Article(id=1148109998183412197, tenantId=1146029695717560320, journalId=1146120122248306696, issueId=1148109990923072455, articleNumber=1009-2617(2025)02-0264-07, orderNo=null, doi=10.13355/j.cnki.sfyj.2025.02.016, pmid=null, cstr=null, oa=null, hot=null, price=null, onlineType=0, articleFormat=0, articleType=null, articleTypeStr=null, receivedDate=1725897600000, receivedDateStr=2024-09-10, revisedDate=null, revisedDateStr=null, acceptedDate=null, acceptedDateStr=null, onlineDate=1751660354419, onlineDateStr=2025-07-05, pubDate=1745769600000, pubDateStr=2025-04-28, doiRegisterDate=null, doiRegisterDateStr=null, onlineIssueDate=1751660354419, onlineIssueDateStr=2025-07-05, onlineJustAcceptDate=null, onlineJustAcceptDateStr=null, onlineFirstDate=null, onlineFirstDateStr=null, sourceXml=null, magXml=null, createTime=1751660354419, creator=13701087609, updateTime=1751660354419, updator=13701087609, issue=Issue{id=1148109990923072455, tenantId=1146029695717560320, journalId=1146120122248306696, year='2025', volume='44', issue='2', pageStart='133', pageEnd='279', issueExtLink='null', onlineDate='null', pubDate='null', beforeIssueId=null, nextIssueId=null, price=null, status=1, issueComplete=1, articleOrder=1, issueType=-1, specialIssue=0, createTime=1751660352687, creator=13701087609, updateTime=1758246043500, updator=13701087609, preIssue=null, nextIssue=null, ext={EN=IssueExt(id=1175732380301148501, tenantId=1146029695717560320, journalId=1146120122248306696, issueId=1148109990923072455, language=EN, specialIssueTitle=, coverIllustrator=, specialIssueEditor=, specialIssueAbout=), CN=IssueExt(id=1175732380301148502, tenantId=1146029695717560320, journalId=1146120122248306696, issueId=1148109990923072455, language=CN, specialIssueTitle=, coverIllustrator=, specialIssueEditor=, specialIssueAbout=)}, issueFiles=null}, startPage=264, endPage=270, ext={EN=ArticleExt(id=1148109998384738810, articleId=1148109998183412197, tenantId=1146029695717560320, journalId=1146120122248306696, language=EN, title=Design and Numerical Simulation of a Deep Learning-Based Model for Wet Metallurgical Parameter Prediction and Optimization, columnId=1152626641181700664, journalTitle=Hydrometallurgy of China, columnName=Experiment Research, runingTitle=null, highlight=null, articleAbstract=

Aiming at the issues of low computational efficiency and insufficient intelligence in predicting hydrometallurgical process parameters, a process optimization control model that utilizes 1D-CNN for predicting copper ion concentration and Seq2Seq for predicting mass transfer rate, with the objective of maximizing economic benefits was proposed. The optimization problem is solved using the DDPG algorithm. The results of numerical simulation and empirical study show that the model can predict the parameters of copper extraction process with high accuracy, realize the effective optimization and adjustment of parameters, and promote the improvement of economic benefits.

, correspAuthors=Jingpu JIA, 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=Chunyan LIU, Jingpu JIA), CN=ArticleExt(id=1148110002822312817, articleId=1148109998183412197, tenantId=1146029695717560320, journalId=1146120122248306696, language=CN, title=基于深度学习的湿法冶金工艺参数预测与优化模型的设计及数值仿真研究, columnId=1152626641328501305, journalTitle=湿法冶金, columnName=试验研究, runingTitle=null, highlight=null, articleAbstract=

针对湿法冶金工艺参数预测中存在的预测模型计算效率低及智能化程度不足等问题,提出了一个基于1D-CNN算法预测铜离子浓度、Seq2Seq模型预测传质速率,并以经济效益最大化为目标的流程优化控制模型,并采用DDPG算法求解最优化问题。数值仿真和实证研究结果表明,该模型对铜萃取流程工艺参数的预测准确度较高,可实现对参数的有效优化调整,从而促进经济效益提升。

, correspAuthors=贾景谱, authorNote=null, correspAuthorsNote=
贾景谱(1979—),女,硕士,副教授,主要研究方向为电子信息技术。E-mail:
, copyrightStatement=null, copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=+gGrIqXCrC5rICWJdMELwQ==, magXml=PBjSuxNkAk4hB/QOaIYkUA==, pdfUrl=null, pdf=mo8lvSs878obnavvG/u2yw==, pdfFileSize=null, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=null, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=IVyujZVz72Nm0tyZaYdvMw==, mapNumber=null, authorCompany=null, fund=null, authors=

刘春艳(1978—),女,硕士,副教授,主要研究方向为物联网技术。

, authorsList=刘春艳, 贾景谱)}, authors=[Author(id=1174443774437638568, tenantId=1146029695717560320, journalId=1146120122248306696, articleId=1148109998183412197, orderNo=0, 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=1174443774517330346, tenantId=1146029695717560320, journalId=1146120122248306696, articleId=1148109998183412197, authorId=1174443774437638568, language=EN, stringName=Chunyan LIU, firstName=Chunyan, middleName=null, lastName=LIU, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=Computer Application Department, Shijiazhuang Information Engineering Vocational College, Shijiazhuang 052161, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1174443774622187947, tenantId=1146029695717560320, journalId=1146120122248306696, articleId=1148109998183412197, authorId=1174443774437638568, language=CN, stringName=刘春艳, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=石家庄信息工程职业学院 计算机应用系, 河北 石家庄 052161, bio={"content":"

刘春艳(1978—),女,硕士,副教授,主要研究方向为物联网技术。

"}, bioImg=null, bioContent=

刘春艳(1978—),女,硕士,副教授,主要研究方向为物联网技术。

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1174443774362141092, tenantId=1146029695717560320, journalId=1146120122248306696, articleId=1148109998183412197, xref=null, ext=[AuthorCompanyExt(id=1174443774366335397, tenantId=1146029695717560320, journalId=1146120122248306696, articleId=1148109998183412197, companyId=1174443774362141092, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=Computer Application Department, Shijiazhuang Information Engineering Vocational College, Shijiazhuang 052161, China), AuthorCompanyExt(id=1174443774383112614, tenantId=1146029695717560320, journalId=1146120122248306696, articleId=1148109998183412197, companyId=1174443774362141092, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=石家庄信息工程职业学院 计算机应用系, 河北 石家庄 052161)])]), Author(id=1174443774676713901, tenantId=1146029695717560320, journalId=1146120122248306696, articleId=1148109998183412197, orderNo=1, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=lcy76355514@163.com, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1174443774777377199, tenantId=1146029695717560320, journalId=1146120122248306696, articleId=1148109998183412197, authorId=1174443774676713901, language=EN, stringName=Jingpu JIA, firstName=Jingpu, middleName=null, lastName=JIA, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=Computer Application Department, Shijiazhuang Information Engineering Vocational College, Shijiazhuang 052161, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1174443774852874672, tenantId=1146029695717560320, journalId=1146120122248306696, articleId=1148109998183412197, authorId=1174443774676713901, language=CN, stringName=贾景谱, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=石家庄信息工程职业学院 计算机应用系, 河北 石家庄 052161, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1174443774362141092, tenantId=1146029695717560320, journalId=1146120122248306696, articleId=1148109998183412197, xref=null, ext=[AuthorCompanyExt(id=1174443774366335397, tenantId=1146029695717560320, journalId=1146120122248306696, articleId=1148109998183412197, companyId=1174443774362141092, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=Computer Application Department, Shijiazhuang Information Engineering Vocational College, Shijiazhuang 052161, China), AuthorCompanyExt(id=1174443774383112614, tenantId=1146029695717560320, journalId=1146120122248306696, articleId=1148109998183412197, companyId=1174443774362141092, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=石家庄信息工程职业学院 计算机应用系, 河北 石家庄 052161)])])], keywords=[Keyword(id=1174443775012258225, tenantId=1146029695717560320, journalId=1146120122248306696, articleId=1148109998183412197, language=EN, orderNo=1, keyword=copper), Keyword(id=1174443775108727218, tenantId=1146029695717560320, journalId=1146120122248306696, articleId=1148109998183412197, language=EN, orderNo=2, keyword=extraction), Keyword(id=1174443775196807603, tenantId=1146029695717560320, journalId=1146120122248306696, articleId=1148109998183412197, language=EN, orderNo=3, keyword=hydrometallurgy), Keyword(id=1174443775263916468, tenantId=1146029695717560320, journalId=1146120122248306696, articleId=1148109998183412197, language=EN, orderNo=4, keyword=DDPG), Keyword(id=1174443775326831029, tenantId=1146029695717560320, journalId=1146120122248306696, articleId=1148109998183412197, language=EN, orderNo=5, keyword=1D-CNN), Keyword(id=1174443775419105718, tenantId=1146029695717560320, journalId=1146120122248306696, articleId=1148109998183412197, language=EN, orderNo=6, keyword=Seq2Seq), Keyword(id=1174443775498797495, tenantId=1146029695717560320, journalId=1146120122248306696, articleId=1148109998183412197, language=EN, orderNo=7, keyword=numerical simulation), Keyword(id=1174443775540740536, tenantId=1146029695717560320, journalId=1146120122248306696, articleId=1148109998183412197, language=CN, orderNo=1, keyword=铜), Keyword(id=1174443775599460793, tenantId=1146029695717560320, journalId=1146120122248306696, articleId=1148109998183412197, language=CN, orderNo=2, keyword=萃取), Keyword(id=1174443775649792442, tenantId=1146029695717560320, journalId=1146120122248306696, articleId=1148109998183412197, language=CN, orderNo=3, keyword=湿法冶金), Keyword(id=1174443775721095611, tenantId=1146029695717560320, journalId=1146120122248306696, articleId=1148109998183412197, language=CN, orderNo=4, keyword=DDPG), Keyword(id=1174443775792398780, tenantId=1146029695717560320, journalId=1146120122248306696, articleId=1148109998183412197, language=CN, orderNo=5, keyword=1D-CNN), Keyword(id=1174443775842730429, tenantId=1146029695717560320, journalId=1146120122248306696, articleId=1148109998183412197, language=CN, orderNo=6, keyword=Seq2Seq), Keyword(id=1174443775901450686, tenantId=1146029695717560320, journalId=1146120122248306696, articleId=1148109998183412197, language=CN, orderNo=7, keyword=数值仿真)], refs=[Reference(id=1174443777444954575, tenantId=1146029695717560320, journalId=1146120122248306696, articleId=1148109998183412197, doi=null, pmid=null, pmcid=null, year=2022, volume=51, issue=5, pageStart=68, pageEnd=72, url=null, language=null, rfNumber=[1], rfOrder=0, authorNames=孙宁磊, 吴筱, 殷书岩, journalName=中国有色冶金, refType=null, unstructuredReference=孙宁磊, 吴筱, 殷书岩, 等. 红土镍矿湿法冶金工艺参数调整对钪走向的影响[J]. 中国有色冶金, 2022, 51(5):68-72., articleTitle=红土镍矿湿法冶金工艺参数调整对钪走向的影响, refAbstract=null), Reference(id=1174443777520452048, tenantId=1146029695717560320, journalId=1146120122248306696, articleId=1148109998183412197, doi=null, pmid=null, pmcid=null, year=2022, volume=51, issue=5, pageStart=68, pageEnd=72, url=null, language=null, rfNumber=[1], rfOrder=1, authorNames=SUN Ninglei, WU Xiao, YIN Shuyan, journalName=China Nonferrous Metallurgy, refType=null, unstructuredReference=SUN Ninglei, WU Xiao, YIN Shuyan, et al. Scandium distribution with parameters adjustment in nickel laterite hydrometallurgical process[J]. China Nonferrous Metallurgy, 2022, 51(5):68-72., articleTitle=Scandium distribution with parameters adjustment in nickel laterite hydrometallurgical process, refAbstract=null), Reference(id=1174443777574978001, tenantId=1146029695717560320, journalId=1146120122248306696, articleId=1148109998183412197, doi=null, pmid=null, pmcid=null, year=2022, volume=41, issue=6, pageStart=553, pageEnd=557, url=null, language=null, rfNumber=[2], rfOrder=2, authorNames=高娜, journalName=湿法冶金, refType=null, unstructuredReference=高娜. 响应曲面法优化废电路板浸金工艺参数试验研究[J]. 湿法冶金, 2022, 41(6):553-557., articleTitle=响应曲面法优化废电路板浸金工艺参数试验研究, refAbstract=null), Reference(id=1174443777621115346, tenantId=1146029695717560320, journalId=1146120122248306696, articleId=1148109998183412197, doi=null, pmid=null, pmcid=null, year=2022, volume=41, issue=6, pageStart=553, pageEnd=557, url=null, language=null, rfNumber=[2], rfOrder=3, authorNames=GAO Na, journalName=Hydrometallurgy of China, refType=null, unstructuredReference=GAO Na. Optimizing leaching conditions of gold from waste printed circuit boards by response surface methodology[J]. Hydrometallurgy of China, 2022, 41(6):553-557., articleTitle=Optimizing leaching conditions of gold from waste printed circuit boards by response surface methodology, refAbstract=null), Reference(id=1174443777675641299, tenantId=1146029695717560320, journalId=1146120122248306696, articleId=1148109998183412197, doi=null, pmid=null, pmcid=null, year=2023, volume=42, issue=6, pageStart=659, pageEnd=665, url=null, language=null, rfNumber=[3], rfOrder=4, authorNames=郭计敏, journalName=湿法冶金, refType=null, unstructuredReference=郭计敏. 金氰化浸出过程非线性预测控制方法及仿真算法分析研究[J]. 湿法冶金, 2023, 42(6):659-665., articleTitle=金氰化浸出过程非线性预测控制方法及仿真算法分析研究, refAbstract=null), Reference(id=1174443777734361556, tenantId=1146029695717560320, journalId=1146120122248306696, articleId=1148109998183412197, doi=null, pmid=null, pmcid=null, year=2023, volume=42, issue=6, pageStart=659, pageEnd=665, url=null, language=null, rfNumber=[3], rfOrder=5, authorNames=GUO Jimin, journalName=Hydrometallurgy of China, refType=null, unstructuredReference=GUO Jimin. Nonlinear predictive control method and simulation algorithm analysis of gold cyanide leaching process[J]. Hydrometallurgy of China, 2023, 42(6):659-665., articleTitle=Nonlinear predictive control method and simulation algorithm analysis of gold cyanide leaching process, refAbstract=null), Reference(id=1174443777788887509, tenantId=1146029695717560320, journalId=1146120122248306696, articleId=1148109998183412197, doi=null, pmid=null, pmcid=null, year=2023, volume=42, issue=2, pageStart=205, pageEnd=214, url=null, language=null, rfNumber=[4], rfOrder=6, authorNames=顾群, journalName=湿法冶金, refType=null, unstructuredReference=顾群. 湿法冶金下游流程的分层优化及全流程优化仿真算法分析研究[J]. 湿法冶金, 2023, 42(2):205-214., articleTitle=湿法冶金下游流程的分层优化及全流程优化仿真算法分析研究, refAbstract=null), Reference(id=1174443777889550806, tenantId=1146029695717560320, journalId=1146120122248306696, articleId=1148109998183412197, doi=null, pmid=null, pmcid=null, year=2023, volume=42, issue=2, pageStart=205, pageEnd=214, url=null, language=null, rfNumber=[4], rfOrder=7, authorNames=GU Qun, journalName=Hydrometallurgy of China, refType=null, unstructuredReference=GU Qun. Hierarchical optimization and whole process optimization simulation algorithm of hydrometallurgy downstream process[J]. Hydrometallurgy of China, 2023, 42(2):205-214., articleTitle=Hierarchical optimization and whole process optimization simulation algorithm of hydrometallurgy downstream process, refAbstract=null), Reference(id=1174443777956659671, tenantId=1146029695717560320, journalId=1146120122248306696, articleId=1148109998183412197, doi=null, pmid=null, pmcid=null, year=2018, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[5], rfOrder=8, authorNames=张强, journalName=基于区间RBF神经元网络的湿法冶金金品位预测, refType=null, unstructuredReference=张强. 基于区间RBF神经元网络的湿法冶金金品位预测[D]. 沈阳: 东北大学, 2018., articleTitle=null, refAbstract=null), Reference(id=1174443778061517272, tenantId=1146029695717560320, journalId=1146120122248306696, articleId=1148109998183412197, doi=null, pmid=null, pmcid=null, year=2013, volume=34, issue=3, pageStart=629, pageEnd=634, url=null, language=null, rfNumber=[6], rfOrder=9, authorNames=张俊, 毛志忠, 贾润达, journalName=仪器仪表学报, refType=null, unstructuredReference=张俊, 毛志忠, 贾润达, 等. 湿法冶金浸出过程金浓度的混合预报模型[J]. 仪器仪表学报, 2013, 34(3):629-634., articleTitle=湿法冶金浸出过程金浓度的混合预报模型, refAbstract=null), Reference(id=1174443778145403353, tenantId=1146029695717560320, journalId=1146120122248306696, articleId=1148109998183412197, doi=null, pmid=null, pmcid=null, year=2013, volume=34, issue=3, pageStart=629, pageEnd=634, url=null, language=null, rfNumber=[6], rfOrder=10, authorNames=ZHANG Qiang, MAO Zhizhong, JIA Runda, journalName=Chinese Journal of Scientific Instrument, refType=null, unstructuredReference=ZHANG Qiang, MAO Zhizhong, JIA Runda, et al. Hybrid predictive model of gold concentration for hydrometallurgy leaching process[J]. Chinese Journal of Scientific Instrument, 2013, 34(3):629-634., articleTitle=Hybrid predictive model of gold concentration for hydrometallurgy leaching process, refAbstract=null), Reference(id=1174443778208317914, tenantId=1146029695717560320, journalId=1146120122248306696, articleId=1148109998183412197, doi=null, pmid=null, pmcid=null, year=2021, volume=40, issue=3, pageStart=260, pageEnd=266, url=null, language=null, rfNumber=[7], rfOrder=11, authorNames=陈溥, journalName=湿法冶金, refType=null, unstructuredReference=陈溥. 基于核偏最小二乘法的湿法冶金萃取过程建模[J]. 湿法冶金, 2021, 40(3):260-266., articleTitle=基于核偏最小二乘法的湿法冶金萃取过程建模, refAbstract=null), Reference(id=1174443778275426779, tenantId=1146029695717560320, journalId=1146120122248306696, articleId=1148109998183412197, doi=null, pmid=null, pmcid=null, year=2021, volume=40, issue=3, pageStart=260, pageEnd=266, url=null, language=null, rfNumber=[7], rfOrder=12, authorNames=CHEN Pu, journalName=Hydrometallurgy of China, refType=null, unstructuredReference=CHEN Pu. Modeling for solvent extraction of copper based on kernel partial least squares method[J]. Hydrometallurgy of China, 2021, 40(3):260-266., articleTitle=Modeling for solvent extraction of copper based on kernel partial least squares method, refAbstract=null), Reference(id=1174443778355118556, tenantId=1146029695717560320, journalId=1146120122248306696, articleId=1148109998183412197, doi=null, pmid=null, pmcid=null, year=2022, volume=null, issue=5, pageStart=70, pageEnd=73, url=null, language=null, rfNumber=[8], rfOrder=13, authorNames=张海宝, 陈燕杰, 伏晓丹, journalName=铜业工程, refType=null, unstructuredReference=张海宝, 陈燕杰, 伏晓丹, 等. 提高铜钴矿湿法冶金过程铜钴回收率的方法概述[J]. 铜业工程, 2022(5):70-73., articleTitle=提高铜钴矿湿法冶金过程铜钴回收率的方法概述, refAbstract=null), Reference(id=1174443778405450205, tenantId=1146029695717560320, journalId=1146120122248306696, articleId=1148109998183412197, doi=null, pmid=null, pmcid=null, year=2022, volume=null, issue=5, pageStart=70, pageEnd=73, url=null, language=null, rfNumber=[8], rfOrder=14, authorNames=ZHANG Haibao, CHEN Yanjie, FU Xiaodan, journalName=Copper Engineering, refType=null, unstructuredReference=ZHANG Haibao, CHEN Yanjie, FU Xiaodan, et al. Methods of improving recovery rate of copper and cobalt in hydrometallurgical process of copper-cobalt oxide ore[J]. Copper Engineering, 2022(5):70-73., articleTitle=Methods of improving recovery rate of copper and cobalt in hydrometallurgical process of copper-cobalt oxide ore, refAbstract=null), Reference(id=1174443778518696414, tenantId=1146029695717560320, journalId=1146120122248306696, articleId=1148109998183412197, doi=null, pmid=null, pmcid=null, year=2023, volume=59, issue=1, pageStart=259, pageEnd=268, url=null, language=null, rfNumber=[9], rfOrder=15, authorNames=曹绍华, 姜佳佳, 陈舒, journalName=计算机工程与应用, refType=null, unstructuredReference=曹绍华, 姜佳佳, 陈舒, 等. A-DDPG:多用户边缘计算系统的卸载研究[J]. 计算机工程与应用, 2023, 59(1):259-268., articleTitle=A-DDPG:多用户边缘计算系统的卸载研究, refAbstract=null), Reference(id=1174443778657108447, tenantId=1146029695717560320, journalId=1146120122248306696, articleId=1148109998183412197, doi=null, pmid=null, pmcid=null, year=2023, volume=59, issue=1, pageStart=259, pageEnd=268, url=null, language=null, rfNumber=[9], rfOrder=16, authorNames=CAO Shaohua, JIANG Jiajia, CHEN Shu, journalName=Computer Engineering and Applications, refType=null, unstructuredReference=CAO Shaohua, JIANG Jiajia, CHEN Shu, et al. A-DDPG:research on offloading of multi-user edge computing system[J]. Computer Engineering and Applications, 2023, 59(1):259-268., articleTitle=A-DDPG:research on offloading of multi-user edge computing system, refAbstract=null), Reference(id=1174443778707440096, tenantId=1146029695717560320, journalId=1146120122248306696, articleId=1148109998183412197, doi=null, pmid=null, pmcid=null, year=2023, volume=45, issue=3, pageStart=17, pageEnd=23, url=null, language=null, rfNumber=[10], rfOrder=17, authorNames=马珂, 毕大平, 周圣栾, journalName=现代雷达, refType=null, unstructuredReference=马珂, 毕大平, 周圣栾, 等. 基于1DCNN的机载火控雷达空空工作状态识别[J]. 现代雷达, 2023, 45(3):17-23., articleTitle=基于1DCNN的机载火控雷达空空工作状态识别, refAbstract=null), Reference(id=1174443778761966049, tenantId=1146029695717560320, journalId=1146120122248306696, articleId=1148109998183412197, doi=null, pmid=null, pmcid=null, year=2023, volume=45, issue=3, pageStart=17, pageEnd=23, url=null, language=null, rfNumber=[10], rfOrder=18, authorNames=MA Ke, BI Daping, ZHOU Shengluan, journalName=Modern Radar, refType=null, unstructuredReference=MA Ke, BI Daping, ZHOU Shengluan, et al. Air-to-air working state recognition of airborne fire control radar based on 1DCNN[J]. Modern Radar, 2023, 45(3):17-23., articleTitle=Air-to-air working state recognition of airborne fire control radar based on 1DCNN, refAbstract=null), Reference(id=1174443778833269218, tenantId=1146029695717560320, journalId=1146120122248306696, articleId=1148109998183412197, doi=null, pmid=null, pmcid=null, year=2023, volume=49, issue=5, pageStart=50, pageEnd=58, url=null, language=null, rfNumber=[11], rfOrder=19, authorNames=王文婷, 刘姝君, 张耀聪, journalName=兰州理工大学学报, refType=null, unstructuredReference=王文婷, 刘姝君, 张耀聪, 等. 基于Seq2Seq深度学习模型的焦炉煤气发生量预测方法研究[J]. 兰州理工大学学报, 2023, 49(5):50-58., articleTitle=基于Seq2Seq深度学习模型的焦炉煤气发生量预测方法研究, refAbstract=null), Reference(id=1174443778912960995, tenantId=1146029695717560320, journalId=1146120122248306696, articleId=1148109998183412197, doi=null, pmid=null, pmcid=null, year=2023, volume=49, issue=5, pageStart=50, pageEnd=58, url=null, language=null, rfNumber=[11], rfOrder=20, authorNames=WANG Wenting, LIU Shujun, ZHANG Yaocong, journalName=Journal of Lanzhou University of Technology, refType=null, unstructuredReference=WANG Wenting, LIU Shujun, ZHANG Yaocong, et al. Prediction of coke oven gas generation based on Seq2Seq[J]. Journal of Lanzhou University of Technology, 2023, 49(5):50-58., articleTitle=Prediction of coke oven gas generation based on Seq2Seq, refAbstract=null), Reference(id=1174443779005235684, tenantId=1146029695717560320, journalId=1146120122248306696, articleId=1148109998183412197, doi=null, pmid=null, pmcid=null, year=2024, volume=45, issue=1, pageStart=168, pageEnd=176, url=null, language=null, rfNumber=[12], rfOrder=21, authorNames=吉晨钟, 次旺晋美, 张伟, journalName=小型微型计算机系统, refType=null, unstructuredReference=吉晨钟, 次旺晋美, 张伟, 等. 改进2D CNN时空特征提取的动作识别研究[J]. 小型微型计算机系统, 2024, 45(1):168-176., articleTitle=改进2D CNN时空特征提取的动作识别研究, refAbstract=null), Reference(id=1174443779051373029, tenantId=1146029695717560320, journalId=1146120122248306696, articleId=1148109998183412197, doi=null, pmid=null, pmcid=null, year=2024, volume=45, issue=1, pageStart=168, pageEnd=176, url=null, language=null, rfNumber=[12], rfOrder=22, authorNames=JI Chenzhong, CI Wangjinmei, ZHANG Wei, journalName=Journal of Chinese Computer Systems, refType=null, unstructuredReference=JI Chenzhong, CI Wangjinmei, ZHANG Wei, et al. Research on action recognition based on improving 2D CNN spatial-temporal feature extraction[J]. Journal of Chinese Computer Systems, 2024, 45(1):168-176., articleTitle=Research on action recognition based on improving 2D CNN spatial-temporal feature extraction, refAbstract=null), Reference(id=1174443779105898982, tenantId=1146029695717560320, journalId=1146120122248306696, articleId=1148109998183412197, doi=null, pmid=null, pmcid=null, year=2023, volume=null, issue=4, pageStart=201, pageEnd=205, url=null, language=null, rfNumber=[13], rfOrder=23, authorNames=刘晓娟, journalName=自动化与仪器仪表, refType=null, unstructuredReference=刘晓娟. 基于改进Seq2Seq的翻译机器人纠错系统设计[J]. 自动化与仪器仪表, 2023(4):201-205., articleTitle=基于改进Seq2Seq的翻译机器人纠错系统设计, refAbstract=null), Reference(id=1174443779147842023, tenantId=1146029695717560320, journalId=1146120122248306696, articleId=1148109998183412197, doi=null, pmid=null, pmcid=null, year=2023, volume=null, issue=4, pageStart=201, pageEnd=205, url=null, language=null, rfNumber=[13], rfOrder=24, authorNames=LIU Xiaojuan, journalName=Automation & Instrumentation, refType=null, unstructuredReference=LIU Xiaojuan. Design of translation robot error correction system based on improved Seq2Seq[J]. Automation & Instrumentation, 2023(4):201-205., articleTitle=Design of translation robot error correction system based on improved Seq2Seq, refAbstract=null), Reference(id=1174443779193979368, tenantId=1146029695717560320, journalId=1146120122248306696, articleId=1148109998183412197, doi=null, pmid=null, pmcid=null, year=2022, volume=30, issue=23, pageStart=6, pageEnd=10, url=null, language=null, rfNumber=[14], rfOrder=25, authorNames=门鼎, 陈亮, journalName=电子设计工程, refType=null, unstructuredReference=门鼎, 陈亮. 基于改进Seq2Seq-Attention模型的文本摘要生成方法[J]. 电子设计工程, 2022, 30(23):6-10., articleTitle=基于改进Seq2Seq-Attention模型的文本摘要生成方法, refAbstract=null), Reference(id=1174443779261088233, tenantId=1146029695717560320, journalId=1146120122248306696, articleId=1148109998183412197, doi=null, pmid=null, pmcid=null, year=2022, volume=30, issue=23, pageStart=6, pageEnd=10, url=null, language=null, rfNumber=[14], rfOrder=26, authorNames=MEN Ding, CHEN Liang, journalName=Electronic Design Engineering, refType=null, unstructuredReference=MEN Ding, CHEN Liang. Text summary generation method based on improved Seq2Seq-Attention model[J]. Electronic Design Engineering, 2022, 30(23):6-10., articleTitle=Text summary generation method based on improved Seq2Seq-Attention model, refAbstract=null), Reference(id=1174443779315614186, tenantId=1146029695717560320, journalId=1146120122248306696, articleId=1148109998183412197, doi=null, pmid=null, pmcid=null, year=2023, volume=null, issue=8, pageStart=257, pageEnd=261, url=null, language=null, rfNumber=[15], rfOrder=27, authorNames=宫昀, journalName=自动化与仪器仪表, refType=null, unstructuredReference=宫昀. 基于Transformer模型的神经机器翻译改进方法研究[J]. 自动化与仪器仪表, 2023(8):257-261., articleTitle=基于Transformer模型的神经机器翻译改进方法研究, refAbstract=null), Reference(id=1174443779370140139, tenantId=1146029695717560320, journalId=1146120122248306696, articleId=1148109998183412197, doi=null, pmid=null, pmcid=null, year=2023, volume=null, issue=8, pageStart=257, pageEnd=261, url=null, language=null, rfNumber=[15], rfOrder=28, authorNames=GONG Yun, journalName=Automation & Instrumentation, refType=null, unstructuredReference=GONG Yun. Research on improved neural machine translation method based on transformer model[J]. Automation & Instrumentation, 2023(8):257-261., articleTitle=Research on improved neural machine translation method based on transformer model, refAbstract=null)], funds=null, companyList=[AuthorCompany(id=1174443774362141092, tenantId=1146029695717560320, journalId=1146120122248306696, articleId=1148109998183412197, xref=null, ext=[AuthorCompanyExt(id=1174443774366335397, tenantId=1146029695717560320, journalId=1146120122248306696, articleId=1148109998183412197, companyId=1174443774362141092, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=Computer Application Department, Shijiazhuang Information Engineering Vocational College, Shijiazhuang 052161, China), AuthorCompanyExt(id=1174443774383112614, tenantId=1146029695717560320, journalId=1146120122248306696, articleId=1148109998183412197, companyId=1174443774362141092, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=石家庄信息工程职业学院 计算机应用系, 河北 石家庄 052161)])], figs=[ArticleFig(id=1174443776069222847, tenantId=1146029695717560320, journalId=1146120122248306696, articleId=1148109998183412197, language=EN, label=Fig.1, caption=Structure of 1D-CNN model, figureFileSmall=6k6xGZiIQiD1Y1pMMjEO4w==, figureFileBig=QT/UOroJ++VX+GSPmfm4VA==, tableContent=null), ArticleFig(id=1174443776136331712, tenantId=1146029695717560320, journalId=1146120122248306696, articleId=1148109998183412197, language=CN, label=图1, caption=1D-CNN模型的结构, figureFileSmall=6k6xGZiIQiD1Y1pMMjEO4w==, figureFileBig=QT/UOroJ++VX+GSPmfm4VA==, tableContent=null), ArticleFig(id=1174443776216023489, tenantId=1146029695717560320, journalId=1146120122248306696, articleId=1148109998183412197, language=EN, label=Fig.2, caption=Structure of Seq2Seq model, figureFileSmall=vx/ypPLDFZLxMoVSwEiT1w==, figureFileBig=Bx9pBaiVXKdC/cfiGj/BXQ==, tableContent=null), ArticleFig(id=1174443776308298178, tenantId=1146029695717560320, journalId=1146120122248306696, articleId=1148109998183412197, language=CN, label=图2, caption=Seq2Seq模型的结构, figureFileSmall=vx/ypPLDFZLxMoVSwEiT1w==, figureFileBig=Bx9pBaiVXKdC/cfiGj/BXQ==, tableContent=null), ArticleFig(id=1174443776425738691, tenantId=1146029695717560320, journalId=1146120122248306696, articleId=1148109998183412197, language=EN, label=Fig.3, caption=Principle of DDPG algorithm, figureFileSmall=EfYyXFwueaDy3vUR4vPRUA==, figureFileBig=jHMzPOBWbHWbpZt7ME/TcA==, tableContent=null), ArticleFig(id=1174443776526401988, tenantId=1146029695717560320, journalId=1146120122248306696, articleId=1148109998183412197, language=CN, label=图3, caption=DDPG算法的原理, figureFileSmall=EfYyXFwueaDy3vUR4vPRUA==, figureFileBig=jHMzPOBWbHWbpZt7ME/TcA==, tableContent=null), ArticleFig(id=1174443776706757061, tenantId=1146029695717560320, journalId=1146120122248306696, articleId=1148109998183412197, language=EN, label=Fig.4, caption=Simulation test environment of copper extraction, figureFileSmall=m87sBh26GWYxZaMp+Ah58A==, figureFileBig=a96PS8qnFIJthSsIqm9fUA==, tableContent=null), ArticleFig(id=1174443776786448838, tenantId=1146029695717560320, journalId=1146120122248306696, articleId=1148109998183412197, language=CN, label=图4, caption=铜萃取的仿真试验环境, figureFileSmall=m87sBh26GWYxZaMp+Ah58A==, figureFileBig=a96PS8qnFIJthSsIqm9fUA==, tableContent=null), ArticleFig(id=1174443776840974791, tenantId=1146029695717560320, journalId=1146120122248306696, articleId=1148109998183412197, language=EN, label=Fig.5, caption=Change curve of input economic benefit under multiple model iterations, figureFileSmall=52XAkdt27SkO4YNuyad6rg==, figureFileBig=l4zE6+WicTigNuNz2OgU3g==, tableContent=null), ArticleFig(id=1174443776903889352, tenantId=1146029695717560320, journalId=1146120122248306696, articleId=1148109998183412197, language=CN, label=图5, caption=多次模型迭代下的投入经济效益变化曲线, figureFileSmall=52XAkdt27SkO4YNuyad6rg==, figureFileBig=l4zE6+WicTigNuNz2OgU3g==, tableContent=null), ArticleFig(id=1174443776954221001, tenantId=1146029695717560320, journalId=1146120122248306696, articleId=1148109998183412197, language=EN, label=Table 1, caption=

Comparison of economic benefits before and after using this method

, figureFileSmall=null, figureFileBig=null, tableContent=
项目 成本/万元 经济效益/万元
使用前 12.4 5.3
使用后 12.4 9.6
), ArticleFig(id=1174443777004552650, tenantId=1146029695717560320, journalId=1146120122248306696, articleId=1148109998183412197, language=CN, label=表1, caption=

使用本方法前、后经济效益对比

, figureFileSmall=null, figureFileBig=null, tableContent=
项目 成本/万元 经济效益/万元
使用前 12.4 5.3
使用后 12.4 9.6
), ArticleFig(id=1174443777059078603, tenantId=1146029695717560320, journalId=1146120122248306696, articleId=1148109998183412197, language=EN, label=Table 2, caption=

Comparison of prediction and evaluation indexes of two process parameters by different models

, figureFileSmall=null, figureFileBig=null, tableContent=
预测模型 萃余液铜离子浓度的预测 传质速率都预测
MSE/% RMSE/% MAE/% MSE/% RMSE/% MAE/%
线性回归 53.40 57.70 59.50 52.60 57.30 61.50
支持向量机 61.43 63.55 65.75 54.99 62.09 65.87
RNN 65.38 67.13 68.58 58.09 64.94 69.16
LSTM 68.51 71.05 70.05 60.89 67.62 72.08
1D-CNN/Seq2Seq 83.95 82.58 81.70 83.02 84.89 84.82
), ArticleFig(id=1174443777126187468, tenantId=1146029695717560320, journalId=1146120122248306696, articleId=1148109998183412197, language=CN, label=表2, caption=

不同模型对2个工艺参数的预测评价指标对比

, figureFileSmall=null, figureFileBig=null, tableContent=
预测模型 萃余液铜离子浓度的预测 传质速率都预测
MSE/% RMSE/% MAE/% MSE/% RMSE/% MAE/%
线性回归 53.40 57.70 59.50 52.60 57.30 61.50
支持向量机 61.43 63.55 65.75 54.99 62.09 65.87
RNN 65.38 67.13 68.58 58.09 64.94 69.16
LSTM 68.51 71.05 70.05 60.89 67.62 72.08
1D-CNN/Seq2Seq 83.95 82.58 81.70 83.02 84.89 84.82
), ArticleFig(id=1174443777239433677, tenantId=1146029695717560320, journalId=1146120122248306696, articleId=1148109998183412197, language=EN, label=Table 3, caption=

Comparison of economic benefits before and after implementation of this method in a copper extraction plant

, figureFileSmall=null, figureFileBig=null, tableContent=
项目 当月总投入成本/万元 当月总经济效益/万元
实施前 342.32 23.66
实施后 492.62 74.92
), ArticleFig(id=1174443777314931150, tenantId=1146029695717560320, journalId=1146120122248306696, articleId=1148109998183412197, language=CN, label=表3, caption=

某铜萃取工厂实施本方法前、后的经济效益对比

, figureFileSmall=null, figureFileBig=null, tableContent=
项目 当月总投入成本/万元 当月总经济效益/万元
实施前 342.32 23.66
实施后 492.62 74.92
)], attaches=null, journal=Journal(id=1146119103623835657, delFlag=0, nameCn=湿法冶金, nameEn=Hydrometallurgy of China, nameHistory1=null, nameHistory2=null, issn=1009-2617, eissn=, cn=11-3012/TF, coden=null, periodic=1, language=CN, oaType=0, 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=ML4PO2yJMiCn17KYxauyiw==, journalPrice=null, startedYear=null, abbrevIsoEn=Hydromet Chin, journalRemark=null, publicationField=null, createdTime=null, updatedTime=1755588063580, createdBy=null, updatedBy=15831073675, firstLetterCn=H, firstLetterEn=H, subjectCode=Engineering, subjectName=工程, subjectCodeEn=Engineering, subjectNameEn=null, picCn=ML4PO2yJMiCn17KYxauyiw==, picEn=Gjj3Lht1PhYSE3+d1o3GzQ==, jcr=null, cjcr=null, exts=[JournalExt(id=1164584004549300292, language=CN, name=湿法冶金, 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=https://sfyj.cbpt.cnki.net/portal, createdTime=1755588063609, updatedTime=1755588063609, createdBy=15831073675, updatedBy=15831073675, submissionGuidelinesUrl=https://sfyj.cbpt.cnki.net/portal/journal/portal/client/news/SFYJ_0a96be87-490b-49ff-90aa-bee7b5d1b2cc, submissionAuthorUrl=https://sfyj.cbpt.cnki.net/index.aspx?t=1, submissionEditorUrl=https://sfyj.cbpt.cnki.net/EditorE3N/index.aspx?t=3, submissionReviewUrl=https://sfyj.cbpt.cnki.net/EditorE3N/index.aspx?t=2, submissionCeEditorUrl=https://sfyj.cbpt.cnki.net/EditorE3N/index.aspx?t=3, submissionAeEditorUrl=https://sfyj.cbpt.cnki.net/EditorE3N/index.aspx?t=3, option={"copyright":""}), JournalExt(id=1164584004591243333, language=EN, name=Hydrometallurgy of China, 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=https://sfyj.cbpt.cnki.net/portal, createdTime=1755588063619, updatedTime=1755588063619, createdBy=15831073675, updatedBy=15831073675, submissionGuidelinesUrl=https://sfyj.cbpt.cnki.net/portal/journal/portal/client/news/SFYJ_0a96be87-490b-49ff-90aa-bee7b5d1b2cc, submissionAuthorUrl=https://sfyj.cbpt.cnki.net/index.aspx?t=1, submissionEditorUrl=https://sfyj.cbpt.cnki.net/EditorE3N/index.aspx?t=3, submissionReviewUrl=https://sfyj.cbpt.cnki.net/EditorE3N/index.aspx?t=2, submissionCeEditorUrl=https://sfyj.cbpt.cnki.net/EditorE3N/index.aspx?t=3, submissionAeEditorUrl=https://sfyj.cbpt.cnki.net/EditorE3N/index.aspx?t=3, option={"copyright":""})], databaseList=null, tenantJournalId=1146120122248306696, websiteList=[Website(id=1148243202391400870, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1146120122248306696, 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/sfyj/CN, language=CN, createTime=1751692112777, createBy=18614031015, updateTime=1753517065508, updateBy=18614031015, name=《湿法冶金》中文站点, tplId=1146099689490845704, title=湿法冶金, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1155898007666155631, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1148243202391400870, code=articleTextType, value=kx, createTime=1753517160575, updateTime=1753517160575, creator=18614031015, updator=18614031015), WebsiteProps(id=1155898007645184108, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1148243202391400870, code=banner, value=null, createTime=1753517160569, updateTime=1753517160569, creator=18614031015, updator=18614031015), WebsiteProps(id=1155898007636795499, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1148243202391400870, code=logo, value=https://castjournals.cast.org.cn/joweb/kjdb/CN/file/pic?fileId=MQxQC8ritkQycwo0QA60VQ==, createTime=1753517160567, updateTime=1753517160567, creator=18614031015, updator=18614031015), WebsiteProps(id=1155898007657767022, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1148243202391400870, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/kjdb/CN/file/pic, createTime=1753517160572, updateTime=1753517160572, creator=18614031015, updator=18614031015), WebsiteProps(id=1155898007653572717, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1148243202391400870, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_cn_619/, createTime=1753517160571, updateTime=1753517160571, creator=18614031015, updator=18614031015)]), Website(id=1155897814010970126, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1146120122248306696, 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/sfyj/EN, language=EN, createTime=1753517114406, createBy=18614031015, updateTime=1753517114406, updateBy=18614031015, name=《湿法冶金》英文站点, tplId=1146101810881728533, title=Hydrometallurgy of China, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1155898118869733563, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1155897814010970126, code=articleTextType, value=kx, createTime=1753517187087, updateTime=1753517187087, creator=18614031015, updator=18614031015), WebsiteProps(id=1155898118852956344, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1155897814010970126, code=banner, value=null, createTime=1753517187083, updateTime=1753517187083, creator=18614031015, updator=18614031015), WebsiteProps(id=1155898118827790519, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1155897814010970126, code=logo, value=https://castjournals.cast.org.cn/joweb/kjdb/CN/file/pic?fileId=MQxQC8ritkQycwo0QA60VQ==, createTime=1753517187077, updateTime=1753517187077, creator=18614031015, updator=18614031015), WebsiteProps(id=1155898118865539258, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1155897814010970126, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/kjdb/CN/file/pic, createTime=1753517187086, updateTime=1753517187086, creator=18614031015, updator=18614031015), WebsiteProps(id=1155898118861344953, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1155897814010970126, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_cn_619/, createTime=1753517187085, updateTime=1753517187085, creator=18614031015, updator=18614031015)])], journalTitle=湿法冶金, weixinUrl=null, journalUrl=null, iacademicId=null, status=0, seqNo=null, journalTitleEn=Hydrometallurgy of China, journalPhotoCn=ML4PO2yJMiCn17KYxauyiw==, journalPhotoEn=Gjj3Lht1PhYSE3+d1o3GzQ==, journalFirstLetter=H, journalRecommend=null, journalNew=null, journalCollection=null, jcrJf=null, cjcrJf=0.00, 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), detailUrlCn=https://castjournals.cast.org.cn/joweb/sfyj/CN/10.13355/j.cnki.sfyj.2025.02.016, detailUrlEn=https://castjournals.cast.org.cn/joweb/sfyj/EN/10.13355/j.cnki.sfyj.2025.02.016, pdfUrlCn=https://castjournals.cast.org.cn/joweb/sfyj/CN/PDF/10.13355/j.cnki.sfyj.2025.02.016, pdfUrlEn=https://castjournals.cast.org.cn/joweb/sfyj/EN/PDF/10.13355/j.cnki.sfyj.2025.02.016, aliStartDate=null, aliEndDate=null, collectionFlag=false, citedCount=null, citedUrl=null, reference=null)
收藏切换
基于深度学习的湿法冶金工艺参数预测与优化模型的设计及数值仿真研究
收藏切换
PDF下载
刘春艳 , 贾景谱
湿法冶金 | 试验研究 2025,44(2): 264-270
收起
收藏切换
湿法冶金 | 试验研究 2025, 44(2): 264-270
基于深度学习的湿法冶金工艺参数预测与优化模型的设计及数值仿真研究
全屏
刘春艳, 贾景谱
作者信息
  • 石家庄信息工程职业学院 计算机应用系, 河北 石家庄 052161
  • 刘春艳(1978—),女,硕士,副教授,主要研究方向为物联网技术。

通讯作者:

贾景谱(1979—),女,硕士,副教授,主要研究方向为电子信息技术。E-mail:
Design and Numerical Simulation of a Deep Learning-Based Model for Wet Metallurgical Parameter Prediction and Optimization
Chunyan LIU, Jingpu JIA
Affiliations
  • Computer Application Department, Shijiazhuang Information Engineering Vocational College, Shijiazhuang 052161, China
出版时间: 2025-04-28 doi: 10.13355/j.cnki.sfyj.2025.02.016
文章导航
收藏切换

针对湿法冶金工艺参数预测中存在的预测模型计算效率低及智能化程度不足等问题,提出了一个基于1D-CNN算法预测铜离子浓度、Seq2Seq模型预测传质速率,并以经济效益最大化为目标的流程优化控制模型,并采用DDPG算法求解最优化问题。数值仿真和实证研究结果表明,该模型对铜萃取流程工艺参数的预测准确度较高,可实现对参数的有效优化调整,从而促进经济效益提升。

铜  /  萃取  /  湿法冶金  /  DDPG  /  1D-CNN  /  Seq2Seq  /  数值仿真

Aiming at the issues of low computational efficiency and insufficient intelligence in predicting hydrometallurgical process parameters, a process optimization control model that utilizes 1D-CNN for predicting copper ion concentration and Seq2Seq for predicting mass transfer rate, with the objective of maximizing economic benefits was proposed. The optimization problem is solved using the DDPG algorithm. The results of numerical simulation and empirical study show that the model can predict the parameters of copper extraction process with high accuracy, realize the effective optimization and adjustment of parameters, and promote the improvement of economic benefits.

copper  /  extraction  /  hydrometallurgy  /  DDPG  /  1D-CNN  /  Seq2Seq  /  numerical simulation
刘春艳, 贾景谱. 基于深度学习的湿法冶金工艺参数预测与优化模型的设计及数值仿真研究. 湿法冶金, 2025 , 44 (2) : 264 -270 . DOI: 10.13355/j.cnki.sfyj.2025.02.016
Chunyan LIU, Jingpu JIA. Design and Numerical Simulation of a Deep Learning-Based Model for Wet Metallurgical Parameter Prediction and Optimization[J]. Hydrometallurgy of China, 2025 , 44 (2) : 264 -270 . DOI: 10.13355/j.cnki.sfyj.2025.02.016
在湿法冶金过程中,通过对关键工艺参数进行准确预测可优化工艺流程,提高资源利用率与生产效率,同时确保生产稳定性,从而提高最终产品纯度和性能;此外,还有助于提前了解生产过程中可能存在的风险,保证生产安全[1-2]。湿法冶金工艺参数的预测研究是实现冶金工艺智能化、自动化的基础,将预测与控制模型相结合,能够实现冶金过程的实时监控与自动调整[3-4],因此,对湿法冶金工艺参数进行预测研究具有重要意义。
目前,关于湿法冶金工艺参数预测的相关研究已取得一定进展。如基于区间RBF神经元网络对湿法冶金过程金泥品位的预测模型[5]可实现金泥品位的在线预测,金氰化浸出过程的动态串联型混合模型[6]通过利用物料守恒方程建立金氰化浸出过程的动态机制模型,并利用神经网络估计机制模型中的未知参数,可实现参与预测。但这2个模型的智能化程度都不够高,计算效率仍有待提升。由参数未知的机制模型串联参数未知的数据预测模型组成的混合模型[7],采用核偏最小二乘法建立了参数预测模型,能显著增强智能化参数预测能力,但在参数预测准确性方面仍需进一步优化。
为解决上述问题,以铜萃取[8]为例,研究提出了一个基于多参数预测结合DDPG(Deep Deterministic Policy Gradient)深度学习算法[9]的混合预测模型,以及基于该预测模型的铜萃取过程优化控制方法。该方法首先使用1D-CNN(1D Convolutional Neural Network)模型[10]进行萃余液中铜离子浓度的预测,同时使用Seq2Seq(Sequence-to-Sequence)模型[11]进行萃取过程中传质速率的预测,构建一个铜萃取过程的参数优化模型。基于该优化模型及参数预测的结果,采用DDPG算法对铜萃取过程进行优化控制。试验研究了以湿法冶金过程中的智能参数预测为基础,通过高效精细的深度强化学习算法,以期实现湿法冶金全流程的智能化、自动化控制。
1D-CNN(1维卷积神经网络,1D Convolutional Neural Network)是卷积神经网络CNN的一种变体,专门用于处理一维数据,特别适用于时间序列、信号处理、文本数据等顺序性强的数据场景。与二维卷积网络(2D-CNN)[12]不同,1D-CNN仅在一个维度上进行卷积操作,适合分析数据的时间依赖性或序列结构。由于1D-CNN可以并行化执行,训练速度快,因此能有效降低计算时延,解决复杂参数预测模型运行效率较低的问题。1D-CNN模型的计算过程如下:
1)输入数据:1D-CNN 输入的是一维序列数据,假设输入为萃余液铜离子浓度序列X,其形状为X∈${R}^{{n}_{samples}\times sep\_length\times features}$,其中,nsamples为序列样本数量,seq_length为输入序列的长度,features为每个时间步的特征数。
2)卷积层(Convolution Layer):卷积层通过卷积核滑动,提取局部特征。1D卷积的核心公式计算如下:
yt=${\sum }_{i=0}^{k-1} $wi·xt+i+b
式中:yt—卷积输出在时间步t处的值;k—卷积核大小;wi—卷积核权重的第i个参数;xt+i—输入序列在时间步t+i处的值;b—偏置项。
卷积输出序列的长度(根据填充方式和步幅计算):
output_length=$\frac{seq\_length-k+2p}{s}$+1。
式中:seq_length—输入序列长度;k—卷积核的大小;p—填充大小;s—步幅大小。
填充使用Same Padding:
p=$\frac{k-1}{2}$。
3)激活函数(Activation Function):卷积后的输出通常会通过激活函数来引入非线性。本研究采用的激活函数是ReLU,其计算公式如下:
ReLU(z)=max(0,z)。
式中,z—卷积层的输出。
ReLU的输出是一个非负数,如果输入值z小于0,则输出为0,否则输出为z
4)池化层(Pooling Layer):池化层用于下采样,减少特征图的尺寸。1D最大池化层的计算公式如下:
yt=max(xt,xt+1,…,xt+p-1)。
式中:p—池化窗口大小;xt,xt+1,…,xt+p-1—输入序列在池化窗口内的值;yt—池化后的输出值。
池化后的序列长度计算公式为:
pooled_length=$\frac{output\_length-p}{{s}_{p}}$+1,
式中,sp—池化层的步幅。
5)展平层(Flatten Layer):池化层的输出通常是一个三维张量,在全连接层之前需要展平成二维张量。假设池化层输出形状为(nsamples,pooled length,channels),则展平后为:
flattened_output=$\boldsymbol{R}^{nsamples×(pooled×channels)}$
6)全连接层(Fully Connected Layer):展平后的输出进入全连接层进行预测。全连接层的计算公式为:
y=W·x+b
式中:W—全连接层的权重矩阵;x—展平后的输入;b—全连接层的偏置项;y—全连接层的输出。
7)输出层(Output Layer):输出层用于给出预测值,输出值的计算公式为:
y=Wo·x+bo
式中,Wobo—输出层中的权重矩阵、偏置项。
8)损失函数和优化:最后,通过计算损失函数来衡量模型的预测结果和真实值之间的差异,并通过优化器更新参数。本研究所用的损失函数为均方误差,其计算公式为:
MSE=$\frac{1}{N}{\sum }_{i=1}^{N} $(yi-${\stackrel{ ︿}{y}}_{i}$)2
如上所述,1D-CNN模型的计算过程包括对历史萃余液铜离子浓度数据的卷积操作、激活、池化、展平、全连接层和输出层的处理。该模型的结构如图1所示。
传质速率是冶金过程中物质传输的重要参数,通过预测传质速率可预估和优化湿法冶金过程的性能。本研究采用Seq2Seq模型对铜萃取过程传质速率进行预测。
Seq2Seq模型是一种神经网络架构,旨在将输入序列映射到输出序列。它由2个主要部分组成:编码器(Encoder)和解码器(Decoder)。编码器将输入序列压缩成1个固定长度的向量(隐藏状态),捕捉输入序列的语义和结构信息;解码器则从该向量开始,逐步生成输出序列。Seq2Seq模型广泛应用于机器翻译[13]、文本摘要[14]等任务。由于Seq2Seq具备高度的并行性,因此也能够有效降低模型的计算时延,解决模型运行效率低的问题。Seq2Seq模型的计算原理如下:
第1层:输入序列编码(Encoder)。设输入的历史传质速率序列为X:
X=[x1,x2,…,xT]。
式中:xi—第i个时间步的输入向量;T—输入序列长度。
第2层:嵌入层(Embedding Layer)。嵌入操作可表示为:
ei=Embed(xi),
式中,ei—嵌入后的输入向量。
第3层:基于Transformer的编码器(Transformer-based Encoder)。该编码器的核心组件包括:
1)自注意力机制:
Attention(Q,K,V)=softmax$\left(\frac{\boldsymbol{Q} \boldsymbol{K}^{T}}{\sqrt{d_{k}}}\right)$V
式中:Q—查询矩阵;K—键矩阵;V—值矩阵;dk—键向量的维度。
2)位置编码:
PE(t,2i)=sin$\left(\frac{t}{10 {000}^{\frac{2i}{{d}_{model}}}}\right)$;
PE(t,2i+1)=cos $\left(\frac{t}{10 {000}^{\frac{2i}{{d}_{model}}}}\right)$。
式中:PE(t,2i)—时间步t的位置编码中偶数维度;PE(t,2i+1)—时间步t的位置编码中奇数维度;dmodel—模型的维度。
第4层:上下文向量生成。编码器的最终隐藏状态(或状态序列)被用作上下文向量C:
C=Concat(h1,h2,…,hT)。
式中,hT—时间步T的隐藏状态;Concat(·)—用于连接所有时间步的隐藏状态。
第5层:基于Transformer[15]的解码器(Transformer-based Decoder)。解码器的关键组件包括:
1)自注意力机制:
Self-Attention(Q,K,V)=softmax$\left(\frac{\boldsymbol{Q} \boldsymbol{K}^{T}}{\sqrt{d_{k}}}\right)$V
式中:Q—来自解码器的查询矩阵;KV—来自编码器的键和值矩阵。
2)编码器-解码器注意力:
Encode-Decoder Attention(Q,K,V)=softmax$\left(\frac{\boldsymbol{Q} \boldsymbol{K}^{T}}{\sqrt{d_{k}}}\right)$V
式中:Q—来自解码器的查询矩阵;KV—来自编码器的键和值矩阵,dk—键向量的的维度。
第6层:输出层。该层通过全连接层映射到预测的结果值:
$\hat{y}_{t}=\operatorname{softmax}\left(\boldsymbol{W} \boldsymbol{cdot} y_{t}+\boldsymbol{b}\right) \text { 。 }$
式中:$\hat{y}_{t}$—时间步t的预测分布;W—输出权重矩阵;b—偏置项;yt—时间t的观测分布。
综上所述,Seq2Seq 模型通过编码器将输入序列转换为上下文向量,并通过解码器生成输出序列。Seq2Seq模型的结构如图2所示。
为实现铜萃取过程的经济效益最大化,需对铜萃取过程工艺参数进行预测和优化。基于经济效益最大化的铜萃取过程工艺参数优化模型如下:
$\underset{{L}_{0},{L}_{1}}{max}$JB-W=L0(ρ0-ρy)P-k1L1Pc-k2L0ρ0P0
s.t.0 ∧≤L0≤1
0≤L1≤1
η=$\frac{{L}_{0}{\rho }_{0}-{L}_{0}{\rho }_{y}}{{L}_{0}{\rho }_{0}}$≥80%
式中:B—金属铜产品收益,元;W—料液成本,元;ρ0—初始条件下水相中铜离子质量浓度,g/L;ρy—萃余液中铜离子质量浓度,g/L;P—金属铜价格,元/g;PcP0—萃取剂、原始料液价格,元/m3;k1k2—单位换算系数1 000;L0L1—水相、萃取剂流量,m3/h。
由两相流量和铜离子质量浓度可计算出铜萃取率η,其中,铜离子质量浓度通过1D-CNN模型预测得到。
为计算经济效益最大化的铜萃取优化参数,使用DDPG算法对铜萃取过程进行优化控制。DDPG算法是一种用于连续动作空间的强化学习算法,结合了深度学习和确定性策略梯度方法,使用策略网络和价值网络2个主要的深度神经网络。策略网络(Actor)负责生成在给定状态下的动作,而价值网络(Critic)则负责估计这些动作的价值;DDPG使用目标网络和经验回放技术来稳定训练过程。目标网络是策略网络和价值网络的延迟更新副本,经验回放则是一个存储过去经验的缓冲区,用于随机抽取训练样本,从而减少数据之间的相关性并提高训练效率。DDPG算法能够在复杂环境中进行高效学习,因为可以通过从历史经验中获取信息来进行训练,而不是仅依赖于最新的经验。这使得算法在面对动态和复杂的任务时适应性更佳,从而更好地实现铜萃取过程的优化控制。下面是DDPG算法的计算步骤。
第1步:初始化。首先初始化各个网络。
1)初始化策略网络(Actor):生成给定状态下的动作。
μ(s|θμ)with parametersθμ
式中:μ(s | θμ)—策略网络生成的动作;θμ—策略网络的参数。
2)初始化价值网络(Critic):估计状态-动作对的价值。
Q(s,aθQ)with parametersθQ
式中:Q(s,aθQ)—价值网络对状态s和动作a的价值估计;θQ—价值网络的参数。
3)初始化目标网络(策略网络和价值网络的目标副本,延迟更新):
μ'Q'with parametersθμ'θQ'
式中:μ',Q'—策略网络和价值网络的目标副本;θμ',θQ'—网络参数。
4)初始化经验回放缓冲区D:存储历史经验。
第2步:数据收集。
1)选择动作:
at=μ(stθμ)+N
式中:at—时间步t的动作;N—噪声。
2)执行动作并收集经验。
3)存储经验:
DD∪{(st,at,rt,st+1)}。
第3步:更新网络。首先,从缓冲区随机抽取一批经验{(si,ai,ri,si+1)}更新Critic网络。
1)计算目标值:
yi=ri+γQ'(si+1,μ'(si+1θμ')∨θQ')。
式中:yi—目标值;γ—折扣因子。
2)计算损失函数:
L(θQ)=$\frac{1}{N}$∑i$({y}_{i}-\boldsymbol{Q}({s}_{i},{a}_{i}|{\boldsymbol{theta} }^{Q}{\left)\right)}^{2}$,
式中,N—批次大小。
3)更新Critic网络参数:
θQθQ-λQ${\Delta }_{{\boldsymbol{theta} }^{Q}}$L(θQ),
式中,λQ—Critic网络的学习率。
之后,从缓冲区随机抽取一批经验{(si,ai,ri,si+1)}更新Actor网络。
1)计算梯度:
${\Delta }_{{\theta }^{\boldsymbol{u} }}$J=$\frac{1}{N}$∑iΔaQ(si,ai|θQ)${\Delta }_{{\theta }^{\mu }}$μ(si|θμ)。
式中:ΔaQ(si,aiθQ)—对动作的价值函数梯度;${\Delta }_{{\theta }^{\mu }}$μ(siθμ)—对策略网络参数的梯度。
2)更新Actor网络参数:
θμθμ+λμ${\Delta }_{{\theta }^{\boldsymbol{u} }}$J,
式中,λμ—Actor网络的学习率。
第4步:更新目标网络。目标网络参数更新公式为:
θμ'τθμ+(1-τ)θμ';
θQ'τθQ+(1-τ)θQ'
式中,τ—软更新系数,是一个小的常数,设为0.001。
DDPG的计算过程包括初始化网络和目标网络、与环境交互以收集数据、从经验回放缓冲区抽取数据来更新Critic和Actor网络,以及通过软更新技术来更新目标网络。通过上述步骤可以实现对铜萃取过程中工艺参数的有效学习和优化。图3为DDPG算法的原理。
为了评估本方法的有效性,分别进行多个试验、数值仿真及1个实证研究,从多个角度评价该方法的实际表现。
铜萃取的仿真试验环境共分为3个阶段:萃取、洗涤和反萃,如图4所示。在该环境下对使用本方法前、后经济效益进行对比,结果见表1。可以看出:使用本方法后,经济效益有明显提升,说明该法能实现对铜萃取工艺流程的优化。
为了评价1D-CNN/Seq2Seq模型对工艺参数的预测准确性,对比研究了该模型与其他4个基线模型对萃余液铜离子浓度的预测和传质速率的预测均方误差(MSE)、均方根误差(RMSE)和平均绝对误差(MAE),结果见表2。可以看出:相比4种基线模型,1D-CNN/Seq2Seq模型对萃余液中铜离子浓度及传质速率的预测评价指标更佳,表明1D-CNN/Seq2Seq模型能更好地预测铜萃取工艺参数变化情况。
为了对铜萃取过程的优化控制进行数值仿真,在考虑了各类成本基础上模拟真实的铜萃取过程,通过数值仿真数据绘制了多次模型迭代下的投入经济效益变化曲线,如图5所示。可以看出:随迭代次数增加,本方法的经济效益迅速增加,对应的成本迅速下降,说明该方法能够有效降低成本,提高经济效益。
为考察本方法在实际生产中的效果,将其应用于某铜萃取工厂的工艺流程优化中,并将当月实施本方法前、后的经济效益进行对比,结果见表3。可以看出:该工厂在实施了本方法后,经济效益得到了显著提升。
实证研究结果表明,利用实时数据分析和模型预测,系统能够优化反应条件,确保工艺始终保持在最佳状态下运行。这种精细化控制方式可减少原材料浪费,有效提升金属回收率。同时,通过智能控制系统还能够及时识别并调整工艺运行过程中发生的异常情况,降低设备故障率和停机时间。此外,该模型具有智能学习能力,能不断适应生产环境的变化,从而进一步提高生产效率和设备控制的灵活性。
针对某铜萃取流程,使用1D-CNN/Seq2Seq模型可较准确地预测萃余液铜离子浓度和传质速率,再通过DDPG算法求解,能实现铜萃取工艺参数的优化,确保工艺始终保持在最佳状态下运行。该模型的应用能有效降低生产成本,实现对资源的更高效利用,降低运营风险,从而实现整体经济效益的提升。
参考文献 引证文献
排序方式:
[1]
孙宁磊, 吴筱, 殷书岩, 等. 红土镍矿湿法冶金工艺参数调整对钪走向的影响[J]. 中国有色冶金, 2022, 51(5):68-72.
SUN Ninglei, WU Xiao, YIN Shuyan, et al. Scandium distribution with parameters adjustment in nickel laterite hydrometallurgical process[J]. China Nonferrous Metallurgy, 2022, 51(5):68-72.
[2]
高娜. 响应曲面法优化废电路板浸金工艺参数试验研究[J]. 湿法冶金, 2022, 41(6):553-557.
GAO Na. Optimizing leaching conditions of gold from waste printed circuit boards by response surface methodology[J]. Hydrometallurgy of China, 2022, 41(6):553-557.
[3]
郭计敏. 金氰化浸出过程非线性预测控制方法及仿真算法分析研究[J]. 湿法冶金, 2023, 42(6):659-665.
GUO Jimin. Nonlinear predictive control method and simulation algorithm analysis of gold cyanide leaching process[J]. Hydrometallurgy of China, 2023, 42(6):659-665.
[4]
顾群. 湿法冶金下游流程的分层优化及全流程优化仿真算法分析研究[J]. 湿法冶金, 2023, 42(2):205-214.
GU Qun. Hierarchical optimization and whole process optimization simulation algorithm of hydrometallurgy downstream process[J]. Hydrometallurgy of China, 2023, 42(2):205-214.
[5]
张强. 基于区间RBF神经元网络的湿法冶金金品位预测[D]. 沈阳: 东北大学, 2018.
[6]
张俊, 毛志忠, 贾润达, 等. 湿法冶金浸出过程金浓度的混合预报模型[J]. 仪器仪表学报, 2013, 34(3):629-634.
ZHANG Qiang, MAO Zhizhong, JIA Runda, et al. Hybrid predictive model of gold concentration for hydrometallurgy leaching process[J]. Chinese Journal of Scientific Instrument, 2013, 34(3):629-634.
[7]
陈溥. 基于核偏最小二乘法的湿法冶金萃取过程建模[J]. 湿法冶金, 2021, 40(3):260-266.
CHEN Pu. Modeling for solvent extraction of copper based on kernel partial least squares method[J]. Hydrometallurgy of China, 2021, 40(3):260-266.
[8]
张海宝, 陈燕杰, 伏晓丹, 等. 提高铜钴矿湿法冶金过程铜钴回收率的方法概述[J]. 铜业工程, 2022(5):70-73.
ZHANG Haibao, CHEN Yanjie, FU Xiaodan, et al. Methods of improving recovery rate of copper and cobalt in hydrometallurgical process of copper-cobalt oxide ore[J]. Copper Engineering, 2022(5):70-73.
[9]
曹绍华, 姜佳佳, 陈舒, 等. A-DDPG:多用户边缘计算系统的卸载研究[J]. 计算机工程与应用, 2023, 59(1):259-268.
CAO Shaohua, JIANG Jiajia, CHEN Shu, et al. A-DDPG:research on offloading of multi-user edge computing system[J]. Computer Engineering and Applications, 2023, 59(1):259-268.
[10]
马珂, 毕大平, 周圣栾, 等. 基于1DCNN的机载火控雷达空空工作状态识别[J]. 现代雷达, 2023, 45(3):17-23.
MA Ke, BI Daping, ZHOU Shengluan, et al. Air-to-air working state recognition of airborne fire control radar based on 1DCNN[J]. Modern Radar, 2023, 45(3):17-23.
[11]
王文婷, 刘姝君, 张耀聪, 等. 基于Seq2Seq深度学习模型的焦炉煤气发生量预测方法研究[J]. 兰州理工大学学报, 2023, 49(5):50-58.
WANG Wenting, LIU Shujun, ZHANG Yaocong, et al. Prediction of coke oven gas generation based on Seq2Seq[J]. Journal of Lanzhou University of Technology, 2023, 49(5):50-58.
[12]
吉晨钟, 次旺晋美, 张伟, 等. 改进2D CNN时空特征提取的动作识别研究[J]. 小型微型计算机系统, 2024, 45(1):168-176.
JI Chenzhong, CI Wangjinmei, ZHANG Wei, et al. Research on action recognition based on improving 2D CNN spatial-temporal feature extraction[J]. Journal of Chinese Computer Systems, 2024, 45(1):168-176.
[13]
刘晓娟. 基于改进Seq2Seq的翻译机器人纠错系统设计[J]. 自动化与仪器仪表, 2023(4):201-205.
LIU Xiaojuan. Design of translation robot error correction system based on improved Seq2Seq[J]. Automation & Instrumentation, 2023(4):201-205.
[14]
门鼎, 陈亮. 基于改进Seq2Seq-Attention模型的文本摘要生成方法[J]. 电子设计工程, 2022, 30(23):6-10.
MEN Ding, CHEN Liang. Text summary generation method based on improved Seq2Seq-Attention model[J]. Electronic Design Engineering, 2022, 30(23):6-10.
[15]
宫昀. 基于Transformer模型的神经机器翻译改进方法研究[J]. 自动化与仪器仪表, 2023(8):257-261.
GONG Yun. Research on improved neural machine translation method based on transformer model[J]. Automation & Instrumentation, 2023(8):257-261.
2025年第44卷第2期
PDF下载
416
173
引用本文
BibTeX
文章信息
doi: 10.13355/j.cnki.sfyj.2025.02.016
  • 接收时间:2024-09-10
  • 首发时间:2025-07-05
  • 出版时间:2025-04-28
补充材料
相关文章
文章信息
作者
出版历史
  • 收稿日期:2024-09-10
基金
作者信息
    石家庄信息工程职业学院 计算机应用系, 河北 石家庄 052161

通讯作者:

贾景谱(1979—),女,硕士,副教授,主要研究方向为电子信息技术。E-mail:
参考文献
分享链接
https://castjournals.cast.org.cn/joweb/sfyj/CN/10.13355/j.cnki.sfyj.2025.02.016
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