to the PSO-BP model, the MAE, RMSE, and MAPE of the IWOA-BP model were reduced by 89.67%, 90.61% and 90.82% respectively. Therefore, the proposed IWOA-BP prediction model can be effectively used to predict grain yield due to its higher coefficient of determination, smaller prediction error, and faster convergence speed. It has important technical reference value for agricultural departments and relevant policymakers.

, correspAuthors=Yan CHEN, authorNote=null, correspAuthorsNote=null, copyrightStatement=null, 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, authorCompany=null, fund=null, authors=null, authorsList=Jing-jing ZHAO, Yan CHEN), CN=ArticleExt(id=1245407864202834881, articleId=1245407859740095214, tenantId=1146029695717560320, journalId=1146123166801305609, language=CN, title=改进鲸鱼算法构建反向传播神经网络粮食产量预测模型及效果分析, columnId=1156262738235089896, journalTitle=科学技术与工程, columnName=论文·农业科学, runingTitle=null, highlight=null, articleAbstract=

为了给农业及其相关部门制定粮食策略提供理论依据,提出一种基于改进鲸鱼优化算法(improved whale optimization algorithm, IWOA)的反向传播(back propagation, BP)神经网络混合算法(IWOA-BP)。该混合算法先通过引入改进收敛因子、非线性惯性权重和最优邻域扰动策略改进鲸鱼优化算法,再将其最优解赋值给BP神经网络的权值和阈值,最终提高IWOA-BP的收敛速度和收敛精度。选取全国近45年粮食总产量和7种影响因素(有效灌溉面积、化肥施用量、农村用电量、农业机械总动力、粮食作物播种面积、受灾面积和农村人均消费支出)作为数据集,构建基于改进鲸鱼算法的反向传播神经网络粮食产量预测模型。多次实验表明,IWOA-BP模型在测试集上的表现均优于其他预测模型,包括长短期记忆网络(long short-term memory network, LSTM)预测模型、极限学习机(extreme learning machine, ELM)预测模型、基于鲸鱼优化算法的BP神经网络(WOA-BP)预测模型以及基于粒子群算法的BP神经网络(PSO-BP)预测模型。IWOA-BP模型和ELM模型相比,前者的均方根误差(root mean square error,RMSE)、平均绝对百分比误差(mean absolute percentage error,MAPE)分别降低了77.12%、88.18%;和LSTM模型相比,前者的RMSE、MAPE分别降低了69.11%、47.36%;和WOA-BP模型相比,前者的平均绝对误差(mean absolute error, MAE)、RMSE和MAPE分别降低了43.78%、43.22%、45.96%。和PSO-BP模型相比,前者的MAE、RMSE、MAPE分别降低了89.67%、90.61%、90.82%。因此IWOA-BP预测模型的决定系数更高、预测误差更小且收敛速度更快,可有效地预测粮食产量,对于农业部门和相关政策制定者来说具有重要的技术参考价值。

, correspAuthors=陈岩, authorNote=null, correspAuthorsNote=
* 陈岩(1984—),男,汉族,山东菏泽人,博士,副教授。研究方向:最优化理论与算法。E-mail:
, copyrightStatement=null, copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=ILxHXGnFvXnX2YTtkfu5ng==, magXml=e0/IKQni75y7R9nbtDC5EA==, pdfUrl=null, pdf=OT8bgSyWDnJ9HjihzuJKgA==, pdfFileSize=7867054, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=KGJRFcc4NmzYEGOrz6VITg==, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=gsQpjpFAtqkor9T65Bn6ww==, mapNumber=null, authorCompany=null, fund=null, authors=

赵晶晶(2000—),女,汉族,湖北黄石人,硕士研究生。研究方向:最优化理论与算法。E-mail:

, authorsList=赵晶晶, 陈岩)}, authors=[Author(id=1245407864622265329, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1245407859740095214, orderNo=0, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=zhaojingjing0302@163.com, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1245407864781648896, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1245407859740095214, authorId=1245407864622265329, language=EN, stringName=Jing-jing ZHAO, firstName=Jing-jing, middleName=null, lastName=ZHAO, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=College of Information and Mathematics, Yangtze University, Jingzhou 434000, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1245407864886505480, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1245407859740095214, authorId=1245407864622265329, language=CN, stringName=赵晶晶, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=长江大学信息与数学学院, 荆州 434000, bio={"content":"

赵晶晶(2000—),女,汉族,湖北黄石人,硕士研究生。研究方向:最优化理论与算法。E-mail:

"}, bioImg=null, bioContent=

赵晶晶(2000—),女,汉族,湖北黄石人,硕士研究生。研究方向:最优化理论与算法。E-mail:

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1245407864500630498, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1245407859740095214, xref=null, ext=[AuthorCompanyExt(id=1245407864504824804, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1245407859740095214, companyId=1245407864500630498, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=College of Information and Mathematics, Yangtze University, Jingzhou 434000, China), AuthorCompanyExt(id=1245407864513213412, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1245407859740095214, companyId=1245407864500630498, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=长江大学信息与数学学院, 荆州 434000)])]), Author(id=1245407864995557400, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1245407859740095214, orderNo=1, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=191399718@qq.com, emailSecond=null, emailThird=null, correspondingAuthor=1, authorType=1, ext={EN=AuthorExt(id=1245407865171718184, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1245407859740095214, authorId=1245407864995557400, language=EN, stringName=Yan CHEN, firstName=Yan, middleName=null, lastName=CHEN, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=*, address=College of Information and Mathematics, Yangtze University, Jingzhou 434000, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1245407865284964402, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1245407859740095214, authorId=1245407864995557400, language=CN, stringName=陈岩, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=*, address=长江大学信息与数学学院, 荆州 434000, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1245407864500630498, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1245407859740095214, xref=null, ext=[AuthorCompanyExt(id=1245407864504824804, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1245407859740095214, companyId=1245407864500630498, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=College of Information and Mathematics, Yangtze University, Jingzhou 434000, China), AuthorCompanyExt(id=1245407864513213412, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1245407859740095214, companyId=1245407864500630498, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=长江大学信息与数学学院, 荆州 434000)])])], keywords=[Keyword(id=1245407865477902405, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1245407859740095214, language=EN, orderNo=1, keyword=grain yield), Keyword(id=1245407865628897361, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1245407859740095214, language=EN, orderNo=2, keyword=back propagation neural network), Keyword(id=1245407865930887264, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1245407859740095214, language=EN, orderNo=3, keyword=whale optimization algorithm), Keyword(id=1245407869198250094, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1245407859740095214, language=EN, orderNo=4, keyword=nonlinear inertia weighting), Keyword(id=1245407869345050753, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1245407859740095214, language=EN, orderNo=5, keyword=random perturbation strategy), Keyword(id=1245407869529600155, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1245407859740095214, language=CN, orderNo=1, keyword=粮食产量), Keyword(id=1245407869688983728, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1245407859740095214, language=CN, orderNo=2, keyword=反向传播神经网络), Keyword(id=1245407869802229949, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1245407859740095214, language=CN, orderNo=3, keyword=鲸鱼优化算法), Keyword(id=1245407869923864777, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1245407859740095214, language=CN, orderNo=4, keyword=非线性惯性权重), Keyword(id=1245407870070665430, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1245407859740095214, language=CN, orderNo=5, keyword=随机扰动策略)], refs=[Reference(id=1245407873937814175, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1245407859740095214, doi=null, pmid=null, pmcid=null, year=2016, volume=10, issue=6, pageStart=895, pageEnd=903, url=null, language=null, rfNumber=[1], rfOrder=0, authorNames=Mokarram M, Bijanzadeh E, journalName=澳大利亚作物科学学报, refType=null, unstructuredReference=Mokarram M, Bijanzadeh E. 基于多元回归和人工神经网络模型的大麦生物产量和籽粒产量预测[J]. 澳大利亚作物科学学报, 2016, 10(6): 895-903., articleTitle=基于多元回归和人工神经网络模型的大麦生物产量和籽粒产量预测, refAbstract=null), Reference(id=1245407874034283176, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1245407859740095214, doi=null, pmid=null, pmcid=null, year=2016, volume=10, issue=6, pageStart=895, pageEnd=903, url=null, language=null, rfNumber=[1], rfOrder=1, authorNames=Mokarram M, Bijanzadeh E, journalName=Australian Journal of Crop Science, refType=null, unstructuredReference=Mokarram M, Bijanzadeh E. Prediction of biological and grain yield of barley using multiple regression and artificial neural network models[J]. Australian Journal of Crop Science, 2016, 10(6): 895-903., articleTitle=Prediction of biological and grain yield of barley using multiple regression and artificial neural network models, refAbstract=null), Reference(id=1245407874260775608, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1245407859740095214, doi=null, pmid=null, pmcid=null, year=2019, volume=47, issue=19, pageStart=241, pageEnd=245, url=null, language=null, rfNumber=[2], rfOrder=2, authorNames=郭亚菲, 樊超, 闫洪涛, journalName=江苏农业科学, refType=null, unstructuredReference=郭亚菲, 樊超, 闫洪涛. 基于主成分分析和粒子群优化神经网络的粮食产量预测[J]. 江苏农业科学, 2019, 47(19): 241-245., articleTitle=基于主成分分析和粒子群优化神经网络的粮食产量预测, refAbstract=null), Reference(id=1245407874382410437, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1245407859740095214, doi=null, pmid=null, pmcid=null, year=2019, volume=47, issue=19, pageStart=241, pageEnd=245, url=null, language=null, rfNumber=[2], rfOrder=3, authorNames=Guo Yafei, Fan Chao, Yan Hongtao, journalName=Jiangsu Agricultural Sciences, refType=null, unstructuredReference=Guo Yafei, Fan Chao, Yan Hongtao. Prediction of grain yield prediction using neural network based on principal component analysis and particle swarm optimization[J]. Jiangsu Agricultural Sciences, 2019, 47(19): 241-245., articleTitle=Prediction of grain yield prediction using neural network based on principal component analysis and particle swarm optimization, refAbstract=null), Reference(id=1245407874495656657, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1245407859740095214, doi=null, pmid=null, pmcid=null, year=2021, volume=2021, issue=1, pageStart=9919332, pageEnd=null, url=null, language=null, rfNumber=[3], rfOrder=4, authorNames=李炳军, 张一帆, 张淑华, journalName=自然与社会离散动力学, refType=null, unstructuredReference=李炳军, 张一帆, 张淑华, . 基于灰色BP神经网络模型的河南省粮食产量预测[J]. 自然与社会离散动力学, 2021, 2021(1): 9919332., articleTitle=基于灰色BP神经网络模型的河南省粮食产量预测, refAbstract=null), Reference(id=1245407874600514264, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1245407859740095214, doi=null, pmid=null, pmcid=null, year=2021, volume=2021, issue=1, pageStart=9919332, pageEnd=null, url=null, language=null, rfNumber=[3], rfOrder=5, authorNames=Li Bingjun, Zhang Yifan, Zhang Shuhua, journalName=Discrete Dynamics in Nature and Society, refType=null, unstructuredReference=Li Bingjun, Zhang Yifan, Zhang Shuhua, et al. Prediction of grain yield in Henan Province based on grey BP neural network model[J]. Discrete Dynamics in Nature and Society, 2021, 2021(1): 9919332., articleTitle=Prediction of grain yield in Henan Province based on grey BP neural network model, refAbstract=null), Reference(id=1245407874772480745, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1245407859740095214, doi=null, pmid=null, pmcid=null, year=2016, volume=95, issue=null, pageStart=51, pageEnd=67, url=null, language=null, rfNumber=[4], rfOrder=6, authorNames=Mirjalili S, Lewis A, journalName=Advances in Engineering Software, refType=null, unstructuredReference=Mirjalili S, Lewis A. The whale optimization algorithm[J]. Advances in Engineering Software, 2016, 95: 51-67., articleTitle=The whale optimization algorithm, refAbstract=null), Reference(id=1245407874948641527, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1245407859740095214, doi=null, pmid=null, pmcid=null, year=2022, volume=22, issue=20, pageStart=19378, pageEnd=19383, url=null, language=null, rfNumber=[5], rfOrder=7, authorNames=Liang Z, Han Q, Zhang T, journalName=IEEE Sensors Journal, refType=null, unstructuredReference=Liang Z, Han Q, Zhang T, et al. Nonlinearity compensation of magneto-optic fiber current sensors based on WOA-BP neural network[J]. IEEE Sensors Journal, 2022, 22(20): 19378-19383., articleTitle=Nonlinearity compensation of magneto-optic fiber current sensors based on WOA-BP neural network, refAbstract=null), Reference(id=1245407875070276357, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1245407859740095214, doi=null, pmid=null, pmcid=null, year=2019, volume=31, issue=7, pageStart=1235, pageEnd=1270, url=null, language=null, rfNumber=[6], rfOrder=8, authorNames=Yu Y, Si X, Hu C, journalName=Neural Computation, refType=null, unstructuredReference=Yu Y, Si X, Hu C, et al. A review of recurrent neural networks: LSTM cells and network architectures[J]. Neural Computation, 2019, 31(7): 1235-1270., articleTitle=A review of recurrent neural networks: LSTM cells and network architectures, refAbstract=null), Reference(id=1245407875217077012, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1245407859740095214, doi=null, pmid=null, pmcid=null, year=2024, volume=null, issue=3, pageStart=47, pageEnd=53, url=null, language=null, rfNumber=[7], rfOrder=9, authorNames=袁世一, journalName=计算机与现代化, refType=null, unstructuredReference=袁世一. 基于经验模态分解与极限学习机的粮食产量模型预测[J]. 计算机与现代化, 2024(3): 47-53., articleTitle=基于经验模态分解与极限学习机的粮食产量模型预测, refAbstract=null), Reference(id=1245407875321934628, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1245407859740095214, doi=null, pmid=null, pmcid=null, year=2024, volume=null, issue=3, pageStart=47, pageEnd=53, url=null, language=null, rfNumber=[7], rfOrder=10, authorNames=Yuan Shiyi, journalName=Computers and Modernization, refType=null, unstructuredReference=Yuan Shiyi, Prediction of grain yield model based on empirical mode decomposition and extreme learning machine[J]. Computers and Modernization, 2024(3): 47-53., articleTitle=Prediction of grain yield model based on empirical mode decomposition and extreme learning machine, refAbstract=null), Reference(id=1245407875451958064, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1245407859740095214, doi=null, pmid=null, pmcid=null, year=2019, volume=47, issue=5, pageStart=992, pageEnd=999, url=null, language=null, rfNumber=[8], rfOrder=11, authorNames=褚鼎立, 陈红, 王旭光, journalName=电子学报, refType=null, unstructuredReference=褚鼎立, 陈红, 王旭光. 基于自适应权重和模拟退火的鲸鱼优化算法[J]. 电子学报, 2019, 47(5): 992-999., articleTitle=基于自适应权重和模拟退火的鲸鱼优化算法, refAbstract=null), Reference(id=1245407875628118850, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1245407859740095214, doi=null, pmid=null, pmcid=null, year=2019, volume=47, issue=5, pageStart=992, pageEnd=999, url=null, language=null, rfNumber=[8], rfOrder=12, authorNames=Chu Dingli, Chen Hong, Wang Xuguang, journalName=Acta Electronica Sinica, refType=null, unstructuredReference=Chu Dingli, Chen Hong, Wang Xuguang. Whale optimization algorithm based on adaptive weighting and simulated annealing[J]. Acta Electronica Sinica, 2019, 47(5): 992-999., articleTitle=Whale optimization algorithm based on adaptive weighting and simulated annealing, refAbstract=null), Reference(id=1245407875787502420, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1245407859740095214, doi=null, pmid=null, pmcid=null, year=2020, volume=8, issue=null, pageStart=77013, pageEnd=77048, url=null, language=null, rfNumber=[9], rfOrder=13, authorNames=Zhang J, Wang J S, journalName=IEEE Access, refType=null, unstructuredReference=Zhang J, Wang J S. Improved whale optimization algorithm based on nonlinear adaptive weight and golden sine operator[J]. IEEE Access, 2020, 8: 77013-77048., articleTitle=Improved whale optimization algorithm based on nonlinear adaptive weight and golden sine operator, refAbstract=null), Reference(id=1245407875913331551, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1245407859740095214, doi=null, pmid=null, pmcid=null, year=2020, volume=41, issue=9, pageStart=1820, pageEnd=1825, url=null, language=null, rfNumber=[10], rfOrder=14, authorNames=刘磊, 白克强, 但志宏, journalName=小型微型计算机系统, refType=null, unstructuredReference=刘磊, 白克强, 但志宏, . 一种全局搜索策略的鲸鱼优化算法[J]. 小型微型计算机系统, 2020, 41(9): 1820-1825., articleTitle=一种全局搜索策略的鲸鱼优化算法, refAbstract=null), Reference(id=1245407876043354982, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1245407859740095214, doi=null, pmid=null, pmcid=null, year=2020, volume=41, issue=9, pageStart=1820, pageEnd=1825, url=null, language=null, rfNumber=[10], rfOrder=15, authorNames=Liu Lei, Bai Keqiang, Dan Zhihong, journalName=Journal of Chinese Computer Systems, refType=null, unstructuredReference=Liu Lei, Bai Keqiang, Dan Zhihong, et al. A whale optimization algorithm for global search strategy[J]. Journal of Chinese Computer Systems, 2020, 41(9): 1820-1825., articleTitle=A whale optimization algorithm for global search strategy, refAbstract=null), Reference(id=1245407876173378421, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1245407859740095214, doi=null, pmid=null, pmcid=null, year=2015, volume=149, issue=null, pageStart=153, pageEnd=165, url=null, language=null, rfNumber=[11], rfOrder=16, authorNames=Marini F, Walczak B, journalName=Chemometrics and Intelligent Laboratory Systems, refType=null, unstructuredReference=Marini F, Walczak B. Particle swarm optimization (PSO): a tutorial[J]. Chemometrics and Intelligent Laboratory Systems, 2015, 149: 153-165., articleTitle=Particle swarm optimization (PSO): a tutorial, refAbstract=null), Reference(id=1245407876328567678, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1245407859740095214, doi=null, pmid=null, pmcid=null, year=2020, volume=8, issue=1, pageStart=22, pageEnd=34, url=null, language=null, rfNumber=[12], rfOrder=17, authorNames=Xue J, Shen B, journalName=Systems Science & Control Engineering, refType=null, unstructuredReference=Xue J, Shen B. A novel swarm intelligence optimization approach: sparrow search algorithm[J]. Systems Science & Control Engineering, 2020, 8(1): 22-34., articleTitle=A novel swarm intelligence optimization approach: sparrow search algorithm, refAbstract=null), Reference(id=1245407876446008200, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1245407859740095214, doi=null, pmid=null, pmcid=null, year=2020, volume=152, issue=null, pageStart=113377, pageEnd=null, url=null, language=null, rfNumber=[13], rfOrder=18, authorNames=Faramarzi A, Heidarinejad M, Mirjalili S, journalName=Expert Systems with Applications, refType=null, unstructuredReference=Faramarzi A, Heidarinejad M, Mirjalili S, et al. Marine predators algorithm: a nature-inspired metaheuristic[J]. Expert Systems with Applications, 2020, 152: 113377., articleTitle=Marine predators algorithm: a nature-inspired metaheuristic, refAbstract=null), Reference(id=1245407876546671507, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1245407859740095214, doi=null, pmid=null, pmcid=null, year=2024, volume=57, issue=5, pageStart=123, pageEnd=null, url=null, language=null, rfNumber=[14], rfOrder=19, authorNames=Fu Y, Liu D, Chen J, journalName=Artificial Intelligence Review, refType=null, unstructuredReference=Fu Y, Liu D, Chen J, et al. Secretary bird optimization algorithm: a new metaheuristic for solving global optimization problems[J]. Artificial Intelligence Review, 2024, 57(5): 123., articleTitle=Secretary bird optimization algorithm: a new metaheuristic for solving global optimization problems, refAbstract=null), Reference(id=1245407876685083546, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1245407859740095214, doi=null, pmid=null, pmcid=null, year=2024, volume=2024, issue=null, pageStart=1, pageEnd=59, url=null, language=null, rfNumber=[15], rfOrder=20, authorNames=Bouaouda A, Hashim F A, Sayouti Y, journalName=Neural Computing and Applications, refType=null, unstructuredReference=Bouaouda A, Hashim F A, Sayouti Y, et al. Pied kingfisher optimizer: a new bio-inspired algorithm for solving numerical optimization and industrial engineering problems[J]. Neural Computing and Applications, 2024, 2024: 1-59., articleTitle=Pied kingfisher optimizer: a new bio-inspired algorithm for solving numerical optimization and industrial engineering problems, refAbstract=null), Reference(id=1245407876882215851, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1245407859740095214, doi=null, pmid=null, pmcid=null, year=2018, volume=39, issue=10, pageStart=1, pageEnd=10, url=null, language=null, rfNumber=[16], rfOrder=21, authorNames=李昊儒, 毛丽丽, 梅旭荣, journalName=中国农业资源与区划, refType=null, unstructuredReference=李昊儒, 毛丽丽, 梅旭荣, . 近30年来我国粮食产量波动影响因素分析[J]. 中国农业资源与区划, 2018, 39(10): 1-10., articleTitle=近30年来我国粮食产量波动影响因素分析, refAbstract=null), Reference(id=1245407877012239287, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1245407859740095214, doi=null, pmid=null, pmcid=null, year=2018, volume=39, issue=10, pageStart=1, pageEnd=10, url=null, language=null, rfNumber=[16], rfOrder=22, authorNames=Li Haoru, Mao Lili, Mei Xurong, journalName=China Agricultural Resources and Regional Planning, refType=null, unstructuredReference=Li Haoru, Mao Lili, Mei Xurong, et al. Analysis of influencing factors of grain yield fluctuation in China in the past 30 years[J]. China Agricultural Resources and Regional Planning, 2018, 39(10): 1-10., articleTitle=Analysis of influencing factors of grain yield fluctuation in China in the past 30 years, refAbstract=null), Reference(id=1245407877125485502, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1245407859740095214, doi=null, pmid=null, pmcid=null, year=2022, volume=35, issue=10, pageStart=46, pageEnd=50, url=null, language=null, rfNumber=[17], rfOrder=23, authorNames=许德刚, 邢奎杰, 李凡, journalName=粮食与油脂, refType=null, unstructuredReference=许德刚, 邢奎杰, 李凡, . 粮食产量影响因素分析及预测方法研究[J]. 粮食与油脂, 2022, 35(10): 46-50., articleTitle=粮食产量影响因素分析及预测方法研究, refAbstract=null), Reference(id=1245407877238731718, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1245407859740095214, doi=null, pmid=null, pmcid=null, year=2022, volume=35, issue=10, pageStart=46, pageEnd=50, url=null, language=null, rfNumber=[17], rfOrder=24, authorNames=Xu Degang, Xing Kuijie, Li Fan, journalName=Grains and Fats, refType=null, unstructuredReference=Xu Degang, Xing Kuijie, Li Fan, et al. Analysis of influencing factors of grain yield and prediction method[J]. Grains and Fats, 2022, 35(10): 46-50., articleTitle=Analysis of influencing factors of grain yield and prediction method, refAbstract=null), Reference(id=1245407877372949455, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1245407859740095214, doi=null, pmid=null, pmcid=null, year=2022, volume=32, issue=3, pageStart=132, pageEnd=138, url=null, language=null, rfNumber=[18], rfOrder=25, authorNames=马健, 李海明, 李鑫, journalName=计算机技术与发展, refType=null, unstructuredReference=马健, 李海明, 李鑫. 基于改进差分进化鲸鱼算法的经济负荷分配[J]. 计算机技术与发展, 2022, 32(3): 132-138., articleTitle=基于改进差分进化鲸鱼算法的经济负荷分配, refAbstract=null), Reference(id=1245407877570081753, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1245407859740095214, doi=null, pmid=null, pmcid=null, year=2022, volume=32, issue=3, pageStart=132, pageEnd=138, url=null, language=null, rfNumber=[18], rfOrder=26, authorNames=Ma Jian, Li Haiming, Li Xin, journalName=Computer Technology and Development, refType=null, unstructuredReference=Ma Jian, Li Haiming, Li Xin. Economic load allocation based on improved differential evolutionary whale algorithm[J]. Computer Technology and Development, 2022, 32(3): 132-138., articleTitle=Economic load allocation based on improved differential evolutionary whale algorithm, refAbstract=null), Reference(id=1245407877687522277, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1245407859740095214, doi=null, pmid=null, pmcid=null, year=2023, volume=40, issue=2, pageStart=328, pageEnd=336, url=null, language=null, rfNumber=[19], rfOrder=27, authorNames=许德刚, 王再庆, 郭奕欣, journalName=计算机应用研究, refType=null, unstructuredReference=许德刚, 王再庆, 郭奕欣, . 鲸鱼优化算法研究综述[J]. 计算机应用研究, 2023, 40(2): 328-336., articleTitle=鲸鱼优化算法研究综述, refAbstract=null), Reference(id=1245407877817545713, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1245407859740095214, doi=null, pmid=null, pmcid=null, year=2023, volume=40, issue=2, pageStart=328, pageEnd=336, url=null, language=null, rfNumber=[19], rfOrder=28, authorNames=Xu Degang, Wang Zaiqing, Guo Yixin, journalName=Application Research of Computers, refType=null, unstructuredReference=Xu Degang, Wang Zaiqing, Guo Yixin, et al. Review of whale optimization algorithms[J]. Application Research of Computers, 2023, 40(2): 328-336., articleTitle=Review of whale optimization algorithms, refAbstract=null)], funds=[Fund(id=1245407873761653391, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1245407859740095214, awardId=6227060, language=CN, fundingSource=国家自然科学基金面上项目(6227060), fundOrder=null, country=null)], companyList=[AuthorCompany(id=1245407864500630498, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1245407859740095214, xref=null, ext=[AuthorCompanyExt(id=1245407864504824804, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1245407859740095214, companyId=1245407864500630498, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=College of Information and Mathematics, Yangtze University, Jingzhou 434000, China), AuthorCompanyExt(id=1245407864513213412, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1245407859740095214, companyId=1245407864500630498, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=长江大学信息与数学学院, 荆州 434000)])], figs=[ArticleFig(id=1245407870217466087, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1245407859740095214, language=EN, label=Fig.1, caption=Flow diagram of improved whale optimization algorithm, figureFileSmall=2V4NrkeeufdsGGlNWjHu3A==, figureFileBig=KGJRFcc4NmzYEGOrz6VITg==, tableContent=null), ArticleFig(id=1245407870309740790, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1245407859740095214, language=CN, label=图1, caption=改进鲸鱼优化算法的流程图, figureFileSmall=2V4NrkeeufdsGGlNWjHu3A==, figureFileBig=KGJRFcc4NmzYEGOrz6VITg==, tableContent=null), ArticleFig(id=1245407870699811098, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1245407859740095214, language=EN, label=Fig.2, caption=Neural network structure of BP, figureFileSmall=th5PSk26rueJ8PXG3kwVdw==, figureFileBig=lgC5VjQBJZS4vMzwS14Yew==, tableContent=null), ArticleFig(id=1245407870813057316, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1245407859740095214, language=CN, label=图2, caption=BP神经网络结构, figureFileSmall=th5PSk26rueJ8PXG3kwVdw==, figureFileBig=lgC5VjQBJZS4vMzwS14Yew==, tableContent=null), ArticleFig(id=1245407870913720624, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1245407859740095214, language=EN, label=Fig.3, caption=Flow diagram of IWOA-BP neural network, figureFileSmall=dbhese8OOwj4KihXNr7kNA==, figureFileBig=c4ib+CJOSh9PnH2QCuKUzQ==, tableContent=null), ArticleFig(id=1245407871043744056, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1245407859740095214, language=CN, label=图3, caption=IWOA-BP神经网络流程图, figureFileSmall=dbhese8OOwj4KihXNr7kNA==, figureFileBig=c4ib+CJOSh9PnH2QCuKUzQ==, tableContent=null), ArticleFig(id=1245407871161184586, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1245407859740095214, language=EN, label=Fig.4, caption=Convergence curve charts under different inertia weight, figureFileSmall=hDMvgFDsWySQc19RSqo9UQ==, figureFileBig=+H96QbXqP3uU6UKMutMsZA==, tableContent=null), ArticleFig(id=1245407871236682070, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1245407859740095214, language=CN, label=图4, caption=不同惯性权重下的收敛曲线图, figureFileSmall=hDMvgFDsWySQc19RSqo9UQ==, figureFileBig=+H96QbXqP3uU6UKMutMsZA==, tableContent=null), ArticleFig(id=1245407871358316897, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1245407859740095214, language=EN, label=Fig.5, caption=Convergence box plots for seven contrast algorithms, figureFileSmall=lJERNqP55TSxi8/q+y/3eg==, figureFileBig=8rwSKaa8OxWhKWlVNlVH/A==, tableContent=null), ArticleFig(id=1245407871475757422, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1245407859740095214, language=CN, label=图5, caption=7种对比算法收敛箱式图, figureFileSmall=lJERNqP55TSxi8/q+y/3eg==, figureFileBig=8rwSKaa8OxWhKWlVNlVH/A==, tableContent=null), ArticleFig(id=1245407871643529607, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1245407859740095214, language=EN, label=Fig.6, caption=Graphs of convergence for seven contrast algorithms, figureFileSmall=cFdS9ggLKddDEfMxO7JVoA==, figureFileBig=dHkMIZvT8eTxU0covWk02g==, tableContent=null), ArticleFig(id=1245407871760970133, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1245407859740095214, language=CN, label=图6, caption=7种对比算法收敛曲线图, figureFileSmall=cFdS9ggLKddDEfMxO7JVoA==, figureFileBig=dHkMIZvT8eTxU0covWk02g==, tableContent=null), ArticleFig(id=1245407871874216356, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1245407859740095214, language=EN, label=Fig.7, caption=Prediction effect of the three optimization algorithm, figureFileSmall=BKysdppn4sn8aAAUXLHvkA==, figureFileBig=u0zhtfRXA+xD8HqK3qUgCg==, tableContent=null), ArticleFig(id=1245407871987462585, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1245407859740095214, language=CN, label=图7, caption=3种优化算法的预测效果, figureFileSmall=BKysdppn4sn8aAAUXLHvkA==, figureFileBig=u0zhtfRXA+xD8HqK3qUgCg==, tableContent=null), ArticleFig(id=1245407872067154373, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1245407859740095214, language=EN, label=Table 1, caption=

Parameter setting of each algorithm

, figureFileSmall=null, figureFileBig=null, tableContent=
算法 参数设置
WOA amax=2,amin=0
IWOA amax=2,amin=0,wmax=0.8,wmin=0.1
PSO wmax=0.9,wmin=0.2,c1=c2=2
SSA
SBOA
MPA p=0.5,FADs=0.2
PKO BF=8,PEmax=0.5,PEmin=0
), ArticleFig(id=1245407872192983510, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1245407859740095214, language=CN, label=表1, caption=

各算法的参数设置

, figureFileSmall=null, figureFileBig=null, tableContent=
算法 参数设置
WOA amax=2,amin=0
IWOA amax=2,amin=0,wmax=0.8,wmin=0.1
PSO wmax=0.9,wmin=0.2,c1=c2=2
SSA
SBOA
MPA p=0.5,FADs=0.2
PKO BF=8,PEmax=0.5,PEmin=0
), ArticleFig(id=1245407872327201258, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1245407859740095214, language=EN, label=Table 2, caption=

Benchmark function

, figureFileSmall=null, figureFileBig=null, tableContent=
函数 表达式 维度 搜索范围 最优值 类型
F1 f1(x)=$\sum _{i=1}^{n}{x}_{i}^{2}$ 30 [-100,100] 0 单峰
F2 f2(x)=$\sum _{i=1}^{n}\left|{x}_{i}\right|$+$\prod _{i=1}^{n}\left|{x}_{i}\right|$ 30 [-10,10] 0 单峰
F3 f3(x)=$\sum _{i=1}^{n}(\sum _{j=1}^{i}{x}_{j}{)}^{2}$ 30 [-100,100] 0 单峰
F4 f4(x)=maxi{$\left|{x}_{i}\right|$,1≤i≤n} 30 [-100,100] 0 单峰
F5 f5(x)=$\sum _{i=1}^{n}$i${x}_{i}^{4}$+random(0,1) 30 [-1.28,1.28] 0 多峰
F6 f6(x)=$\sum _{i=1}^{n}$[${x}_{i}^{2}$-10cos(2πxi)+10] 30 [-5.12,5.12] 0 多峰
F7 f7(x)=-20exp -0.2$\sqrt{\frac{1}{n}\sum _{i=1}^{n}{{x}_{i}}^{2}}$ -exp$\left[\frac{1}{n}\sum _{i=1}^{n}cos\left(2\right.\pi {x}_{i})\right]$+20+e 30 [-32,32] 8.881 8×1016 多峰
F8 f8(x)=$\frac{1}{4 000}\sum _{i=1}^{n}{x}_{i}^{2}$-$\prod _{i=1}^{n}$cos$\left(\frac{{x}_{i}}{\sqrt{i}}\right)$+1 30 [-600,600] 0 多峰
), ArticleFig(id=1245407872474001919, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1245407859740095214, language=CN, label=表2, caption=

基准测试函数

, figureFileSmall=null, figureFileBig=null, tableContent=
函数 表达式 维度 搜索范围 最优值 类型
F1 f1(x)=$\sum _{i=1}^{n}{x}_{i}^{2}$ 30 [-100,100] 0 单峰
F2 f2(x)=$\sum _{i=1}^{n}\left|{x}_{i}\right|$+$\prod _{i=1}^{n}\left|{x}_{i}\right|$ 30 [-10,10] 0 单峰
F3 f3(x)=$\sum _{i=1}^{n}(\sum _{j=1}^{i}{x}_{j}{)}^{2}$ 30 [-100,100] 0 单峰
F4 f4(x)=maxi{$\left|{x}_{i}\right|$,1≤i≤n} 30 [-100,100] 0 单峰
F5 f5(x)=$\sum _{i=1}^{n}$i${x}_{i}^{4}$+random(0,1) 30 [-1.28,1.28] 0 多峰
F6 f6(x)=$\sum _{i=1}^{n}$[${x}_{i}^{2}$-10cos(2πxi)+10] 30 [-5.12,5.12] 0 多峰
F7 f7(x)=-20exp -0.2$\sqrt{\frac{1}{n}\sum _{i=1}^{n}{{x}_{i}}^{2}}$ -exp$\left[\frac{1}{n}\sum _{i=1}^{n}cos\left(2\right.\pi {x}_{i})\right]$+20+e 30 [-32,32] 8.881 8×1016 多峰
F8 f8(x)=$\frac{1}{4 000}\sum _{i=1}^{n}{x}_{i}^{2}$-$\prod _{i=1}^{n}$cos$\left(\frac{{x}_{i}}{\sqrt{i}}\right)$+1 30 [-600,600] 0 多峰
), ArticleFig(id=1245407872612413966, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1245407859740095214, language=EN, label=Table 3, caption=

Comparison of test results between IWOA and other intelligent algorithms

, figureFileSmall=null, figureFileBig=null, tableContent=
函数 算法 最优值 平均值 标准差 函数 算法 最优值 平均值 标准差
F1 WOA 7.30×10-173 7.02×10-149 4.64×10-148 F5 WOA 6.55×10-5 4.99×10-3 5.95×10-3
PSO 0.15×100 0.34×100 0.10×100 PSO 1.12e×101 9.92×101 5.57×101
SSA 0 4.34×10-52 3.05×10-51 SSA 7.44×10-5 9.21×10-4 7.69×10-4
SBOA 0 1.62×10-302 0 SBOA 4.07×10-5 6.04×10-4 4.28×10-4
MPA 5.52×10-52 7.13×10-50 1.78×10-49 MPA 2.35×10-4 1.85×10-3 1.09×10-3
PKO 3.25×10-14 3.25×10-7 1.53×10-6 PKO 8.51×10-3 5.03×10-2 2.88×10-2
IWOA 0 0 0 IWOA 3.82×10-6 1.22×10-4 1.19×10-4
F2 WOA 3.60×10-113 8.08×10-101 5.05×10-100 F6 WOA 0 3.41×10-15 1.36×10-14
PSO 1.50×100 2.72×100 2.57×10-24 PSO 8.06×101 1.46×102 2.29×101
SSA 0 3.71×10-25 2.57×10-24 SSA 0 0 0
SBOA 7.08×10-179 2.17×10-160 1.53×10-159 SBOA 0 0 0
MPA 3.14×10-30 6.18×10-28 1.14×10-27 MPA 0 0 0
PKO 2.66×10-10 1.54×10-6 3.43×10-6 PKO 2.15×10-4 3.17×101 2.25×101
IWOA 0 0 0 IWOA 0 0 0
F3 WOA 4.98×102 4.36×103 1.39×103 F7 WOA 8.88×10-16 4.72×10-15 2.36×10-15
PSO 5.19×100 11.4×100 3.88×100 PSO 0.85×100 2.42×100 0.54×100
SSA 0 1.18×10-54 8.40×10-54 SSA 8.88×10-16 8.88×10-16 0
SBOA 1.64×10-123 3.53×10-98 1.64×10-97 SBOA 8.88×10-16 1.74×10-15 1.53×10-15
MPA 4.05×10-9 1.03×10-4 1.65×10-4 MPA 4.69×10-13 1.70×10-12 1.22×10-12
PKO 1.18×10+2 2.36×103 1.78×103 PKO 3.42×10-3 1.07×101 0.10×102
IWOA 0 0 0 IWOA 8.88×10-16 8.88×10-16 0
F4 WOA 0.40×100 5.64×101 2.79×10+1 F8 WOA 0 5.60×10-3 2.78×10-2
PSO 0.69×100 1.06×100 0.21×100 PSO 3.64×10-2 6.21×10-2 1.98×10-2
SSA 0 3.07×10-11 1.58×10-10 SSA 0 0 0
SBOA 4.49×10-73 4.84×10-61 3.32×10-60 SBOA 0 0 0
MPA 5.23×10-10 2.66×10-9 1.75×10-9 MPA 0 0 0
PKO 1.66×100 7.51×100 3.82×100 PKO 4.68×10-5 6.05×10-2 1.01×10-1
IWOA 0 0 0 IWOA 0 0 0
), ArticleFig(id=1245407872801157665, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1245407859740095214, language=CN, label=表3, caption=

IWOA和其他智能算法的测试结果对比

, figureFileSmall=null, figureFileBig=null, tableContent=
函数 算法 最优值 平均值 标准差 函数 算法 最优值 平均值 标准差
F1 WOA 7.30×10-173 7.02×10-149 4.64×10-148 F5 WOA 6.55×10-5 4.99×10-3 5.95×10-3
PSO 0.15×100 0.34×100 0.10×100 PSO 1.12e×101 9.92×101 5.57×101
SSA 0 4.34×10-52 3.05×10-51 SSA 7.44×10-5 9.21×10-4 7.69×10-4
SBOA 0 1.62×10-302 0 SBOA 4.07×10-5 6.04×10-4 4.28×10-4
MPA 5.52×10-52 7.13×10-50 1.78×10-49 MPA 2.35×10-4 1.85×10-3 1.09×10-3
PKO 3.25×10-14 3.25×10-7 1.53×10-6 PKO 8.51×10-3 5.03×10-2 2.88×10-2
IWOA 0 0 0 IWOA 3.82×10-6 1.22×10-4 1.19×10-4
F2 WOA 3.60×10-113 8.08×10-101 5.05×10-100 F6 WOA 0 3.41×10-15 1.36×10-14
PSO 1.50×100 2.72×100 2.57×10-24 PSO 8.06×101 1.46×102 2.29×101
SSA 0 3.71×10-25 2.57×10-24 SSA 0 0 0
SBOA 7.08×10-179 2.17×10-160 1.53×10-159 SBOA 0 0 0
MPA 3.14×10-30 6.18×10-28 1.14×10-27 MPA 0 0 0
PKO 2.66×10-10 1.54×10-6 3.43×10-6 PKO 2.15×10-4 3.17×101 2.25×101
IWOA 0 0 0 IWOA 0 0 0
F3 WOA 4.98×102 4.36×103 1.39×103 F7 WOA 8.88×10-16 4.72×10-15 2.36×10-15
PSO 5.19×100 11.4×100 3.88×100 PSO 0.85×100 2.42×100 0.54×100
SSA 0 1.18×10-54 8.40×10-54 SSA 8.88×10-16 8.88×10-16 0
SBOA 1.64×10-123 3.53×10-98 1.64×10-97 SBOA 8.88×10-16 1.74×10-15 1.53×10-15
MPA 4.05×10-9 1.03×10-4 1.65×10-4 MPA 4.69×10-13 1.70×10-12 1.22×10-12
PKO 1.18×10+2 2.36×103 1.78×103 PKO 3.42×10-3 1.07×101 0.10×102
IWOA 0 0 0 IWOA 8.88×10-16 8.88×10-16 0
F4 WOA 0.40×100 5.64×101 2.79×10+1 F8 WOA 0 5.60×10-3 2.78×10-2
PSO 0.69×100 1.06×100 0.21×100 PSO 3.64×10-2 6.21×10-2 1.98×10-2
SSA 0 3.07×10-11 1.58×10-10 SSA 0 0 0
SBOA 4.49×10-73 4.84×10-61 3.32×10-60 SBOA 0 0 0
MPA 5.23×10-10 2.66×10-9 1.75×10-9 MPA 0 0 0
PKO 1.66×100 7.51×100 3.82×100 PKO 4.68×10-5 6.05×10-2 1.01×10-1
IWOA 0 0 0 IWOA 0 0 0
), ArticleFig(id=1245407872964735543, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1245407859740095214, language=EN, label=Table 4, caption=

Performance ranking results of seven algorithms

, figureFileSmall=null, figureFileBig=null, tableContent=
测试函数 WOA PSO SSA SBOA MPA PKO IWOA
F1 3 7 4 2 5 6 1
F2 3 7 5 2 4 6 1
F3 7 5 3 2 4 6 1
F4 7 5 3 2 4 6 1
F5 5 7 3 2 4 6 1
F6 5 7 1 1 1 6 1
F7 4 5 1 3 6 7 1
F8 5 7 1 1 1 6 1
), ArticleFig(id=1245407873073787457, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1245407859740095214, language=CN, label=表4, caption=

7种算法性能排序结果

, figureFileSmall=null, figureFileBig=null, tableContent=
测试函数 WOA PSO SSA SBOA MPA PKO IWOA
F1 3 7 4 2 5 6 1
F2 3 7 5 2 4 6 1
F3 7 5 3 2 4 6 1
F4 7 5 3 2 4 6 1
F5 5 7 3 2 4 6 1
F6 5 7 1 1 1 6 1
F7 4 5 1 3 6 7 1
F8 5 7 1 1 1 6 1
), ArticleFig(id=1245407873203810896, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1245407859740095214, language=EN, label=Table 5, caption=

Comparison of different forecasting methods

, figureFileSmall=null, figureFileBig=null, tableContent=
项目 模型 R2 MAPE/% RMSE/104 t
训练集 ELM 0.990 79 0.872 98 611.526
LSTM 0.965 43 2.063 27 1 426.810
IWOA-BP 0.999 97 0.002 12 62.989 7
测试集 ELM -0.784 67 1.706 13 1 245.980
LSTM 0.906 53 0.383 12 922.676
IWOA-BP 0.998 95 0.201 67 285.021
), ArticleFig(id=1245407873321251424, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1245407859740095214, language=CN, label=表5, caption=

不同预测方法对比

, figureFileSmall=null, figureFileBig=null, tableContent=
项目 模型 R2 MAPE/% RMSE/104 t
训练集 ELM 0.990 79 0.872 98 611.526
LSTM 0.965 43 2.063 27 1 426.810
IWOA-BP 0.999 97 0.002 12 62.989 7
测试集 ELM -0.784 67 1.706 13 1 245.980
LSTM 0.906 53 0.383 12 922.676
IWOA-BP 0.998 95 0.201 67 285.021
), ArticleFig(id=1245407873459663469, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1245407859740095214, language=EN, label=Table 6, caption=

Prediction and evaluation indicators of the three optimization algorithms

, figureFileSmall=null, figureFileBig=null, tableContent=
项目 算法 R2 RMSE/104 t MAE/104 t MAPE/%
训练集 IWOA-BP 0.998 78 396.146 9 285.937 0 0.000 93
WOA-BP 0.998 96 31.458 3 18.004 3 0.000 92
PSO-BP 0.999 99 16.989 7 11.238 8 0.000 74
测试集 IWOA-BP 0.990 45 1 021.53 774.159 0.221 35
WOA-BP 0.955 36 1 817.03 1 363.503 0.409 65
PSO-BP -0.321 29 9 885.12 8 249.021 2.413 20
), ArticleFig(id=1245407873614852732, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1245407859740095214, language=CN, label=表6, caption=

3种优化算法的预测评价指标

, figureFileSmall=null, figureFileBig=null, tableContent=
项目 算法 R2 RMSE/104 t MAE/104 t MAPE/%
训练集 IWOA-BP 0.998 78 396.146 9 285.937 0 0.000 93
WOA-BP 0.998 96 31.458 3 18.004 3 0.000 92
PSO-BP 0.999 99 16.989 7 11.238 8 0.000 74
测试集 IWOA-BP 0.990 45 1 021.53 774.159 0.221 35
WOA-BP 0.955 36 1 817.03 1 363.503 0.409 65
PSO-BP -0.321 29 9 885.12 8 249.021 2.413 20
)], attaches=null, journal=Journal(id=1146119176004939786, delFlag=0, nameCn=科学技术与工程, nameEn=Science Technology and Engineering, nameHistory1=null, nameHistory2=null, issn=1671-1815, eissn=, cn=11-4688/T, coden=null, periodic=4, language=CN, oaType=是, 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=UKU/O7GSka5polgCTkbIIw==, journalPrice=null, startedYear=null, abbrevIsoEn=Sci Technol Eng, journalRemark=null, publicationField=null, createdTime=null, updatedTime=1754445529766, createdBy=null, updatedBy=13701087609, firstLetterCn=S, firstLetterEn=S, subjectCode=Natural Sciences, subjectName=自然科学, subjectCodeEn=Natural Sciences, subjectNameEn=null, picCn=UKU/O7GSka5polgCTkbIIw==, picEn=5hwlULoNwcbj3xUmVi9MAQ==, jcr=null, cjcr=null, exts=[JournalExt(id=1159791870395564357, language=CN, name=科学技术与工程, nameHistory1=null, nameHistory2=null, managedBy=, sponsoredBy=, publishedBy=, editorOffice=, officeProv=null, officeCity=null, officeAddr=, officeZip=, editDirector=null, officeDirector=null, officePhone=null, coverPicUrl=null, journalRemark=, submitArticleUrl=null, websiteUrl=http://www.stae.com.cn/jsygc/home, createdTime=1754445529793, updatedTime=1754445529793, createdBy=13701087609, updatedBy=13701087609, submissionGuidelinesUrl=http://www.stae.com.cn/jsygc/site/menus/20090429150146001, submissionAuthorUrl=http://www.stae.com.cn/jsygc/author/login, submissionEditorUrl=http://www.stae.com.cn/jsygc/editor/login, submissionReviewUrl=http://www.stae.com.cn/jsygc/reviewer/login, submissionCeEditorUrl=, submissionAeEditorUrl=, option={"copyright":""}), JournalExt(id=1159791870441701702, language=EN, name=Science Technology and Engineering, nameHistory1=null, nameHistory2=null, managedBy=, sponsoredBy=, publishedBy=, editorOffice=, officeProv=null, officeCity=null, officeAddr=, officeZip=, editDirector=null, officeDirector=null, officePhone=null, coverPicUrl=null, journalRemark=, submitArticleUrl=null, websiteUrl=http://www.stae.com.cn/jsygc/home, createdTime=1754445529804, updatedTime=1754445529804, createdBy=13701087609, updatedBy=13701087609, submissionGuidelinesUrl=, submissionAuthorUrl=http://www.stae.com.cn/jsygc/author/login, submissionEditorUrl=http://www.stae.com.cn/jsygc/editor/login, submissionReviewUrl=http://www.stae.com.cn/jsygc/reviewer/login, submissionCeEditorUrl=, submissionAeEditorUrl=, option={"copyright":""})], databaseList=null, tenantJournalId=1146123166801305609, websiteList=[Website(id=1148243202391400884, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1146123166801305609, 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/kxjsygc/CN, language=CN, createTime=1751692112777, createBy=18614031015, updateTime=1753520965431, updateBy=18614031015, name=科学技术与工程-中文站点, tplId=1146099689490845704, title=科学技术与工程, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1148622798802673703, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1148243202391400884, code=articleTextType, value=kx, createTime=1751782615614, updateTime=1751782615614, creator=18614031015, updator=18614031015), WebsiteProps(id=1148622798781702180, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1148243202391400884, code=banner, value=null, createTime=1751782615609, updateTime=1751782615609, creator=18614031015, updator=18614031015), WebsiteProps(id=1148622798769119267, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1148243202391400884, code=logo, value=https://castjournals.cast.org.cn/joweb/kjdb/CN/file/pic?fileId=j86gbwi+p0Idkyl5SzIlmQ==, createTime=1751782615606, updateTime=1751782615606, creator=18614031015, updator=18614031015), WebsiteProps(id=1148622798794285094, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1148243202391400884, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/kjdb/CN/file/pic, createTime=1751782615612, updateTime=1751782615612, creator=18614031015, updator=18614031015), WebsiteProps(id=1148622798790090789, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1148243202391400884, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_cn_619/, createTime=1751782615611, updateTime=1751782615611, creator=18614031015, updator=18614031015)]), Website(id=1155914124811976731, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1146123166801305609, 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/kxjsygc/EN, language=EN, createTime=1753521003206, createBy=18614031015, updateTime=1753521003206, updateBy=18614031015, name=科学技术与工程-英文站点, tplId=1146101810881728533, title=Science Technology and Engineering, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1155914371227308235, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1155914124811976731, code=articleTextType, value=kx, createTime=1753521061952, updateTime=1753521061952, creator=18614031015, updator=18614031015), WebsiteProps(id=1155914371210531016, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1155914124811976731, code=banner, value=null, createTime=1753521061947, updateTime=1753521061947, creator=18614031015, updator=18614031015), WebsiteProps(id=1155914371202142407, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1155914124811976731, code=logo, value=https://castjournals.cast.org.cn/joweb/kjdb/CN/file/pic?fileId=j86gbwi+p0Idkyl5SzIlmQ==, createTime=1753521061945, updateTime=1753521061945, creator=18614031015, updator=18614031015), WebsiteProps(id=1155914371223113930, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1155914124811976731, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/kjdb/CN/file/pic, createTime=1753521061950, updateTime=1753521061950, creator=18614031015, updator=18614031015), WebsiteProps(id=1155914371218919625, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1155914124811976731, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_cn_619/, createTime=1753521061949, updateTime=1753521061949, creator=18614031015, updator=18614031015)])], journalTitle=科学技术与工程, weixinUrl=null, journalUrl=null, iacademicId=null, status=0, seqNo=null, journalTitleEn=Science Technology and Engineering, journalPhotoCn=UKU/O7GSka5polgCTkbIIw==, journalPhotoEn=5hwlULoNwcbj3xUmVi9MAQ==, journalFirstLetter=S, 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=null, provinceCode=null, provinceName=null, collectFlag=false), detailUrlCn=https://castjournals.cast.org.cn/joweb/kxjsygc/CN/10.12404/j.issn.1671-1815.2402625, detailUrlEn=https://castjournals.cast.org.cn/joweb/kxjsygc/EN/10.12404/j.issn.1671-1815.2402625, pdfUrlCn=https://castjournals.cast.org.cn/joweb/kxjsygc/CN/PDF/10.12404/j.issn.1671-1815.2402625, pdfUrlEn=https://castjournals.cast.org.cn/joweb/kxjsygc/EN/PDF/10.12404/j.issn.1671-1815.2402625, aliStartDate=null, aliEndDate=null, collectionFlag=false, citedCount=null, citedUrl=null, reference=null)
收藏切换
改进鲸鱼算法构建反向传播神经网络粮食产量预测模型及效果分析
收藏切换
PDF下载
赵晶晶 , 陈岩 *
科学技术与工程 | 论文·农业科学 2025,25(7): 2748-2759
收起
收藏切换
科学技术与工程 | 论文·农业科学 2025, 25(7): 2748-2759
改进鲸鱼算法构建反向传播神经网络粮食产量预测模型及效果分析
全屏
赵晶晶 , 陈岩*
作者信息
  • 长江大学信息与数学学院, 荆州 434000
  • 赵晶晶(2000—),女,汉族,湖北黄石人,硕士研究生。研究方向:最优化理论与算法。E-mail:

通讯作者:

* 陈岩(1984—),男,汉族,山东菏泽人,博士,副教授。研究方向:最优化理论与算法。E-mail:
Enhanced Whale Optimization Algorithm for Constructing a Back Propagation Neural Network Model for Predicting Grain Yield and Its Effectiveness Analysis
Jing-jing ZHAO , Yan CHEN*
Affiliations
  • College of Information and Mathematics, Yangtze University, Jingzhou 434000, China
出版时间: 2025-03-08 doi: 10.12404/j.issn.1671-1815.2402625
文章导航
收藏切换

为了给农业及其相关部门制定粮食策略提供理论依据,提出一种基于改进鲸鱼优化算法(improved whale optimization algorithm, IWOA)的反向传播(back propagation, BP)神经网络混合算法(IWOA-BP)。该混合算法先通过引入改进收敛因子、非线性惯性权重和最优邻域扰动策略改进鲸鱼优化算法,再将其最优解赋值给BP神经网络的权值和阈值,最终提高IWOA-BP的收敛速度和收敛精度。选取全国近45年粮食总产量和7种影响因素(有效灌溉面积、化肥施用量、农村用电量、农业机械总动力、粮食作物播种面积、受灾面积和农村人均消费支出)作为数据集,构建基于改进鲸鱼算法的反向传播神经网络粮食产量预测模型。多次实验表明,IWOA-BP模型在测试集上的表现均优于其他预测模型,包括长短期记忆网络(long short-term memory network, LSTM)预测模型、极限学习机(extreme learning machine, ELM)预测模型、基于鲸鱼优化算法的BP神经网络(WOA-BP)预测模型以及基于粒子群算法的BP神经网络(PSO-BP)预测模型。IWOA-BP模型和ELM模型相比,前者的均方根误差(root mean square error,RMSE)、平均绝对百分比误差(mean absolute percentage error,MAPE)分别降低了77.12%、88.18%;和LSTM模型相比,前者的RMSE、MAPE分别降低了69.11%、47.36%;和WOA-BP模型相比,前者的平均绝对误差(mean absolute error, MAE)、RMSE和MAPE分别降低了43.78%、43.22%、45.96%。和PSO-BP模型相比,前者的MAE、RMSE、MAPE分别降低了89.67%、90.61%、90.82%。因此IWOA-BP预测模型的决定系数更高、预测误差更小且收敛速度更快,可有效地预测粮食产量,对于农业部门和相关政策制定者来说具有重要的技术参考价值。

粮食产量  /  反向传播神经网络  /  鲸鱼优化算法  /  非线性惯性权重  /  随机扰动策略

A hybrid algorithm (IWOA-BP) combining the improved whale optimization algorithm (IWOA) and backpropagation neural network (BP) was proposed to offer theoretical support for the formulation of grain strategies in the agriculture sector and its related industries. By introducing an improved convergence factor, nonlinear inertia weight, and optimal neighborhood disturbance strategy into the modified whale optimization algorithm, the optimal solution of the algorithm was obtained. This solution was then utilized as the initial weights and thresholds of the BP neural network, thereby enhancing the convergence speed and accuracy of the IWOA-BP hybrid algorithm. Subsequently, a grain yield prediction model based on the improved whale optimization algorithm was established using data from China’s grain yield over 45 years and seven influencing factors including effective irrigation area, chemical fertilizer application, rural electricity consumption, total power of agricultural machinery, sowing area of grain crops, disaster-affected area, and per capita consumption expenditure in rural areas. Through extensive experiments on a test set, it was found that the IWOA-BP model consistently outperformed other prediction models such as long short-term memory (LSTM), extreme learning machine (ELM), BP neural network with whale optimization algorithm (WOA-BP), and BP neural network with particle swarm optimization (PSO-BP). Compared to the ELM model, the root mean square error (RMSE) and mean absolute percentage error (MAPE) of the IWOA-BP model were reduced by 77.12% and 88.18% respectively. When compared to the LSTM model, the RMSE and MAPE of the IWOA-BP model were reduced by 69.11% and 47.36% respectively. Furthermore, in comparison to the WOA-BP model, the mean absolute error (MAE), RMSE, and MAPE of the IWOA-BP model were reduced by 43.78%, 43.22% and 45.96% respectively. Additionally, when compared to the PSO-BP model, the MAE, RMSE, and MAPE of the IWOA-BP model were reduced by 89.67%, 90.61% and 90.82% respectively. Therefore, the proposed IWOA-BP prediction model can be effectively used to predict grain yield due to its higher coefficient of determination, smaller prediction error, and faster convergence speed. It has important technical reference value for agricultural departments and relevant policymakers.

grain yield  /  back propagation neural network  /  whale optimization algorithm  /  nonlinear inertia weighting  /  random perturbation strategy
赵晶晶, 陈岩. 改进鲸鱼算法构建反向传播神经网络粮食产量预测模型及效果分析. 科学技术与工程, 2025 , 25 (7) : 2748 -2759 . DOI: 10.12404/j.issn.1671-1815.2402625
Jing-jing ZHAO, Yan CHEN. Enhanced Whale Optimization Algorithm for Constructing a Back Propagation Neural Network Model for Predicting Grain Yield and Its Effectiveness Analysis[J]. Science Technology and Engineering, 2025 , 25 (7) : 2748 -2759 . DOI: 10.12404/j.issn.1671-1815.2402625
粮食产量预测是一个复杂而又重要的任务,对中国的农业生产和政府决策都有重要的现实意义。准确预测粮食产量可以帮助相关部门提前做好粮食储备、调配和进出口等决策,以保障国家粮食安全,同时也有助于提升中国粮食生产效益和可持续发展。
近年来,随着人工智能和机器学习等技术的快速发展,很多学者试图将这些技术应用在粮食产量预测中。Mokarram等[1]研究了基于多元回归和人工神经网络模型的粮食产量预测,但是它们的预测速度和预测精度都有待提高,且不适用于小样本数据预测。粮食产量和影响因素之间并不是简单的线性关系,影响因素和因素之间也互相影响,因此前者研究的线性模型在长时期预测上会造成很大的误差,降低预测精度。反向传播(back propagation neural network, BP)神经网络算法具有较强的非线性映射能力、泛化能力和容错能力,经常应用在图像处理、故障诊断和时间序列预测等领域。和前面那些算法相比,BP神经网络能更好地处理非线性关系和复杂模式,具有更高的预测精度和稳定性,可以应用于粮食产量预测。BP神经网络也具有一定的局限性,有噪音或缺乏代表性的数据会降低网络的性能,所以郭亚菲等[2]先通过主成分分析法选取输入指标,再利用BP神经网络进行粮食产量预测。李炳军等[3]提将灰色预测模型与BP神经网络相结合,通过优化BP神经网络的输入变量达到提高预测模型的预测精度和预测速度的目的。
BP神经网络的预测结果比较依赖于初始权值和阈值,因此对初始权值和阈值的优化能提高BP神经网络预测模型的准确度和稳定性。鲸鱼优化算法(whale optimization algorithm, WOA)作为一种新型的群体智能优化算法[4],结构简单、寻优能力强,具有更高的收敛速度和寻优能力,可以有效地解决BP神经网络收敛慢和全局搜索能力弱等缺点。Liang等[5]提出一种基于WOA的BP神经网络预测模型,实验表明该模型的预测精度远高于基于粒子群算法的BP预测模型。
因此提出一种基于改进鲸鱼算法(improved whale optimization algorithm, IWOA)优化BP神经网络的预测模型——IWOA-BP模型。该方法把影响粮食产量因素和产量分别作为网络输入和输出构建神经网络结构,再利用改进后的鲸鱼算法优化网络权值和阈值,最后对优化后的网络进行训练和预测。实验阶段,首先将IWOA-BP预测模型和长短期记忆网络预测模型[6]、极限学习机预测模型[7]进行对比,其次将IWOA-BP模型和基于鲸鱼优化算法的BP神经网络预测模型以及基于粒子群算法的BP神经网络预测模型对比,最终所有预测结果进行决定系数、平均绝对误差、均方根误差和平均绝对百分比误差4个指标的对比分析,进一步验证IWOA-BP模型的预测精度和稳定性。
WOA算法的数学模型有3种:包围猎物、泡泡网捕食和随机搜索。以下是3种更新方式的介绍。
该模式的种群个体先以猎物或最接近猎物的个体位置作为当前最优位置解,其他个体向其趋近,数学表达式为
D1=$\left|C{X}_{best}^{*}\left(t\right)-X\left(t\right)\right|$
X(t+1)=${X}_{best}^{*}$(t)-AD1
A=a(2r-1)
C=2r
a=2-2t/Tmax
式中:t为目前的迭代次数;D1为包围步长;AC为系数变量;${X}_{best}^{*}$(t)为目前适应度最好的个体位置;X(t)为目前迭代次数中个体的位置;r为[0,1]之间的随机数;Tmax为初始设置的最大迭代次数。式(3)中a从2下降到0,此时的Aa的影响,在[-a,a]内波动。将A作为分界点,判断是随机移动还是靠近猎物,当$\left|A\right|$≤1时选择靠近猎物,当$\left|A\right|$>1时选择随机搜索。
为了模拟座头鲸沿着螺旋线吐出气泡捕获猎物的行为,将该捕食模式分为两部分:收缩包围和螺旋吐泡。
(1)收缩包围机制与包围猎物模式类似,但$\left|A\right|$a变成了$\left|A\right|$≤1,数学表达式为
D2=$\left|C{X}_{best}^{*}\left(t\right)-X\left(t\right)\right|$
X(t+1)=${X}_{best}^{*}$(t)-AD2
(2)螺旋吐泡机制的个体先计算自身与当前种群内最优个体的间距,然后以螺旋式的移动方式向最优个体靠近,数学表达式为
Dp=$\left|{X}_{best}^{*}\left(t\right)-X\left(t\right)\right|$
X(t+1)=${X}_{best}^{*}$(t)+Dpeblcos(2πl)
式中:Dp表示鲸鱼到猎物之间的距离;b为对数螺旋线形状的常数;l为[-1,1]之间的随机数。
每只鲸鱼的行为存在随机性,通过概率p、参数a和波动范围A的变化,鲸鱼个体会用不同的方式更新位置,向更优的位置移动,数学表达式为
X(t+1)=$\left\{\begin{array}{l}{X}_{best}^{*}\left(t\right)-A{D}_{2},\\ {X}_{best}^{*}\left(t\right)+{D}_{p}{e}^{bl}cos\left(2\pi l\right), \end{array}\right.\begin{array}{l}p<0.5\\ p\ge 0.5\end{array}$
种群捕猎时,随机选择一个个体位置并向其趋近,实现全局搜索找到更优解,一定程度上避免局部最优,数学表达式为
D3=$\left|C{X}_{rand}\left(t\right)-X\left(t\right)\right|$
X(t+1)=Xrand(t)-AD3
式中:Xrand(t)为随机的鲸鱼位置,且$\left|A\right|$>1。
为了提高鲸鱼优化算法的收敛速度和寻优能力,对其参数进行调整:改进收敛因子a、增加非线性惯性权重w和最优邻域扰动策略。
WOA中有两个重要的系数参数AC,其中A主要取决于a,C主要取决于r。鲸鱼算法的全局勘探和局部开发都主要和A相关,所以控制参数a可以有效地改变算法的收敛速度和搜索精度。当a较大时,算法的全局搜索能力优于局部开发能力,不易陷入局部最小值,但收敛速度较慢。相反,如果a比较小,则算法的局部开发能力较强,收敛速度加快,但容易陷入局部最优。
在传统的WOA算法位置更新公式中,收敛因子a从2到0线性递减,本文中引入非线性收敛因子a,提高算法的局部算法能力。更新后的公式为
a=2-2sin 0.5$\frac{t}{{T}_{max}}$π
式(13)中:t为当前迭代次数;Tmax为最大迭代次数。
线性权重不会动态变化,难以平衡算法的全局搜索和局部搜索,所以很多算法中都会添加非线性权重,试图调整算法的整体搜索能力。
本文在鲸鱼的位置更新公式中加入一个随迭代次数变化的非线性惯性权重w[8-9],公式为
w=wmin+(wmax-wmin)tan[0.5(1-t/Tmax)π]
加入w后的WOA位置更新公式为
X(t+1)=w${X}_{best}^{*}$(t)-AD1
X(t+1)=$\left\{\begin{array}{l}w{X}_{best}^{*}\left(t\right)-A{D}_{2},\\ w{X}_{best}^{*}\left(t\right)+{D}_{p}{e}^{bl}cos\left(2\pi l\right), \end{array}\right.\begin{array}{l}p<0.5\\ p\ge 0.5\end{array}$
X(t+1)=wXrand(t)-AD3
式中:w为初始惯性权重;wmaxwmin分别是最大、最小惯性权重。随着迭代次数的增加,惯性权重会逐渐从wmax衰减到wmin
鲸鱼在更新个体位置的时候,一般都是以当前最优位置作为本次迭代的目标,但这样会降低算法的寻优效率。针对此,在鲸鱼算法位置更新公式中引入最优邻域扰动策略[10]能够扩大搜索范围,避免算法早熟。
在最优位置产生随机扰动,位置更新公式为
Xrand(t)=$\left\{\begin{array}{l}{X}_{best}^{*}\left(t\right)+0.5{r}_{1}{X}_{rand}^{*}\left(t\right),\\ {X}_{best}^{*}\left(t\right),  \end{array}\right.\begin{array}{l}{r}_{2}<0.5\\  {r}_{2}\ge 0.5\end{array}$
式(18)中:r1r2为[0,1]之间均匀产生的随机数;Xrand(t)是在最优位置附近产生的新位置。
对于Xrand(t),采用贪婪策略公式判断是否保留,公式为
$\boldsymbol{X}_{\text {best }}^{*}(t)=\left\{\begin{array}{ll}\boldsymbol{X}_{\text {rand }}(t), & f\left[\boldsymbol{X}_{\text {rand }}(t)\right]<f\left[\boldsymbol{X}_{\text {best }}^{*}(t)\right] \\\boldsymbol{X}_{\text {best }}^{*}(t), & f\left[\boldsymbol{X}_{\text {rand }}(t)\right] \geqslant f\left[\boldsymbol{X}_{\text {best }}^{*}(t)\right]\end{array}\right.$
式(19)中:f[Xrand(t)]和f[${X}_{best}^{*}$(t)]分别为对应的适应度值。如果新位置比原位置好,则将新位置替换成最优位置,反之最优位置保持不变。
在引入最优邻域扰动时,概率设置和接受准则是两个关键环节。其中,概率设置可以保证算法兼顾全局开发能力和局部开发能力,而接受准则可以保证算法跳出局部最优解的同时提高算法的收敛速度。
基于3种改进策略的鲸鱼优化算法(improved whale optimization algorithm, IWOA)的具体流程如图1所示。
BP神经网络的网络结构如图2所示。
BP神经网络的具体流程如下。
(1)初始化网络连接权值和阈值,对数据归一化处理。
(2)根据输入样本值和初始参数进行正向传播,计算样本的实际输出。
(3)计算实际输出和理想输出的误差,并进行误差反向传播,更新网络权值和阈值。循环上述操作直到误差达到精度要求,停止训练。
(4)用训练好的网络进行预测。
IWOA-BP神经网络混合算法的特点:先用改进鲸鱼算法(IWOA)优化BP神经网络结构和参数,提高BP算法的全局搜索能力,找到更优的网络结构和参数,最后结合BP神经网络自身较强的局部寻优能力,达到网络的训练目标,提高算法的预测精度和稳定性。
IWOA-BP混合算法的实现过程如下:
(1)数据归一化,确定BP神经网络结构,初始化网络的权值与阈值。
(2)将训练样本输入到网络中并计算训练误差,求得适应度值。
(3)对神经网络权值和阈值编码,初始化IWOA算法的各项参数(最大迭代次数Tmax、种群大小N、收敛因子a、惯性权重w),得到初始种群。
(4)计算每个个体适应度值的大小获得初始最优个体。
(5)更新鲸鱼位置,并进行越界检查。将神经网络的实际输出与预测输出的均方差设为适应度函数。
(6)根据改进后的位置更新公式进行更新迭代,并加入最优邻域扰动策略,选取最小适应度值和相对应的位置解,更新全局最优解。
(7)若不满足终止条件则继续优化,否则根据更新规则将数据收集起来,最终完成算法的优化阶段,得到全局最优解。
(8)将IWOA优化后最优解赋值给BP神经网络的权值和阈值,用IWOA-BP神经网络结构进行训练和预测。
具体流程如图3所示。
为了分析和测试IWOA的性能,做以下实验安排[11-15]:①将IWOA与其他群智能算法做对比,验证IWOA的寻优效果;②对IWOA算法的自适应惯性权重进行敏感性分析得到最大惯性权重和最小惯性权重分别为0.8和0.1;③对各算法寻优效果进行数据统计分析;④对IWOA算法复杂度分析。所对比的算法包括:经典基本算法粒子群算法(particle swarm optimization, PSO)。新型群智能算法,如麻雀搜索算法(sparrow search algorithm, SSA)、海洋捕食者算法(marine predators algorithm, MPA)、蛇鹭优化算法(secretary bird optimization algorithm, SBOA)、斑翠鸟优化(pied kingfisher optimizer, PKO)。选取WOA作对比,检验本文改进策略对原算法性能的提升效果。所有算法的控制参数设置如表1所示,其中对比算法的控制参数和原文献保持一致。
本次实验的算法均使用 MATLAB R2018a 的 m 文件编写,Windows 10 系统,Intel i5 处理器与 8 G 运行内存环境下独立运行。
选取8个基准测试函数对IWOA的收敛速度和寻优能力进行测试,测试函数的表达式、搜索范围、最优值和类型如表2所示。设置所有算法的种群数为30,总迭代次数为500,每个算法独立运行50次。
设置IWOA算法的种群数为30,最大迭代次数分别为10、15和20。目标函数为Sphere函数,计算公式为
f(x)=$\sum _{i=1}^{N}{x}_{i}^{2}$
式(20)中:f(x)为适应度值;xi为鲸鱼个体位置。
在相同迭代次数的不同惯性权重下的收敛曲线如图4所示。由图4可知,wmax=0.8,wmin=0.1时IWOA的收敛速度最快,可以有效控制IWOA算法的时间复杂度,提高IWOA算法的收敛速度。
经过50次独立实验后从每种算法中获得的最优值、平均值和标准差如表3所示。其中最优值和平均值体现出算法的寻优能力,标准差体现出算法的稳定性。对于单峰测试函数F1~F4,IWOA的寻优精度和寻优稳定性远高于对比算法;对于多峰测试函数F5~F8,IWOA和SSA、MPA的寻优效果差不多,均能达到最大迭代次数之前求解最优值。为了进一步验证IWOA突出的寻优性能,将表3中各个算法的平均值进行排序,如表4所示。结果表明,在所有的算法中,IWOA的排序均位居第一,IWOA整体上具有最好的寻优能力。
将上述7种对比算法独立求解8个基准测试函数50次,得到箱式图和收敛曲线图如图5图6所示。
图5可知,在进行求解时,IWOA求得的异常点均少于对比算法,收敛值的分布整体上也更为集中。因此,IWOA和对比算法相比具有更强的鲁棒性。
图6可知,求解F1F3~F8时,IWOA的收敛速度和收敛精度明显优于对比算法,在求解F2时,虽然IWOA的收敛速度在前期弱于SSA,但是在后期能够收敛到全局最优值,而SSA陷入局部最优。因此,IWOA在拥有较快的收敛速度的同时,还具有跳出局部最优的能力。
综上所述,IWOA具有更高的收敛速度、收敛精度以及稳定性,验证了本文改进算法的有效性。
设IWOA算法的种群数量为N,搜索空间维度为d,总迭代次数为T,现对WOA、IWOA复杂度进行分析。
WOA主要分为以下几个计算部分:
(1)种群初始化:O(N×d)。
(2)主循环部分:O(N×d×T)。
(3)总复杂程度=初始化+主循环=O(N×d×T)。
IWOA主要分为以下几个计算部分。
(1)种群初始化:O(N×d)。
(2)非线性收敛因子:O(1×T)。
(3)非线性惯性权重:O(1×T)。
(4)主循环:O(N×d×T)。
(5)最优邻域扰动:O(N×T)。
总复杂程度=种群初始化+非线性收敛因子+非线性惯性权重+主循环+最优邻域扰动=O(N×d×T)。
由此可见,基于3种改进策略的IWOA算法并没有增加原算法的复杂度,反而提高了算法的寻优能力和收敛速度。
为了验证IWOA-BP预测模型的准确性和稳定性,做以下实验安排:①将IWOA-BP模型和常见的粮食产量预测模型进行对比分析,包括长短期记忆网络(long short-term memory network, LSTM)预测模型、极限学习机(extreme learning machine, ELM)预测模型,参数设置和原文献保持一致;②将IWOA-BP模型和基于鲸鱼优化算法的BP神经网络(WOA-BP)预测模型以及基于粒子群算法的BP神经网络(PSO-BP)预测模型对比,参数设置和表1保持一致,进一步检验IWOA-BP预测模型的预测效果;③模型预测效果进行数据统计分析。
所有模型均选取《中国统计年鉴》中中国近45年的粮食产量[16-17]及7项影响因素的数据作为数据集。影响指标分别是有效灌溉面积X1(103 hm2);化肥施用量X2(104 t);农村用电量X3(109 kWh);农业机械总动力X4(104 kW);粮食作物播种面积X5(103 hm2);受灾面积X6(103 hm2);农村人均消费支出X7(元)。将它们作为网络输入,粮食产量Y(万t)作为网络输出,构建IWOA-BP神经网络粮食预测模型。从45组样本中随机选取38组作为训练数据,剩余7组作为测试数据。在神经网络训练之前,对数据进行归一化处理,使所有样本数据转化为[0,1]之内的标准数据。
为公平比较,本次实验的算法使用MATLAB R2018a的m文件编写,Windows 10系统,Intel i5处理器与8 G 运行内存环境下独立运行,设置种群参数为N=30,最大迭代次数Tmax=15,最大惯性权重wmax=0.8,最小惯性权重wmin=0.1,IWOA-BP神经网络的隐含层节点数Dh=13。
选用常见的几项回归预测评价指标来验证预测结果的准确性。其中:决定系数R2(coefficient of determination)、均方根误差(root mean square error,RMSE)、平均绝对误差(mean absolute error, MAE)和平均绝对百分比误差(mean absolute percentage error, MAPE)。R2越接近1,RMSE、MAE越小以及MAPE越接近0,模型预测性能越好,计算公式为
R2=1-$\frac{\sum _{i=1}^{n}{(x-y)}^{2}}{\sum _{i=1}^{n}{(x-z)}^{2}}$
RMSE=$\sqrt{\frac{1}{n}\sum _{i=1}^{n}{(x-y)}^{2}}$
MAE=$\frac{1}{n}\sum _{i=1}^{n}\left|x-y\right|$
MAPE=$\frac{100}{n}\sum _{i=1}^{n}\left|\frac{x-y}{x}\right|$
式中:x为实际值,104 t;y为预测值,104 t;z为观测数据的平均值,104 t。
IWOA-BP模型和LSTM、ELM 3种不同类型的预测模型在训练集和测试集上的性能评估结果如表5所示。
表5表明,和ELM模型、LSTM模型相比IWOA-BP模型在训练集和测试集上都表现出色,没有出现ELM的过拟合情况,也比LSTM的泛化能力强,高R2、低RMSE和低MAPE使得IWOA-BP模型预测准确度更高,稳定性更强。
为了进一步验证IWOA算法对BP神经网络预测性能的提升效果,重新选取45组数据,IWOA-BP和WOA-BP以及PSO-BP模型的对比预测效果如图7所示,此时各项预测输出误差如表6所示。
图7可知,经过IWOA优化后的BP神经网络的预测效果明显优于其他两种预测模型,预测更加准确,整体预测数据和理想数据的折线图基本一致。
表6实验数据表明,IWOA-BP在训练集的预测性能弱于对比模型,但是在测试集上IWOA-BP在R2、RMSE、MAE以及MAPE 4项指标上均表现出最佳性能,显示出良好的泛化能力和预测精度。
为了更加突出IWOA-BP模型测试集的预测精度的提升效果,运用百分比下降公式进行计算,公式为
百分比下降率=$\frac{B-A}{B}$×100%
式(25)中:B为其他模型测试集的数据;A为IWOA-BP模型的测试集数据。
经过计算,IWOA-BP模型和ELM模型相比,其RMSE、MAPE分别降低了71.12%、88.18%。和LSTM模型相比,其RMSE、MAPE分别降低了69.11%、47.36%。和WOA-BP模型相比,其RMSE、MAE、MAPE分别降低了43.78%、43.22%、45.96%。和PSO-BP模型相比,其RMSE、MAE、MAPE分别降低了89.67%、90.61%、90.82%。
在IWOA-BP混合算法中,将改进后的鲸鱼算法优化BP神经网络的初始权值和阈值,在正式的BP训练开始之前,增加了一个额外的搜索和优化过程。这个过程涉及多次迭代和目标函数评估,从而增加了计算复杂度。实际应用的角度来看,BP神经网络通过IWOA算法找到更好的初始权值和阈值,加速了BP神经网络的训练过程,同时IWOA的全局搜索能力有助于避免BP神经网络陷入局部最优解,从而提高模型的预测精度和泛化能力。
因此,用IWOA算法优化BP神经网络是值得的,基于该算法所构建的预测模型是有效的。
对鲸鱼优化算法进行收敛因子、非线性惯性权重和随机扰动这3种策略的改进,改进后的鲸鱼算法具有更强的全局寻优能力和更快的收敛速度,能很好地避免算法陷入局部最优。其次将改进鲸鱼算法优化BP神经网络,根据粮食产量相关数据构建IWOA-BP神经网络预测模型。将模型进行实验对比,验证本文模型的有效性,得到以下结论。
(1)IWOA-BP模型与ELM、LSTM模型相比,IWOA-BP模型的RMSE分别减少了77.12%、69.11%,MAPE分别减少了88.18%、47.36%。与WOA-BP、PSO-BP模型相比,IWOA-BP的RMSE分别减少了43.78%、89.67%,MAE分别减少了43.22%、90.61%,MAPE分别减少了45.96%、90.82%。因此,基于IWOA-BP混合算法的模型预测速度更快、预测精度更高、稳定性更强,在一定程度上对未来几年粮食产量的预测和分析起到重要的作用。
(2)提出的改进鲸鱼优化算法有时仍会陷入局部最优,影响局部寻优能力,因此可以引入差分因子[18]更新鲸鱼位置,或是引入Lévy飞行[19]、混沌映射对鲸鱼初始位置进行优化,增加解的多样性。
(3)预测粮食产量的研究还有待进一步完善,研究不足在于未完整地考虑粮食产量的影响因素,可能忽略了其他重要输入指标。因此,寻找更合适的预测算法,并对预测模型的输入数据质量进行优化,这也是今后研究的重要方向之一。
总体来说,IWOA-BP神经网络模型可以很好地应用在中国的粮食产量预测方面,对于农业部门和相关政策制定者来说具有重要的技术参考价值。
  • 国家自然科学基金面上项目(6227060)
参考文献 引证文献
排序方式:
[1]
Mokarram M, Bijanzadeh E. 基于多元回归和人工神经网络模型的大麦生物产量和籽粒产量预测[J]. 澳大利亚作物科学学报, 2016, 10(6): 895-903.
Mokarram M, Bijanzadeh E. Prediction of biological and grain yield of barley using multiple regression and artificial neural network models[J]. Australian Journal of Crop Science, 2016, 10(6): 895-903.
[2]
郭亚菲, 樊超, 闫洪涛. 基于主成分分析和粒子群优化神经网络的粮食产量预测[J]. 江苏农业科学, 2019, 47(19): 241-245.
Guo Yafei, Fan Chao, Yan Hongtao. Prediction of grain yield prediction using neural network based on principal component analysis and particle swarm optimization[J]. Jiangsu Agricultural Sciences, 2019, 47(19): 241-245.
[3]
李炳军, 张一帆, 张淑华, . 基于灰色BP神经网络模型的河南省粮食产量预测[J]. 自然与社会离散动力学, 2021, 2021(1): 9919332.
Li Bingjun, Zhang Yifan, Zhang Shuhua, et al. Prediction of grain yield in Henan Province based on grey BP neural network model[J]. Discrete Dynamics in Nature and Society, 2021, 2021(1): 9919332.
[4]
Mirjalili S, Lewis A. The whale optimization algorithm[J]. Advances in Engineering Software, 2016, 95: 51-67.
[5]
Liang Z, Han Q, Zhang T, et al. Nonlinearity compensation of magneto-optic fiber current sensors based on WOA-BP neural network[J]. IEEE Sensors Journal, 2022, 22(20): 19378-19383.
[6]
Yu Y, Si X, Hu C, et al. A review of recurrent neural networks: LSTM cells and network architectures[J]. Neural Computation, 2019, 31(7): 1235-1270.
[7]
袁世一. 基于经验模态分解与极限学习机的粮食产量模型预测[J]. 计算机与现代化, 2024(3): 47-53.
Yuan Shiyi, Prediction of grain yield model based on empirical mode decomposition and extreme learning machine[J]. Computers and Modernization, 2024(3): 47-53.
[8]
褚鼎立, 陈红, 王旭光. 基于自适应权重和模拟退火的鲸鱼优化算法[J]. 电子学报, 2019, 47(5): 992-999.
Chu Dingli, Chen Hong, Wang Xuguang. Whale optimization algorithm based on adaptive weighting and simulated annealing[J]. Acta Electronica Sinica, 2019, 47(5): 992-999.
[9]
Zhang J, Wang J S. Improved whale optimization algorithm based on nonlinear adaptive weight and golden sine operator[J]. IEEE Access, 2020, 8: 77013-77048.
[10]
刘磊, 白克强, 但志宏, . 一种全局搜索策略的鲸鱼优化算法[J]. 小型微型计算机系统, 2020, 41(9): 1820-1825.
Liu Lei, Bai Keqiang, Dan Zhihong, et al. A whale optimization algorithm for global search strategy[J]. Journal of Chinese Computer Systems, 2020, 41(9): 1820-1825.
[11]
Marini F, Walczak B. Particle swarm optimization (PSO): a tutorial[J]. Chemometrics and Intelligent Laboratory Systems, 2015, 149: 153-165.
[12]
Xue J, Shen B. A novel swarm intelligence optimization approach: sparrow search algorithm[J]. Systems Science & Control Engineering, 2020, 8(1): 22-34.
[13]
Faramarzi A, Heidarinejad M, Mirjalili S, et al. Marine predators algorithm: a nature-inspired metaheuristic[J]. Expert Systems with Applications, 2020, 152: 113377.
[14]
Fu Y, Liu D, Chen J, et al. Secretary bird optimization algorithm: a new metaheuristic for solving global optimization problems[J]. Artificial Intelligence Review, 2024, 57(5): 123.
[15]
Bouaouda A, Hashim F A, Sayouti Y, et al. Pied kingfisher optimizer: a new bio-inspired algorithm for solving numerical optimization and industrial engineering problems[J]. Neural Computing and Applications, 2024, 2024: 1-59.
[16]
李昊儒, 毛丽丽, 梅旭荣, . 近30年来我国粮食产量波动影响因素分析[J]. 中国农业资源与区划, 2018, 39(10): 1-10.
Li Haoru, Mao Lili, Mei Xurong, et al. Analysis of influencing factors of grain yield fluctuation in China in the past 30 years[J]. China Agricultural Resources and Regional Planning, 2018, 39(10): 1-10.
[17]
许德刚, 邢奎杰, 李凡, . 粮食产量影响因素分析及预测方法研究[J]. 粮食与油脂, 2022, 35(10): 46-50.
Xu Degang, Xing Kuijie, Li Fan, et al. Analysis of influencing factors of grain yield and prediction method[J]. Grains and Fats, 2022, 35(10): 46-50.
[18]
马健, 李海明, 李鑫. 基于改进差分进化鲸鱼算法的经济负荷分配[J]. 计算机技术与发展, 2022, 32(3): 132-138.
Ma Jian, Li Haiming, Li Xin. Economic load allocation based on improved differential evolutionary whale algorithm[J]. Computer Technology and Development, 2022, 32(3): 132-138.
[19]
许德刚, 王再庆, 郭奕欣, . 鲸鱼优化算法研究综述[J]. 计算机应用研究, 2023, 40(2): 328-336.
Xu Degang, Wang Zaiqing, Guo Yixin, et al. Review of whale optimization algorithms[J]. Application Research of Computers, 2023, 40(2): 328-336.
2025年第25卷第7期
PDF下载
100
41
引用本文
BibTeX
文章信息
doi: 10.12404/j.issn.1671-1815.2402625
  • 接收时间:2024-04-11
  • 首发时间:2026-03-30
  • 出版时间:2025-03-08
补充材料
相关文章
文章信息
作者
出版历史
  • 收稿日期:2024-04-11
  • 修回日期:2024-07-26
基金
国家自然科学基金面上项目(6227060)
作者信息
    长江大学信息与数学学院, 荆州 434000

通讯作者:

* 陈岩(1984—),男,汉族,山东菏泽人,博士,副教授。研究方向:最优化理论与算法。E-mail:
参考文献
分享链接
https://castjournals.cast.org.cn/joweb/kxjsygc/CN/10.12404/j.issn.1671-1815.2402625
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