Article(id=1241406723555127764, tenantId=1146029695717560320, journalId=1235980550691926019, issueId=1241406711219680205, articleNumber=null, orderNo=null, doi=10.3969/j.issn.0253-6099.2024.06.031, pmid=null, cstr=null, oa=null, hot=null, price=null, onlineType=0, articleFormat=0, articleType=null, articleTypeStr=null, receivedDate=1716566400000, receivedDateStr=2024-05-25, revisedDate=null, revisedDateStr=null, acceptedDate=null, acceptedDateStr=null, onlineDate=1773904027117, onlineDateStr=2026-03-19, pubDate=1732982400000, pubDateStr=2024-12-01, doiRegisterDate=null, doiRegisterDateStr=null, onlineIssueDate=1773904027117, onlineIssueDateStr=2026-03-19, onlineJustAcceptDate=null, onlineJustAcceptDateStr=null, onlineFirstDate=null, onlineFirstDateStr=null, sourceXml=null, magXml=null, createTime=1773904027117, creator=13701087609, updateTime=1773904027117, updator=13701087609, issue=Issue{id=1241406711219680205, tenantId=1146029695717560320, journalId=1235980550691926019, year='2024', volume='44', issue='6', pageStart='1', pageEnd='174', issueExtLink='null', onlineDate='null', pubDate='null', beforeIssueId=null, nextIssueId=null, price=null, status=1, issueComplete=1, articleOrder=1, issueType=-1, specialIssue=null, createTime=1773904024176, creator=13701087609, updateTime=1773911273793, updator=13701087609, preIssue=null, nextIssue=null, ext={EN=IssueExt(id=1241437118384362345, tenantId=1146029695717560320, journalId=1235980550691926019, issueId=1241406711219680205, language=EN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=), CN=IssueExt(id=1241437118388556650, tenantId=1146029695717560320, journalId=1235980550691926019, issueId=1241406711219680205, language=CN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=)}, issueFiles=null}, startPage=144, endPage=150, ext={EN=ArticleExt(id=1241406725098631656, articleId=1241406723555127764, tenantId=1146029695717560320, journalId=1235980550691926019, language=EN, title=Weighted Prediction Model of Hot Rolled Strip Crown Based on Random Forest and Support Vector Machine, columnId=1236276108207902848, journalTitle=Mining and Metallurgical Engineering, columnName=MATERIALS, runingTitle=null, highlight=null, articleAbstract=

In view of low prediction accuracy and slow speed of traditional prediction methods for strip crown, a weighted prediction model based on random forest (RF) and support vector machine (SVM) was established. The parameters of models based on RF, SVM, and a combination of RF and SVM were optimized respectively by adopting the improved coati optimization algorithm (ICOA), so as to improve crown prediction accuracy. A 1 580 mm production line of a hot-rolling mill in one company was taken in a simulation research on crown prediction based on its actual measurement. The root mean square error of the weighted prediction model based on RF and SVM is 2.23 μm. It is found that this weighted prediction model has its prediction accuracy increased by 7.08% and 2.62% respectively, compared with the models based on RF and SVM respectively.

, correspAuthors=null, 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=Yaluo ZHOU, Zixuan LI, Shaochuan ZHANG, Wenguang LIU, Ruicheng ZHANG), CN=ArticleExt(id=1241406739266990320, articleId=1241406723555127764, tenantId=1146029695717560320, journalId=1235980550691926019, language=CN, title=基于随机森林与支持向量机的热轧带钢凸度加权预测模型研究, columnId=1236276110049202322, journalTitle=矿冶工程杂志, columnName=材料, runingTitle=null, highlight=null, articleAbstract=

针对传统带钢凸度预测方法预测精度低、速度慢的问题,建立了基于随机森林和支持向量机的热轧带钢凸度加权预测模型。采用改进长鼻浣熊算法分别对随机森林、支持向量机和随机森林与支持向量机加权预测模型的参数进行优化,提高凸度预测精度。以某公司热轧1 580 mm生产线实测数据进行凸度预测仿真研究,随机森林与支持向量机加权预测模型的均方根误差为2.23 μm,与随机森林模型、支持向量机模型预测精度进行比较,加权预测模型的精度分别提高了7.08%、2.62%。

, correspAuthors=null, authorNote=null, correspAuthorsNote=null, copyrightStatement=null, copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=JYkf810mL70ccS45G4uYbg==, magXml=UIzac+DxpPzVMEfHxsEHqQ==, pdfUrl=null, pdf=q0sMjgLoG4kUQcOqJJ30zA==, pdfFileSize=1975183, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=lzQAr83uf3xsinb9l01BqQ==, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=PO2cuidwicVLk6N9KJC8OQ==, mapNumber=null, authorCompany=null, fund=null, authors=

周亚罗(1982—),女,河北安平人,硕士,副教授,主要研究方向为复杂系统的建模与控制。E-mail:

, authorsList=周亚罗, 李子轩, 张少川, 刘文广, 张瑞成)}, authors=[Author(id=1241406739707392260, tenantId=1146029695717560320, journalId=1235980550691926019, articleId=1241406723555127764, orderNo=0, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=550589525@qq.com, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1241406739812249860, tenantId=1146029695717560320, journalId=1235980550691926019, articleId=1241406723555127764, authorId=1241406739707392260, language=EN, stringName=Yaluo ZHOU, firstName=Yaluo, middleName=null, lastName=ZHOU, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1.College of Electrical Engineering, North China University of Science and Technology, Tangshan 063210, Hebei, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1241406739887747334, tenantId=1146029695717560320, journalId=1235980550691926019, articleId=1241406723555127764, authorId=1241406739707392260, language=CN, stringName=周亚罗, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1.华北理工大学 电气工程学院,河北 唐山 063210, bio={"content":"

周亚罗(1982—),女,河北安平人,硕士,副教授,主要研究方向为复杂系统的建模与控制。E-mail:

"}, bioImg=null, bioContent=

周亚罗(1982—),女,河北安平人,硕士,副教授,主要研究方向为复杂系统的建模与控制。E-mail:

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1241406739493482744, tenantId=1146029695717560320, journalId=1235980550691926019, articleId=1241406723555127764, xref=1., ext=[AuthorCompanyExt(id=1241406739501871353, tenantId=1146029695717560320, journalId=1235980550691926019, articleId=1241406723555127764, companyId=1241406739493482744, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.College of Electrical Engineering, North China University of Science and Technology, Tangshan 063210, Hebei, China), AuthorCompanyExt(id=1241406739510259962, tenantId=1146029695717560320, journalId=1235980550691926019, articleId=1241406723555127764, companyId=1241406739493482744, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.华北理工大学 电气工程学院,河北 唐山 063210)])]), Author(id=1241406739984216331, tenantId=1146029695717560320, journalId=1235980550691926019, articleId=1241406723555127764, orderNo=1, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1241406740101656849, tenantId=1146029695717560320, journalId=1235980550691926019, articleId=1241406723555127764, authorId=1241406739984216331, language=EN, stringName=Zixuan LI, firstName=Zixuan, middleName=null, lastName=LI, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1.College of Electrical Engineering, North China University of Science and Technology, Tangshan 063210, Hebei, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1241406740189737236, tenantId=1146029695717560320, journalId=1235980550691926019, articleId=1241406723555127764, authorId=1241406739984216331, language=CN, stringName=李子轩, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1.华北理工大学 电气工程学院,河北 唐山 063210, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1241406739493482744, tenantId=1146029695717560320, journalId=1235980550691926019, articleId=1241406723555127764, xref=1., ext=[AuthorCompanyExt(id=1241406739501871353, tenantId=1146029695717560320, journalId=1235980550691926019, articleId=1241406723555127764, companyId=1241406739493482744, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.College of Electrical Engineering, North China University of Science and Technology, Tangshan 063210, Hebei, China), AuthorCompanyExt(id=1241406739510259962, tenantId=1146029695717560320, journalId=1235980550691926019, articleId=1241406723555127764, companyId=1241406739493482744, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.华北理工大学 电气工程学院,河北 唐山 063210)])]), Author(id=1241406740357509400, tenantId=1146029695717560320, journalId=1235980550691926019, articleId=1241406723555127764, orderNo=2, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1241406740453978394, tenantId=1146029695717560320, journalId=1235980550691926019, articleId=1241406723555127764, authorId=1241406740357509400, language=EN, stringName=Shaochuan ZHANG, firstName=Shaochuan, middleName=null, lastName=ZHANG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1.College of Electrical Engineering, North China University of Science and Technology, Tangshan 063210, Hebei, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1241406740592390427, tenantId=1146029695717560320, journalId=1235980550691926019, articleId=1241406723555127764, authorId=1241406740357509400, language=CN, stringName=张少川, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1.华北理工大学 电气工程学院,河北 唐山 063210, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1241406739493482744, tenantId=1146029695717560320, journalId=1235980550691926019, articleId=1241406723555127764, xref=1., ext=[AuthorCompanyExt(id=1241406739501871353, tenantId=1146029695717560320, journalId=1235980550691926019, articleId=1241406723555127764, companyId=1241406739493482744, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.College of Electrical Engineering, North China University of Science and Technology, Tangshan 063210, Hebei, China), AuthorCompanyExt(id=1241406739510259962, tenantId=1146029695717560320, journalId=1235980550691926019, articleId=1241406723555127764, companyId=1241406739493482744, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.华北理工大学 电气工程学院,河北 唐山 063210)])]), Author(id=1241406740663693598, tenantId=1146029695717560320, journalId=1235980550691926019, articleId=1241406723555127764, orderNo=3, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1241406740751773985, tenantId=1146029695717560320, journalId=1235980550691926019, articleId=1241406723555127764, authorId=1241406740663693598, language=EN, stringName=Wenguang LIU, firstName=Wenguang, middleName=null, lastName=LIU, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2.Shougang Jingtang United Iron and Steel Co., Ltd., Tangshan 063200, Hebei, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1241406740844048677, tenantId=1146029695717560320, journalId=1235980550691926019, articleId=1241406723555127764, authorId=1241406740663693598, language=CN, stringName=刘文广, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2.首钢京唐钢铁联合有限责任公司,河北 唐山 063200, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1241406739619311869, tenantId=1146029695717560320, journalId=1235980550691926019, articleId=1241406723555127764, xref=2., ext=[AuthorCompanyExt(id=1241406739627700478, tenantId=1146029695717560320, journalId=1235980550691926019, articleId=1241406723555127764, companyId=1241406739619311869, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.Shougang Jingtang United Iron and Steel Co., Ltd., Tangshan 063200, Hebei, China), AuthorCompanyExt(id=1241406739636089087, tenantId=1146029695717560320, journalId=1235980550691926019, articleId=1241406723555127764, companyId=1241406739619311869, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.首钢京唐钢铁联合有限责任公司,河北 唐山 063200)])]), Author(id=1241406740965683497, tenantId=1146029695717560320, journalId=1235980550691926019, articleId=1241406723555127764, orderNo=4, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1241406741053763885, tenantId=1146029695717560320, journalId=1235980550691926019, articleId=1241406723555127764, authorId=1241406740965683497, language=EN, stringName=Ruicheng ZHANG, firstName=Ruicheng, middleName=null, lastName=ZHANG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1.College of Electrical Engineering, North China University of Science and Technology, Tangshan 063210, Hebei, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1241406741137649968, tenantId=1146029695717560320, journalId=1235980550691926019, articleId=1241406723555127764, authorId=1241406740965683497, language=CN, stringName=张瑞成, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1.华北理工大学 电气工程学院,河北 唐山 063210, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1241406739493482744, tenantId=1146029695717560320, journalId=1235980550691926019, articleId=1241406723555127764, xref=1., ext=[AuthorCompanyExt(id=1241406739501871353, tenantId=1146029695717560320, journalId=1235980550691926019, articleId=1241406723555127764, companyId=1241406739493482744, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.College of Electrical Engineering, North China University of Science and Technology, Tangshan 063210, Hebei, China), AuthorCompanyExt(id=1241406739510259962, tenantId=1146029695717560320, journalId=1235980550691926019, articleId=1241406723555127764, companyId=1241406739493482744, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.华北理工大学 电气工程学院,河北 唐山 063210)])])], keywords=[Keyword(id=1241406741229924660, tenantId=1146029695717560320, journalId=1235980550691926019, articleId=1241406723555127764, language=EN, orderNo=1, keyword=crown prediction), Keyword(id=1241406741305422135, tenantId=1146029695717560320, journalId=1235980550691926019, articleId=1241406723555127764, language=EN, orderNo=2, keyword=hot rolling strip), Keyword(id=1241406741397696825, tenantId=1146029695717560320, journalId=1235980550691926019, articleId=1241406723555127764, language=EN, orderNo=3, keyword=support vector machine (SVM)), Keyword(id=1241406742962172219, tenantId=1146029695717560320, journalId=1235980550691926019, articleId=1241406723555127764, language=EN, orderNo=4, keyword=coati optimization algorithm (COA)), Keyword(id=1241406743033475389, tenantId=1146029695717560320, journalId=1235980550691926019, articleId=1241406723555127764, language=EN, orderNo=5, keyword=crown), Keyword(id=1241406743096389952, tenantId=1146029695717560320, journalId=1235980550691926019, articleId=1241406723555127764, language=EN, orderNo=6, keyword=random forest (RF)), Keyword(id=1241406743192858947, tenantId=1146029695717560320, journalId=1235980550691926019, articleId=1241406723555127764, language=CN, orderNo=1, keyword=凸度预测), Keyword(id=1241406743276745030, tenantId=1146029695717560320, journalId=1235980550691926019, articleId=1241406723555127764, language=CN, orderNo=2, keyword=热轧带钢), Keyword(id=1241406743373214026, tenantId=1146029695717560320, journalId=1235980550691926019, articleId=1241406723555127764, language=CN, orderNo=3, keyword=支持向量机), Keyword(id=1241406743482265932, tenantId=1146029695717560320, journalId=1235980550691926019, articleId=1241406723555127764, language=CN, orderNo=4, keyword=长鼻浣熊算法), Keyword(id=1241406743599706448, tenantId=1146029695717560320, journalId=1235980550691926019, articleId=1241406723555127764, language=CN, orderNo=5, keyword=凸度), Keyword(id=1241406743700369748, tenantId=1146029695717560320, journalId=1235980550691926019, articleId=1241406723555127764, language=CN, orderNo=6, keyword=随机森林)], refs=[Reference(id=1241406748163109257, tenantId=1146029695717560320, journalId=1235980550691926019, articleId=1241406723555127764, doi=null, pmid=null, pmcid=null, year=2019, volume=39, issue=2, pageStart=128, pageEnd=132, url=null, language=null, rfNumber=[1], rfOrder=0, authorNames=王贵成, 贺振, 高俊丽, journalName=矿冶工程, refType=null, unstructuredReference=王贵成, 贺振, 高俊丽. 基于灰色系统理论的我国钢铁产业与GDP关系研究[J]. 矿冶工程, 2019, 39(2): 128-132., articleTitle=基于灰色系统理论的我国钢铁产业与GDP关系研究, refAbstract=null), Reference(id=1241406748234412426, tenantId=1146029695717560320, journalId=1235980550691926019, articleId=1241406723555127764, doi=null, pmid=null, pmcid=null, year=2018, volume=38, issue=1, pageStart=111, pageEnd=114, url=null, language=null, rfNumber=[2], rfOrder=1, authorNames=田宝亮, 牛培峰, journalName=矿冶工程, refType=null, unstructuredReference=田宝亮, 牛培峰. 基于GA-BP神经网络的弯辊力预设定模型研究与应用[J]. 矿冶工程, 2018, 38(1): 111-114., articleTitle=基于GA-BP神经网络的弯辊力预设定模型研究与应用, refAbstract=null), Reference(id=1241406748318298507, tenantId=1146029695717560320, journalId=1235980550691926019, articleId=1241406723555127764, doi=null, pmid=null, pmcid=null, year=2009, volume=26, issue=6, pageStart=29, pageEnd=32, url=null, language=null, rfNumber=[3], rfOrder=2, authorNames=周莲莲, 白振华, 李亮亮, journalName=轧钢, refType=null, unstructuredReference=周莲莲, 白振华, 李亮亮, 等. UCM冷连轧机组基于机理模型的板形与板凸度在线综合控制技术[J]. 轧钢, 2009, 26(6): 29-32., articleTitle=UCM冷连轧机组基于机理模型的板形与板凸度在线综合控制技术, refAbstract=null), Reference(id=1241406748393795980, tenantId=1146029695717560320, journalId=1235980550691926019, articleId=1241406723555127764, doi=null, pmid=null, pmcid=null, year=2017, volume=53, issue=2, pageStart=61, pageEnd=66, url=null, language=null, rfNumber=[4], rfOrder=3, authorNames=陈胜利, 何安瑞, 徐致让, journalName=机械工程学报, refType=null, unstructuredReference=陈胜利, 何安瑞, 徐致让, 等. 一个轧制单元内实时辊系综合凸度预测及应用[J]. 机械工程学报, 2017, 53(2): 61-66., articleTitle=一个轧制单元内实时辊系综合凸度预测及应用, refAbstract=null), Reference(id=1241406748490264973, tenantId=1146029695717560320, journalId=1235980550691926019, articleId=1241406723555127764, doi=null, pmid=null, pmcid=null, year=2023, volume=40, issue=1, pageStart=90, pageEnd=96, url=null, language=null, rfNumber=[5], rfOrder=4, authorNames=汪龙军, 丁成砚, 范宇超, journalName=轧钢, refType=null, unstructuredReference=汪龙军, 丁成砚, 范宇超, 等. 基于深度森林的热轧带钢凸度预测模型[J]. 轧钢, 2023, 40(1): 90-96., articleTitle=基于深度森林的热轧带钢凸度预测模型, refAbstract=null), Reference(id=1241406748561568142, tenantId=1146029695717560320, journalId=1235980550691926019, articleId=1241406723555127764, doi=null, pmid=null, pmcid=null, year=2019, volume=50, issue=11, pageStart=2743, pageEnd=2752, url=null, language=null, rfNumber=[6], rfOrder=5, authorNames=曹建国, 江军, 赵秋芳, journalName=中南大学学报, refType=null, unstructuredReference=曹建国, 江军, 赵秋芳, 等. 基于数据挖掘的宽厚板板凸度控制[J]. 中南大学学报, 2019, 50(11): 2743-2752., articleTitle=基于数据挖掘的宽厚板板凸度控制, refAbstract=null), Reference(id=1241406748628677007, tenantId=1146029695717560320, journalId=1235980550691926019, articleId=1241406723555127764, doi=null, pmid=null, pmcid=null, year=2024, volume=59, issue=1, pageStart=99, pageEnd=107, url=null, language=null, rfNumber=[7], rfOrder=6, authorNames=王优龙, 李维刚, 王永强, journalName=钢铁, refType=null, unstructuredReference=王优龙, 李维刚, 王永强. 基于集成特征选择和SVR的热连轧板凸度预测[J]. 钢铁, 2024, 59(1): 99-107., articleTitle=基于集成特征选择和SVR的热连轧板凸度预测, refAbstract=null), Reference(id=1241406748695785872, tenantId=1146029695717560320, journalId=1235980550691926019, articleId=1241406723555127764, doi=null, pmid=null, pmcid=null, year=2020, volume=31, issue=22, pageStart=2728, pageEnd=2733, url=null, language=null, rfNumber=[8], rfOrder=7, authorNames=刘元铭, 王振华, 王涛, journalName=中国机械工程, refType=null, unstructuredReference=刘元铭, 王振华, 王涛, 等. 热轧带钢出口凸度数据驱动建模及智能化预测分析[J]. 中国机械工程, 2020, 31(22): 2728-2733., articleTitle=热轧带钢出口凸度数据驱动建模及智能化预测分析, refAbstract=null), Reference(id=1241406748762894737, tenantId=1146029695717560320, journalId=1235980550691926019, articleId=1241406723555127764, doi=null, pmid=null, pmcid=null, year=2022, volume=21, issue=5, pageStart=364, pageEnd=370, url=null, language=null, rfNumber=[9], rfOrder=8, authorNames=郝学斌, journalName=材料与冶金学报, refType=null, unstructuredReference=郝学斌. 深度信念网络算法下的热连轧板凸度预测模型[J]. 材料与冶金学报, 2022, 21(5): 364-370., articleTitle=深度信念网络算法下的热连轧板凸度预测模型, refAbstract=null), Reference(id=1241406748838392210, tenantId=1146029695717560320, journalId=1235980550691926019, articleId=1241406723555127764, doi=null, pmid=null, pmcid=null, year=2021, volume=28, issue=8, pageStart=2333, pageEnd=2344, url=null, language=null, rfNumber=[10], rfOrder=9, authorNames=姬亚锋, 宋乐宝, 孙杰, journalName=中南大学学报, refType=null, unstructuredReference=姬亚锋, 宋乐宝, 孙杰, 等. 基于SVM和PCA-CS算法的热轧带钢板凸度预测[J]. 中南大学学报, 2021, 28(8): 2333-2344., articleTitle=基于SVM和PCA-CS算法的热轧带钢板凸度预测, refAbstract=null), Reference(id=1241406748934861203, tenantId=1146029695717560320, journalId=1235980550691926019, articleId=1241406723555127764, doi=null, pmid=null, pmcid=null, year=2019, volume=39, issue=2, pageStart=102, pageEnd=107, url=null, language=null, rfNumber=[11], rfOrder=10, authorNames=马志强, 魏立新, 孙浩, journalName=矿冶工程, refType=null, unstructuredReference=马志强, 魏立新, 孙浩, 等. 考虑辊缝摩擦及张力影响的冷轧机非线性振动特性研究[J]. 矿冶工程, 2019, 39(2): 102-107., articleTitle=考虑辊缝摩擦及张力影响的冷轧机非线性振动特性研究, refAbstract=null), Reference(id=1241406749022941588, tenantId=1146029695717560320, journalId=1235980550691926019, articleId=1241406723555127764, doi=null, pmid=null, pmcid=null, year=2023, volume=43, issue=4, pageStart=48, pageEnd=51, url=null, language=null, rfNumber=[12], rfOrder=11, authorNames=王鑫瑀, 曹鹏飞, 肖一清, journalName=矿冶工程, refType=null, unstructuredReference=王鑫瑀, 曹鹏飞, 肖一清, 等. 基于WOA-SVM模型的爆破振动预测研究[J]. 矿冶工程, 2023, 43(4): 48-51., articleTitle=基于WOA-SVM模型的爆破振动预测研究, refAbstract=null), Reference(id=1241406749090050453, tenantId=1146029695717560320, journalId=1235980550691926019, articleId=1241406723555127764, doi=null, pmid=null, pmcid=null, year=2001, volume=45, issue=1, pageStart=5, pageEnd=32, url=null, language=null, rfNumber=[13], rfOrder=12, authorNames=BREIMAN L, journalName=Machine Learning, refType=null, unstructuredReference=BREIMAN L. Random forests[J]. Machine Learning, 2001, 45(1): 5-32., articleTitle=Random forests, refAbstract=null), Reference(id=1241406749194908054, tenantId=1146029695717560320, journalId=1235980550691926019, articleId=1241406723555127764, doi=null, pmid=null, pmcid=null, year=2023, volume=259, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[14], rfOrder=13, authorNames=DEHGHANI M, MONTAZERZ Z, TROJOVSKA E, journalName=Knowledge-Based Systems, refType=null, unstructuredReference=DEHGHANI M, MONTAZERZ Z, TROJOVSKA E, et al. Coati optimization algorithm: a new bio-inspired metaheuristic algorithm for solving optimization problems[J]. Knowledge-Based Systems, 2023, 259: 110011., articleTitle=Coati optimization algorithm: a new bio-inspired metaheuristic algorithm for solving optimization problems, refAbstract=null), Reference(id=1241406749362680215, tenantId=1146029695717560320, journalId=1235980550691926019, articleId=1241406723555127764, doi=null, pmid=null, pmcid=null, year=2017, volume=17, issue=2, pageStart=71, pageEnd=79, url=null, language=null, rfNumber=[15], rfOrder=14, authorNames=TANYILDIZI E, DEMIR G, journalName=Advances in Electrical and Computer Engineering, refType=null, unstructuredReference=TANYILDIZI E, DEMIR G. Golden sine algorithm: a novel math-inspired algorithm[J]. Advances in Electrical and Computer Engineering, 2017, 17(2): 71-79., articleTitle=Golden sine algorithm: a novel math-inspired algorithm, refAbstract=null), Reference(id=1241406749442371992, tenantId=1146029695717560320, journalId=1235980550691926019, articleId=1241406723555127764, doi=null, pmid=null, pmcid=null, year=2023, volume=43, issue=6, pageStart=162, pageEnd=168, url=null, language=null, rfNumber=[16], rfOrder=15, authorNames=周亚罗, 张少川, 刘文广, journalName=矿冶工程, refType=null, unstructuredReference=周亚罗, 张少川, 刘文广, 等. 基于IHPO-KELM的冷轧带钢板形模式识别[J]. 矿冶工程, 2023, 43(6): 162-168., articleTitle=基于IHPO-KELM的冷轧带钢板形模式识别, refAbstract=null), Reference(id=1241406749543035289, tenantId=1146029695717560320, journalId=1235980550691926019, articleId=1241406723555127764, doi=null, pmid=null, pmcid=null, year=2019, volume=39, issue=6, pageStart=124, pageEnd=128, url=null, language=null, rfNumber=[17], rfOrder=16, authorNames=张秀玲, 代景欢, 康学楠, journalName=矿冶工程, refType=null, unstructuredReference=张秀玲, 代景欢, 康学楠, 等. 基于多RBF神经网络的板形数据建模[J]. 矿冶工程, 2019, 39(6): 124-128., articleTitle=基于多RBF神经网络的板形数据建模, refAbstract=null), Reference(id=1241406749631115674, tenantId=1146029695717560320, journalId=1235980550691926019, articleId=1241406723555127764, doi=null, pmid=null, pmcid=null, year=2022, volume=42, issue=2, pageStart=42, pageEnd=45, url=null, language=null, rfNumber=[18], rfOrder=17, authorNames=阳俊, 曾维伟, journalName=矿冶工程, refType=null, unstructuredReference=阳俊, 曾维伟. 基于GA-BP神经网络的采空区地表沉降预测模型[J]. 矿冶工程, 2022, 42(2): 42-45., articleTitle=基于GA-BP神经网络的采空区地表沉降预测模型, refAbstract=null)], funds=[Fund(id=1241406748007920007, tenantId=1146029695717560320, journalId=1235980550691926019, articleId=1241406723555127764, awardId=F2018209201, language=CN, fundingSource=河北省自然科学基金资助项目(F2018209201), fundOrder=null, country=null), Fund(id=1241406748079223176, tenantId=1146029695717560320, journalId=1235980550691926019, articleId=1241406723555127764, awardId=22130213G, language=CN, fundingSource=唐山市科技局科技计划资助项目(22130213G), fundOrder=null, country=null)], companyList=[AuthorCompany(id=1241406739493482744, tenantId=1146029695717560320, journalId=1235980550691926019, articleId=1241406723555127764, xref=1., ext=[AuthorCompanyExt(id=1241406739501871353, tenantId=1146029695717560320, journalId=1235980550691926019, articleId=1241406723555127764, companyId=1241406739493482744, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.College of Electrical Engineering, North China University of Science and Technology, Tangshan 063210, Hebei, China), AuthorCompanyExt(id=1241406739510259962, tenantId=1146029695717560320, journalId=1235980550691926019, articleId=1241406723555127764, companyId=1241406739493482744, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.华北理工大学 电气工程学院,河北 唐山 063210)]), AuthorCompany(id=1241406739619311869, tenantId=1146029695717560320, journalId=1235980550691926019, articleId=1241406723555127764, xref=2., ext=[AuthorCompanyExt(id=1241406739627700478, tenantId=1146029695717560320, journalId=1235980550691926019, articleId=1241406723555127764, companyId=1241406739619311869, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.Shougang Jingtang United Iron and Steel Co., Ltd., Tangshan 063200, Hebei, China), AuthorCompanyExt(id=1241406739636089087, tenantId=1146029695717560320, journalId=1235980550691926019, articleId=1241406723555127764, companyId=1241406739619311869, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.首钢京唐钢铁联合有限责任公司,河北 唐山 063200)])], figs=[ArticleFig(id=1241406743826198869, tenantId=1146029695717560320, journalId=1235980550691926019, articleId=1241406723555127764, language=EN, label=null, caption=null, figureFileSmall=DfICaaVfZW5sSy1NbHcjuA==, figureFileBig=lzQAr83uf3xsinb9l01BqQ==, tableContent=null), ArticleFig(id=1241406743897502039, tenantId=1146029695717560320, journalId=1235980550691926019, articleId=1241406723555127764, language=CN, label=图1, caption=带钢凸度计算示意图, figureFileSmall=DfICaaVfZW5sSy1NbHcjuA==, figureFileBig=lzQAr83uf3xsinb9l01BqQ==, tableContent=null), ArticleFig(id=1241406744098828634, tenantId=1146029695717560320, journalId=1235980550691926019, articleId=1241406723555127764, language=EN, label=null, caption=null, figureFileSmall=QJhepCUvM7wJaFsDuxjXYw==, figureFileBig=sVw6guBnKapGYCip+T3hww==, tableContent=null), ArticleFig(id=1241406744186909020, tenantId=1146029695717560320, journalId=1235980550691926019, articleId=1241406723555127764, language=CN, label=图2, caption=随机森林预测过程示意图, figureFileSmall=QJhepCUvM7wJaFsDuxjXYw==, figureFileBig=sVw6guBnKapGYCip+T3hww==, tableContent=null), ArticleFig(id=1241406744262406494, tenantId=1146029695717560320, journalId=1235980550691926019, articleId=1241406723555127764, language=EN, label=null, caption=null, figureFileSmall=Wd3qRI+JxLeF6IpsPOfjVw==, figureFileBig=QoaCcTUR7GXUdK3cAIB7fg==, tableContent=null), ArticleFig(id=1241406744333709664, tenantId=1146029695717560320, journalId=1235980550691926019, articleId=1241406723555127764, language=CN, label=图3, caption=ICOA优化SVM参数流程图, figureFileSmall=Wd3qRI+JxLeF6IpsPOfjVw==, figureFileBig=QoaCcTUR7GXUdK3cAIB7fg==, tableContent=null), ArticleFig(id=1241406744421790050, tenantId=1146029695717560320, journalId=1235980550691926019, articleId=1241406723555127764, language=EN, label=null, caption=null, figureFileSmall=gOeist0THiw67UoqdlvJiw==, figureFileBig=/th6X5mksWqDhN41GsBrNA==, tableContent=null), ArticleFig(id=1241406744518259044, tenantId=1146029695717560320, journalId=1235980550691926019, articleId=1241406723555127764, language=CN, label=图4, caption=ICOA优化RF参数流程图, figureFileSmall=gOeist0THiw67UoqdlvJiw==, figureFileBig=/th6X5mksWqDhN41GsBrNA==, tableContent=null), ArticleFig(id=1241406744623116646, tenantId=1146029695717560320, journalId=1235980550691926019, articleId=1241406723555127764, language=EN, label=null, caption=null, figureFileSmall=T3LVnfd2BUtOlrx7Q/S+hw==, figureFileBig=xp3uBqhM0+z0uhNWirLP8g==, tableContent=null), ArticleFig(id=1241406744681836904, tenantId=1146029695717560320, journalId=1235980550691926019, articleId=1241406723555127764, language=CN, label=图5, caption=测试函数适应度值收敛曲线

(a)f1收敛曲线;(bf2收敛曲线;(cf3收敛曲线;(df4收敛曲线

, figureFileSmall=T3LVnfd2BUtOlrx7Q/S+hw==, figureFileBig=xp3uBqhM0+z0uhNWirLP8g==, tableContent=null), ArticleFig(id=1241406744757334378, tenantId=1146029695717560320, journalId=1235980550691926019, articleId=1241406723555127764, language=EN, label=null, caption=null, figureFileSmall=T6KKr0xGm9W0sm05n99ZjA==, figureFileBig=G6as//06lZFtL8mZVxXW3A==, tableContent=null), ArticleFig(id=1241406744837026156, tenantId=1146029695717560320, journalId=1235980550691926019, articleId=1241406723555127764, language=CN, label=图6, caption=RF预测模型收敛曲线, figureFileSmall=T6KKr0xGm9W0sm05n99ZjA==, figureFileBig=G6as//06lZFtL8mZVxXW3A==, tableContent=null), ArticleFig(id=1241406744916717933, tenantId=1146029695717560320, journalId=1235980550691926019, articleId=1241406723555127764, language=EN, label=null, caption=null, figureFileSmall=b6EItJkLJxuq7cLMt9cFPA==, figureFileBig=tP2EAOC4t4Ecq6T2t2adWw==, tableContent=null), ArticleFig(id=1241406745004798319, tenantId=1146029695717560320, journalId=1235980550691926019, articleId=1241406723555127764, language=CN, label=图7, caption=SVM预测模型收敛曲线, figureFileSmall=b6EItJkLJxuq7cLMt9cFPA==, figureFileBig=tP2EAOC4t4Ecq6T2t2adWw==, tableContent=null), ArticleFig(id=1241406745071907185, tenantId=1146029695717560320, journalId=1235980550691926019, articleId=1241406723555127764, language=EN, label=null, caption=null, figureFileSmall=g1irI5a3s464x7om1Ujo/g==, figureFileBig=ZY6dRGn8YLeWrFFu1RTlCA==, tableContent=null), ArticleFig(id=1241406745155793267, tenantId=1146029695717560320, journalId=1235980550691926019, articleId=1241406723555127764, language=CN, label=图8, caption=RF与SVM加权预测模型收敛曲线, figureFileSmall=g1irI5a3s464x7om1Ujo/g==, figureFileBig=ZY6dRGn8YLeWrFFu1RTlCA==, tableContent=null), ArticleFig(id=1241406745222902133, tenantId=1146029695717560320, journalId=1235980550691926019, articleId=1241406723555127764, language=EN, label=null, caption=null, figureFileSmall=HnsFw/8kwiga7BuqsaTwjw==, figureFileBig=Q1O3vgT+XCiVb0bHcGVf/w==, tableContent=null), ArticleFig(id=1241406745294205303, tenantId=1146029695717560320, journalId=1235980550691926019, articleId=1241406723555127764, language=CN, label=图9, caption=预测结果对比, figureFileSmall=HnsFw/8kwiga7BuqsaTwjw==, figureFileBig=Q1O3vgT+XCiVb0bHcGVf/w==, tableContent=null), ArticleFig(id=1241406745357119865, tenantId=1146029695717560320, journalId=1235980550691926019, articleId=1241406723555127764, language=EN, label=null, caption=null, figureFileSmall=CXsXS7TzKq+F324xYif4FQ==, figureFileBig=dGr+QDS9MKzo3T2xVUuuRw==, tableContent=null), ArticleFig(id=1241406745453588858, tenantId=1146029695717560320, journalId=1235980550691926019, articleId=1241406723555127764, language=CN, label=图10, caption=预测误差对比, figureFileSmall=CXsXS7TzKq+F324xYif4FQ==, figureFileBig=dGr+QDS9MKzo3T2xVUuuRw==, tableContent=null), ArticleFig(id=1241406745545863547, tenantId=1146029695717560320, journalId=1235980550691926019, articleId=1241406723555127764, language=EN, label=null, caption=null, figureFileSmall=null, figureFileBig=null, tableContent=
测试函数定义域最小值
[-100,100]0
[-10,10]0
[-100,100]0
[-1.28,1.28]0
), ArticleFig(id=1241406745625555324, tenantId=1146029695717560320, journalId=1235980550691926019, articleId=1241406723555127764, language=CN, label=表1, caption=

测试函数

, figureFileSmall=null, figureFileBig=null, tableContent=
测试函数定义域最小值
[-100,100]0
[-10,10]0
[-100,100]0
[-1.28,1.28]0
), ArticleFig(id=1241406745747190141, tenantId=1146029695717560320, journalId=1235980550691926019, articleId=1241406723555127764, language=EN, label=null, caption=null, figureFileSmall=null, figureFileBig=null, tableContent=
函数不同算法求解指标平均值
ICOACOAPSO
f10021.599 4
f26.765 7×10-2623.656 9×10-1960.395 7
f300582.341 2
f42.912 2×10-055.666 8×10-050.015 16
), ArticleFig(id=1241406745831076222, tenantId=1146029695717560320, journalId=1235980550691926019, articleId=1241406723555127764, language=CN, label=表2, caption=

测试函数求解指标统计

, figureFileSmall=null, figureFileBig=null, tableContent=
函数不同算法求解指标平均值
ICOACOAPSO
f10021.599 4
f26.765 7×10-2623.656 9×10-1960.395 7
f300582.341 2
f42.912 2×10-055.666 8×10-050.015 16
), ArticleFig(id=1241406745914962303, tenantId=1146029695717560320, journalId=1235980550691926019, articleId=1241406723555127764, language=EN, label=null, caption=null, figureFileSmall=null, figureFileBig=null, tableContent=
序号特征参数单位
1~7工作辊有效凸度(F1~F7mm
8~14出口厚度(F1~F7mm
15~21轧制力(F1~F7kN
22~28弯辊力(F1~F7kN
29~35窜辊量(F1~F7mm
36宽度mm
37中间坯凸度mm
38中间坯厚度mm
39精轧入口温度
40精轧出口温度
41穿带速度m/s
42末机架出口凸度mm
), ArticleFig(id=1241406747420717440, tenantId=1146029695717560320, journalId=1235980550691926019, articleId=1241406723555127764, language=CN, label=表3, caption=

预测模型输入参数与输出参数列表

, figureFileSmall=null, figureFileBig=null, tableContent=
序号特征参数单位
1~7工作辊有效凸度(F1~F7mm
8~14出口厚度(F1~F7mm
15~21轧制力(F1~F7kN
22~28弯辊力(F1~F7kN
29~35窜辊量(F1~F7mm
36宽度mm
37中间坯凸度mm
38中间坯厚度mm
39精轧入口温度
40精轧出口温度
41穿带速度m/s
42末机架出口凸度mm
), ArticleFig(id=1241406747492020609, tenantId=1146029695717560320, journalId=1235980550691926019, articleId=1241406723555127764, language=EN, label=null, caption=null, figureFileSmall=null, figureFileBig=null, tableContent=
模型名称种群大小最大迭代次数上限下限
RF预测模型305050010
SVM预测模型3050256-256
RF与SVM加权预测模型30501-1
), ArticleFig(id=1241406747550740866, tenantId=1146029695717560320, journalId=1235980550691926019, articleId=1241406723555127764, language=CN, label=表4, caption=

预测模型寻优参数设置

, figureFileSmall=null, figureFileBig=null, tableContent=
模型名称种群大小最大迭代次数上限下限
RF预测模型305050010
SVM预测模型3050256-256
RF与SVM加权预测模型30501-1
), ArticleFig(id=1241406747651404163, tenantId=1146029695717560320, journalId=1235980550691926019, articleId=1241406723555127764, language=EN, label=null, caption=null, figureFileSmall=null, figureFileBig=null, tableContent=
预测模型误差指标
MSE/mm2MAPE/%
RF5.76×10-64.83
SVM5.24×10-64.53
RF-SVM4.98×10-64.43
), ArticleFig(id=1241406747752067460, tenantId=1146029695717560320, journalId=1235980550691926019, articleId=1241406723555127764, language=CN, label=表5, caption=

误差指标计算结果

, figureFileSmall=null, figureFileBig=null, tableContent=
预测模型误差指标
MSE/mm2MAPE/%
RF5.76×10-64.83
SVM5.24×10-64.53
RF-SVM4.98×10-64.43
), ArticleFig(id=1241406747840147845, tenantId=1146029695717560320, journalId=1235980550691926019, articleId=1241406723555127764, language=EN, label=null, caption=null, figureFileSmall=null, figureFileBig=null, tableContent=
预测模型命中率(±5 μm)/%
RF96.3
SVM96.7
RF-SVM97.3
), ArticleFig(id=1241406747907256710, tenantId=1146029695717560320, journalId=1235980550691926019, articleId=1241406723555127764, language=CN, label=表6, caption=

不同误差凸度命中率

, figureFileSmall=null, figureFileBig=null, tableContent=
预测模型命中率(±5 μm)/%
RF96.3
SVM96.7
RF-SVM97.3
)], attaches=null, journal=Journal(id=1235979682521329665, delFlag=0, nameCn=矿冶工程杂志, nameEn=Mining and Metallurgical Engineering, nameHistory1=null, nameHistory2=null, issn=0253-6099, eissn=null, cn=43-1104/TD, coden=null, periodic=1, language=CN, oaType=null, ccby=null, superviseOffice=null, ownerOffice=null, pubOffice=null, editorOffice=null, officeType=null, aims=null, clcCode=null, officeProv=null, officeCity=null, officeAddr=null, officeZip=null, officeEmail=null, officePhone=null, editDirector=null, officeDirector=null, officeDirectorPhone=null, officeStaffNum=null, officeEmpNum=null, coverPicUrl=sIAtluqp1t366oKMF09POA==, journalPrice=null, startedYear=null, abbrevIsoEn=Mining and Metallurgical Engineering, journalRemark=null, publicationField=null, createdTime=1772610119708, updatedTime=1772610494020, createdBy=18614031015, updatedBy=13701087609, firstLetterCn=M, firstLetterEn=M, subjectCode=Engineering, subjectName=null, subjectCodeEn=Engineering, subjectNameEn=null, picCn=sIAtluqp1t366oKMF09POA==, picEn=8lFm/e3VFuRPvwuEPHk4Qg==, jcr=null, cjcr=null, exts=[JournalExt(id=1235981252583551310, language=CN, name=矿冶工程杂志, nameHistory1=null, nameHistory2=null, managedBy=, sponsoredBy=, publishedBy=, editorOffice=, officeProv=null, officeCity=null, officeAddr=, officeZip=, editDirector=, officeDirector=null, officePhone=null, coverPicUrl=null, journalRemark=, submitArticleUrl=null, websiteUrl=, createdTime=1772610494037, updatedTime=1772610494037, createdBy=13701087609, updatedBy=13701087609, submissionGuidelinesUrl=, submissionAuthorUrl=http://www.kygczz.com/Journalx_kygc/authorLogOn.action, submissionEditorUrl=http://www.kygczz.com/Journalx_kygc/editorLogOn.action, submissionReviewUrl=http://www.kygczz.com/Journalx_kygc/expertLogOn.action, submissionCeEditorUrl=, submissionAeEditorUrl=, option={"copyright":""}), JournalExt(id=1235981252633882959, language=EN, name=Mining and Metallurgical Engineering, nameHistory1=null, nameHistory2=null, managedBy=, sponsoredBy=, publishedBy=, editorOffice=, officeProv=null, officeCity=null, officeAddr=, officeZip=, editDirector=, officeDirector=null, officePhone=null, coverPicUrl=null, journalRemark=, submitArticleUrl=null, websiteUrl=, createdTime=1772610494049, updatedTime=1772610494049, createdBy=13701087609, updatedBy=13701087609, submissionGuidelinesUrl=, submissionAuthorUrl=http://www.kygczz.com/Journalx_kygc/authorLogOn.action, submissionEditorUrl=http://www.kygczz.com/Journalx_kygc/editorLogOn.action, submissionReviewUrl=http://www.kygczz.com/Journalx_kygc/expertLogOn.action, submissionCeEditorUrl=, submissionAeEditorUrl=, option={"copyright":""})], databaseList=null, tenantJournalId=1235980550691926019, websiteList=[Website(id=1235982099019256290, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1235980550691926019, 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/kygczz/CN, language=CN, createTime=1772610695843, createBy=18614031015, updateTime=1772610913564, updateBy=18614031015, name=矿冶工程杂志-中文, tplId=1146099689490845704, title=矿冶工程杂志, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1235983631420805700, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1235982099019256290, code=articleTextType, value=kx, createTime=1772611061196, updateTime=1772611061196, creator=18614031015, updator=18614031015), WebsiteProps(id=1235983631378862657, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1235982099019256290, code=banner, value=null, createTime=1772611061186, updateTime=1772611061186, creator=18614031015, updator=18614031015), WebsiteProps(id=1235983631441777223, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1235982099019256290, code=grayFlag, value=0, createTime=1772611061201, updateTime=1772611061201, creator=18614031015, updator=18614031015), WebsiteProps(id=1235983631370474048, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1235982099019256290, code=logo, value=https://castjournals.cast.org.cn/joweb/kygczz/CN/file/pic?fileId=seRpqoNiVtKzuWGeM8/PzA==, createTime=1772611061184, updateTime=1772611061184, creator=18614031015, updator=18614031015), WebsiteProps(id=1235983631454360137, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1235982099019256290, code=minRunFlag, value=0, createTime=1772611061204, updateTime=1772611061204, creator=18614031015, updator=18614031015), WebsiteProps(id=1235983631408222787, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1235982099019256290, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/kygczz/CN/file/pic, createTime=1772611061193, updateTime=1772611061193, creator=18614031015, updator=18614031015), WebsiteProps(id=1235983631445971528, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1235982099019256290, code=silenceFlag, value=0, createTime=1772611061202, updateTime=1772611061202, creator=18614031015, updator=18614031015), WebsiteProps(id=1235983631387251266, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1235982099019256290, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_cn_619/, createTime=1772611061188, updateTime=1772611061188, creator=18614031015, updator=18614031015), WebsiteProps(id=1235983631429194309, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1235982099019256290, code=themeColor, value=null, createTime=1772611061198, updateTime=1772611061198, creator=18614031015, updator=18614031015), WebsiteProps(id=1235983631433388614, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1235982099019256290, code=themeStyle, value=null, createTime=1772611061199, updateTime=1772611061199, creator=18614031015, updator=18614031015)]), Website(id=1235982099262525932, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1235980550691926019, 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/kygczz/EN, language=EN, createTime=1772610695901, createBy=18614031015, updateTime=1772610917908, updateBy=18614031015, name=矿冶工程杂志-英文, tplId=1146101810881728533, title=Mining and Metallurgical Engineering, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1235983658880913998, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1235982099262525932, code=articleTextType, value=kx, createTime=1772611067743, updateTime=1772611067743, creator=18614031015, updator=18614031015), WebsiteProps(id=1235983658864136779, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1235982099262525932, code=banner, value=null, createTime=1772611067739, updateTime=1772611067739, creator=18614031015, updator=18614031015), WebsiteProps(id=1235983658897691217, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1235982099262525932, code=grayFlag, value=0, createTime=1772611067747, updateTime=1772611067747, creator=18614031015, updator=18614031015), WebsiteProps(id=1235983658855748170, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1235982099262525932, code=logo, value=https://castjournals.cast.org.cn/joweb/kygczz/EN/file/pic?fileId=seRpqoNiVtKzuWGeM8/PzA==, createTime=1772611067737, updateTime=1772611067737, creator=18614031015, updator=18614031015), WebsiteProps(id=1235983658910274131, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1235982099262525932, code=minRunFlag, value=0, createTime=1772611067750, updateTime=1772611067750, creator=18614031015, updator=18614031015), WebsiteProps(id=1235983658876719693, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1235982099262525932, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/kygczz/EN/file/pic, createTime=1772611067742, updateTime=1772611067742, creator=18614031015, updator=18614031015), WebsiteProps(id=1235983658901885522, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1235982099262525932, code=silenceFlag, value=0, createTime=1772611067748, updateTime=1772611067748, creator=18614031015, updator=18614031015), WebsiteProps(id=1235983658872525388, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1235982099262525932, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_en_623/, createTime=1772611067741, updateTime=1772611067741, creator=18614031015, updator=18614031015), WebsiteProps(id=1235983658889302607, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1235982099262525932, code=themeColor, value=null, createTime=1772611067745, updateTime=1772611067745, creator=18614031015, updator=18614031015), WebsiteProps(id=1235983658893496912, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1235982099262525932, code=themeStyle, value=null, createTime=1772611067746, updateTime=1772611067746, creator=18614031015, updator=18614031015)])], journalTitle=矿冶工程杂志, weixinUrl=null, journalUrl=http://www.kygczz.com/, iacademicId=null, status=1, seqNo=null, journalTitleEn=Mining and Metallurgical Engineering, journalPhotoCn=sIAtluqp1t366oKMF09POA==, journalPhotoEn=8lFm/e3VFuRPvwuEPHk4Qg==, journalFirstLetter=M, journalRecommend=null, journalNew=null, journalCollection=null, jcrJf=null, cjcrJf=null, jcrJfStr=null, cjcrJfStr=null, submissionFirstDecision=null, sciSubjectClassification=null, casSubjectClassification=null, citeScore=null, totalCitationFrequency=null, icpCode=null, psCode=null, advertisingLicenseCode=null, copyrightInformation=null, country=null, option=, provinceCode=null, provinceName=null, collectFlag=false), detailUrlCn=https://castjournals.cast.org.cn/joweb/kygczz/CN/10.3969/j.issn.0253-6099.2024.06.031, detailUrlEn=https://castjournals.cast.org.cn/joweb/kygczz/EN/10.3969/j.issn.0253-6099.2024.06.031, pdfUrlCn=https://castjournals.cast.org.cn/joweb/kygczz/CN/PDF/10.3969/j.issn.0253-6099.2024.06.031, pdfUrlEn=https://castjournals.cast.org.cn/joweb/kygczz/EN/PDF/10.3969/j.issn.0253-6099.2024.06.031, aliStartDate=null, aliEndDate=null, collectionFlag=false, citedCount=null, citedUrl=null, reference=null)
收藏切换
基于随机森林与支持向量机的热轧带钢凸度加权预测模型研究
收藏切换
PDF下载
周亚罗 1 , 李子轩 1 , 张少川 1 , 刘文广 2 , 张瑞成 1
矿冶工程杂志 | 材料 2024,44(6): 144-150
收起
收藏切换
矿冶工程杂志 | 材料 2024, 44(6): 144-150
基于随机森林与支持向量机的热轧带钢凸度加权预测模型研究
全屏
周亚罗1 , 李子轩1, 张少川1, 刘文广2, 张瑞成1
作者信息
  • 1.华北理工大学 电气工程学院,河北 唐山 063210
  • 2.首钢京唐钢铁联合有限责任公司,河北 唐山 063200
  • 周亚罗(1982—),女,河北安平人,硕士,副教授,主要研究方向为复杂系统的建模与控制。E-mail:

Weighted Prediction Model of Hot Rolled Strip Crown Based on Random Forest and Support Vector Machine
Yaluo ZHOU1 , Zixuan LI1, Shaochuan ZHANG1, Wenguang LIU2, Ruicheng ZHANG1
Affiliations
  • 1.College of Electrical Engineering, North China University of Science and Technology, Tangshan 063210, Hebei, China
  • 2.Shougang Jingtang United Iron and Steel Co., Ltd., Tangshan 063200, Hebei, China
出版时间: 2024-12-01 doi: 10.3969/j.issn.0253-6099.2024.06.031
文章导航
收藏切换

针对传统带钢凸度预测方法预测精度低、速度慢的问题,建立了基于随机森林和支持向量机的热轧带钢凸度加权预测模型。采用改进长鼻浣熊算法分别对随机森林、支持向量机和随机森林与支持向量机加权预测模型的参数进行优化,提高凸度预测精度。以某公司热轧1 580 mm生产线实测数据进行凸度预测仿真研究,随机森林与支持向量机加权预测模型的均方根误差为2.23 μm,与随机森林模型、支持向量机模型预测精度进行比较,加权预测模型的精度分别提高了7.08%、2.62%。

凸度预测  /  热轧带钢  /  支持向量机  /  长鼻浣熊算法  /  凸度  /  随机森林

In view of low prediction accuracy and slow speed of traditional prediction methods for strip crown, a weighted prediction model based on random forest (RF) and support vector machine (SVM) was established. The parameters of models based on RF, SVM, and a combination of RF and SVM were optimized respectively by adopting the improved coati optimization algorithm (ICOA), so as to improve crown prediction accuracy. A 1 580 mm production line of a hot-rolling mill in one company was taken in a simulation research on crown prediction based on its actual measurement. The root mean square error of the weighted prediction model based on RF and SVM is 2.23 μm. It is found that this weighted prediction model has its prediction accuracy increased by 7.08% and 2.62% respectively, compared with the models based on RF and SVM respectively.

crown prediction  /  hot rolling strip  /  support vector machine (SVM)  /  coati optimization algorithm (COA)  /  crown  /  random forest (RF)
周亚罗, 李子轩, 张少川, 刘文广, 张瑞成. 基于随机森林与支持向量机的热轧带钢凸度加权预测模型研究. 矿冶工程杂志, 2024 , 44 (6) : 144 -150 . DOI: 10.3969/j.issn.0253-6099.2024.06.031
Yaluo ZHOU, Zixuan LI, Shaochuan ZHANG, Wenguang LIU, Ruicheng ZHANG. Weighted Prediction Model of Hot Rolled Strip Crown Based on Random Forest and Support Vector Machine[J]. Mining and Metallurgical Engineering, 2024 , 44 (6) : 144 -150 . DOI: 10.3969/j.issn.0253-6099.2024.06.031
钢铁行业是国民经济的基础性支柱产业[1],热轧带钢生产在现代钢铁工业体系中占据重要地位。在轧制过程中,热轧带钢产品会出现凸度命中率低以及边降、卷曲、楔形、局部高点等板形不良问题,严重影响热轧带钢的成材率。有效控制热轧带钢产品凸度[2]可减少楔形等缺陷的出现,从而改善产品质量。
传统的凸度预测模型通常采用由物理原理和经验公式构建的机理模型[3-4],具有一定准确性和可解释性。但是,由于实际生产的复杂性和不确定性,机理模型的建立需要进行多种简化和假设,导致机理模型预测结果和生产实际存在偏差。机器学习[5-9]可以高效地处理复杂的数据和非线性关系,提高预测模型的准确性和实时性。轧钢过程是非线性、强耦合的复杂系统,本文利用随机森林(random forests,RF)与支持向量机(support vector machine,SVM)加权预测模型对末机架出口凸度进行预测,并采用改进长鼻浣熊算法(improvement coati optimization algorithm,ICOA)分别对RF的决策树数量和最大分裂节点个数、SVM的惩罚因子和核函数宽度以及加权预测模型的加权系数进行优化,进一步提高热轧带钢凸度预测模型的精度。
凸度是指带钢中部标志点厚度hc与两侧标志点的平均厚度之差[10],根据两侧标志点与边部的距离,凸度可用C20C40C100表示,实际应用中常用C40作为控制指标,凸度示意图见图1
凸度C40计算公式如下:
式中:hc为带钢中部标志点的厚度;hi″hi′分别为带钢两侧标志点的厚度;i为标志点距带钢边部的距离,i=40 mm。
轧件形状、轧辊形状以及轧制条件等因素影响有载辊缝的形状,有载辊缝[11]又决定带钢凸度。因此,在分析带钢的断面形状凸度时,需要综合考虑轧件形状、轧辊形状、轧制条件等各方面的影响因素。轧件形状主要包括带钢厚度、中间坯凸度等,在轧制力作用下通过轧辊弹跳影响末机架出口凸度。轧辊形状包括工作辊有效凸度等,工作辊有效凸度影响工作辊之间辊缝的几何形状,从而直接影响带钢形变,通过控制工作辊有效凸度,可以减少不良板形、表面缺陷和尺寸偏差的问题。轧制条件主要包括轧制力、窜辊量、弯辊力、温度、速度等,当温度较高时,带钢易发生形变,有助于减少轧制力以及变形抗力从而减小带钢凸度;低温轧制时会增加带钢变形抗力,但会提高带钢的力学性能。
SVM[12]是基于结构风险最小化、解决回归问题的常见机器学习算法,其原理是将样本从初始空间映射到高维度的空间,通过超平面将样本分隔开。超平面计算公式如下:
式中:fx)为预测值;ωT为超平面法向量;φx)为非线性映射;b为超平面平移量。
引入惩罚因子和松弛变量后软间隔SVM目标函数如公式(3)所示:
式中:C为惩罚因子;ξi均为松弛变量。
求解有约束的极小值问题引入拉格朗日乘子法求解后,最终求解公式如下:
式中:ai为拉格朗日乘子;Kxixj)为核函数。核函数将特征从低维转换到高维,同时将高维空间的内积运算转换为低维空间的核函数计算,即在低维下求解高维问题,加快了计算速度。为了获得更好的非线性映射,SVM核函数选用RBF核函数:
式中:xixj为第i个和第j个样本数据;σ为径向基函数的宽度。
RF算法由Breiman[13]在2001年提出,是集成学习中常见的预测模型。其核心思想为随机抽取样本建立不同特征组合的决策树,通过平均法从建立的决策树中输出最终预测结果。模型如图2所示。
RF预测过程如下:
步骤1:从预测模型训练集D个样本中随机、有放回地抽取M个样本组成子训练集,将子训练集用于每个决策树训练中。
步骤2:在生成决策树过程中,利用随机选取的部分特征进行训练,并针对选取的不同特征的节点分裂n次,增强随机森林预测模型的泛化性。
步骤3:重复步骤1和步骤2,构建s个决策树。
步骤4:输出各个决策树预测结果的平均值。
根据自然界长鼻浣熊哺食和逃离捕食者的行为,Mohammad Dehghani[14]等人在2023年提出了长鼻浣熊算法(coati optimization algorithm,COA)。通过模拟长鼻浣熊的集体行为,使COA具有收敛速度快、稳定性好、全局寻优能力强的优点。
长鼻浣熊在猎食过程中分为攻击和捕猎鬣蜥行为,由一半浣熊上树靠近并驱赶鬣蜥,等鬣蜥落地之后,再由剩下的长鼻浣熊猎杀。由公式(6)模拟所有长鼻浣熊的位置:
式中:xij为长鼻浣熊的位置;bjubjl为寻优参数的上限和下限;r为[0,1]内的随机数;i为长鼻浣熊的种群数量;j为求解问题变量的维度。
由公式(7)模拟长鼻浣熊在树上的位置:
式中:为长鼻浣熊在树上的位置;xbest为猎物鬣蜥的位置;I为[1,2]内的随机整数。
当鬣蜥被驱赶下树时,落于搜索空间的随机位置,地面剩余的长鼻浣熊根据鬣蜥的位置进行移动。鬣蜥落地后的位置如公式(8)所示。
式中:ajiguana为鬣蜥落地后的随机位置;为等待鬣蜥落地的浣熊的位置;Figuana为鬣蜥位置对应的目标函数的值;Fi为浣熊位置对对应目标函数的值。
在逃离捕食者过程中,每只浣熊根据当前位置随机生成新的位置:
式中:为逃离捕食者过程的寻优参数的下限和上限;t为迭代次数;为等待浣熊逃离捕食者的位置。
针对长鼻浣熊算法在预测模型中容易陷入局部最优的问题,提出了黄金正弦、莱维飞行策略对长鼻浣熊算法进行改进,提高算法的寻优能力。
1)黄金正弦算法[15]根据正弦和单位圆的联系,引用黄金分割系数更新位置公式,提高搜索速度,使局部寻优和全局寻优达到平衡。引用黄金正弦算法的思想,将黄金分割系数与正、余弦引入长鼻浣熊算法内。
2)为了避免长鼻浣熊算法在处理高维度数据易陷入局部最优的问题,引入莱维飞行[16]机制,增强长鼻浣熊算法的全局寻优能力,并跳出局部最优值。
改进的长鼻浣熊算法更新公式为:
式中:为改进后的长鼻浣熊位置;x1x2均为黄金分割系数,取值分别为-0.74、0.74;r1为[0,2π]内的随机数;Slevy为莱维飞行公式更新的位置;r2为[0,1]内的随机数。
在数据采集过程中,数据集包含噪声,可能出现较大测量误差,并且数据集的量纲不一样,为了预测模型的准确性,首先采用拉依达准则去除包含较大误差的样本[17],然后采用归一化[18]缩小数据之间相对大小并使数据具有参照性。拉依达准则如下:
归一化公式如下:
式中:xi为样本;xi′为归一化后的样本;ximinximax分别为样本数据中最小值与最大值;为样本平均值;m为样本数量。
支持向量机在进行多特征、小样本数据预测时,可能出现过拟合现象,超参数惩罚因子C和核函数宽度σ影响预测精度。针对以上问题,本文提出了改进长鼻浣熊算法优化支持向量机的惩罚因子C和核函数宽度σ的预测模型。ICOA优化SVM参数流程如图3所示。
决策树的数量s和最大节点分裂次数n是随机森林凸度预测模型训练过程的关键因素。s影响模型的预测精度和计算复杂度,s过大时,有助于提高模型预测精度,但计算时间会变长;n能控制树的深度,有效避免过拟合的现象。本文利用ICOA对随机森林凸度预测模型的超参数sn寻优,将最优超参数组合代入随机森林预测模型中,提高模型的预测性能和鲁棒性。ICOA优化RF参数流程如图4所示。
为了提高末机架出口凸度预测的准确度,本文提出了支持向量机和随机森林加权的末机架出口凸度预测模型。支持向量机、随机森林分别对非线性数据、多特征数据处理能力强,两者结合可以有效减轻支持向量机在多特征数据上可能出现的过拟合问题,从而提高预测模型的泛化能力。此外,支持向量机、随机森林模型采用不同的机理与策略,两者相结合可提高末机架出口凸度预测模型的鲁棒性。随机森林与支持向量机加权预测模型末机架出口凸度计算式如下:
式中:Y为加权求和预测模型最终输出;为ICOA优化SVM的输出;为ICOA优化RF的输出;C1C2分别为SVM、RF模型的权重。
为了验证改进算法有效性和加权凸度预测模型精准性,本文在测试平台操作系统为Windows 10家庭版的环境下进行10次算法有效性实验和5次加权预测模型对比实验。
为了验证ICOA的性能,在CEC2005中选择4个基准测试函数进行测试,f1f2f3为单峰函数,验证测试算法的寻优速度;f4为多峰函数,且全局最优解位于搜索空间的边界上,验证算法的全局寻优能力,测试函数如表1所示。
本文选用粒子群优化算法(PSO)、COA以及ICOA对表1中的测试函数进行对比实验,为保证算法对比的有效性,设置种群为60,最大迭代次数为500,测试10次,迭代过程如图5所示,迭代结果如表2所示。
图5可知,4个测试函数中,粒子群算法的收敛速度慢、跳出局部最优的能力差。改进的长鼻浣熊算法收敛速度更快,收敛精度更高。
表2可知,ICOA在f1f3函数中均能找到理论最小值,在函数f2f4中并没有寻到理论最小值,但平均值低于COA算法和PSO算法的平均值。综上所述,相比PSO算法、COA算法,ICOA算法在基准函数中全局寻优能力更强,搜索速度更快。
以国内某钢铁企业热轧1 580 mm生产线精轧机组为背景,精轧机组由7台CVC轧机组成,每台轧机主要由工作辊、窜辊等组成,选取目标凸度为40 μm的钢种数据1 053组,根据拉依达准则将有异常点的25组数据删除,最终选取了1 028组数据,其中728组数据作为训练集,300组数据作为测试集。工作辊有效凸度、各机架出口厚度、窜辊量和弯辊力等41种特征作为RF、SVM、RF与SVM加权预测模型的输入,适应度函数为均方误差。各输入、输出参数如表3所示。
为了验证改进长鼻浣熊算法在RF、SVM、RF与SVM加权预测模型中的收敛速度和精度,采用粒子群算法、麻雀算法(SSA)、改进长鼻浣熊算法分别对RF中的决策树数量、最大节点分裂次数,SVM中的惩罚因子和核函数宽度,RF与SVM加权预测模型的加权系数进行寻优对比。算法参数设置如表4所示。在RF、SVM、RF与SVM加权预测模型的优化过程中,不同预测模型的训练集适应度函数迭代曲线如图68所示。
图6可知,在优化RF过程中,ICOA在第10次迭代开始收敛,最终收敛值为3.08×10-6。PSO和SSA收敛精度和速度均不及ICOA算法。
图7可知,在优化SVM过程中,ICOA在第5次迭代开始收敛,最终收敛值为7.67×10-7,收敛精度和速度都优于PSO和SSA算法。
图8可知,在RF与SVM加权预测模型中,ICOA算法收敛速度最快,精度最高,在第36次迭代开始收敛,最终收敛值为7.02×10-7。RF、SVM、RF与SVM加权预测模型中,RF与SVM加权预测模型的适应度值最低,说明RF与SVM加权预测模型更有利于热轧带钢凸度的预测。
改进的长鼻浣熊算法优化后RF预测模型的决策树数量s=127,最大节点分裂次数n=319,对SVM预测模型寻优后的惩罚因子C=40.386 4,核函数宽度σ=1.320 3,支持向量机和随机森林加权预测模型寻得加权参数C1=0.888 6,C2=0.113 1。
为了对比ICOA-RF与SVM加权预测模型的预测效果,将ICOA-RF、ICOA-SVM预测模型用于凸度预测中,对以上模型进行5次实验,并以均方误差(MSE)、平均绝对百分比误差(MAPE)2种性能指标进行评价。
式中:为真实值;yi为预测值;m为样本个数。均方误差表示预测值和真实值之间差异平方的均值,平均绝对百分比误差代表预测值相对于真实值的平均相对误差。最终取各指标平均值作为评价指标。预测结果对比和预测误差对比分别如图9图10所示。
图9可知,RF与SVM加权预测模型的精度最高,预测结果和真实值更接近。由图10可以得出,ICOA优化的RF与SVM加权预测模型的预测误差全部在6 μm以内,而ICOA-SVM预测模型和ICOA-RF预测模型分别有1个和2个样本预测结果在6 μm以外,表明ICOA优化的RF与SVM加权预测模型预测误差小,且精度更高。
各预测模型误差指标计算结果见表5。从表5可以得出,基于改进长鼻浣熊算法优化的RF和SVM加权预测模型均方根误差和平均绝对百分比误差分别为2.23 μm和4.43%,RF预测模型的均方根误差为2.40 μm,SVM预测模型的均方根误差为2.29 μm。与随机森林模型、支持向量机模型预测精度进行比较,加权预测模型的精度分别提高了7.08%、2.62%。
为了验证RF与SVM加权预测模型的稳定性,选取预测值和真实值绝对误差在±5 μm范围内的样本与全体样本的比率进行比较,结果如表6所示。
RF与SVM加权预测模型预测误差在±5 μm以内的凸度命中率为97.3%,分别大于RF、SVM的96.3%和96.7%,表明RF与SVM加权预测模型对于大部分样本,预测误差都能保持在较小的误差内,并且在凸度预测过程中稳定性和可靠性较高,有助于提升板形质量。
1)利用黄金正弦和莱维飞行策略对长鼻浣熊算法进行改进,平衡了算法的全局寻优和局部搜索能力,增强了算法跳出局部最优的能力。
2)采用改进长鼻浣熊算法对随机森林、支持向量机模型的超参数和加权系数进行优化,可加快寻优速度、提高收敛精度。
3)随机森林与支持向量机加权预测模型有助于减少边降、卷曲、楔形、局部高点等板形不良问题,对热轧带钢生产具有现实意义。
  • 河北省自然科学基金资助项目(F2018209201)
  • 唐山市科技局科技计划资助项目(22130213G)
参考文献 引证文献
排序方式:
[1]
王贵成, 贺振, 高俊丽. 基于灰色系统理论的我国钢铁产业与GDP关系研究[J]. 矿冶工程, 2019, 39(2): 128-132.
[2]
田宝亮, 牛培峰. 基于GA-BP神经网络的弯辊力预设定模型研究与应用[J]. 矿冶工程, 2018, 38(1): 111-114.
[3]
周莲莲, 白振华, 李亮亮, 等. UCM冷连轧机组基于机理模型的板形与板凸度在线综合控制技术[J]. 轧钢, 2009, 26(6): 29-32.
[4]
陈胜利, 何安瑞, 徐致让, 等. 一个轧制单元内实时辊系综合凸度预测及应用[J]. 机械工程学报, 2017, 53(2): 61-66.
[5]
汪龙军, 丁成砚, 范宇超, 等. 基于深度森林的热轧带钢凸度预测模型[J]. 轧钢, 2023, 40(1): 90-96.
[6]
曹建国, 江军, 赵秋芳, 等. 基于数据挖掘的宽厚板板凸度控制[J]. 中南大学学报, 2019, 50(11): 2743-2752.
[7]
王优龙, 李维刚, 王永强. 基于集成特征选择和SVR的热连轧板凸度预测[J]. 钢铁, 2024, 59(1): 99-107.
[8]
刘元铭, 王振华, 王涛, 等. 热轧带钢出口凸度数据驱动建模及智能化预测分析[J]. 中国机械工程, 2020, 31(22): 2728-2733.
[9]
郝学斌. 深度信念网络算法下的热连轧板凸度预测模型[J]. 材料与冶金学报, 2022, 21(5): 364-370.
[10]
姬亚锋, 宋乐宝, 孙杰, 等. 基于SVM和PCA-CS算法的热轧带钢板凸度预测[J]. 中南大学学报, 2021, 28(8): 2333-2344.
[11]
马志强, 魏立新, 孙浩, 等. 考虑辊缝摩擦及张力影响的冷轧机非线性振动特性研究[J]. 矿冶工程, 2019, 39(2): 102-107.
[12]
王鑫瑀, 曹鹏飞, 肖一清, 等. 基于WOA-SVM模型的爆破振动预测研究[J]. 矿冶工程, 2023, 43(4): 48-51.
[13]
BREIMAN L. Random forests[J]. Machine Learning, 2001, 45(1): 5-32.
[14]
DEHGHANI M, MONTAZERZ Z, TROJOVSKA E, et al. Coati optimization algorithm: a new bio-inspired metaheuristic algorithm for solving optimization problems[J]. Knowledge-Based Systems, 2023, 259: 110011.
[15]
TANYILDIZI E, DEMIR G. Golden sine algorithm: a novel math-inspired algorithm[J]. Advances in Electrical and Computer Engineering, 2017, 17(2): 71-79.
[16]
周亚罗, 张少川, 刘文广, 等. 基于IHPO-KELM的冷轧带钢板形模式识别[J]. 矿冶工程, 2023, 43(6): 162-168.
[17]
张秀玲, 代景欢, 康学楠, 等. 基于多RBF神经网络的板形数据建模[J]. 矿冶工程, 2019, 39(6): 124-128.
[18]
阳俊, 曾维伟. 基于GA-BP神经网络的采空区地表沉降预测模型[J]. 矿冶工程, 2022, 42(2): 42-45.
2024年第44卷第6期
PDF下载
40
15
引用本文
BibTeX
文章信息
doi: 10.3969/j.issn.0253-6099.2024.06.031
  • 接收时间:2024-05-25
  • 首发时间:2026-03-19
  • 出版时间:2024-12-01
补充材料
相关文章
文章信息
作者
出版历史
  • 收稿日期:2024-05-25
基金
河北省自然科学基金资助项目(F2018209201)
唐山市科技局科技计划资助项目(22130213G)
作者信息
    1.华北理工大学 电气工程学院,河北 唐山 063210
    2.首钢京唐钢铁联合有限责任公司,河北 唐山 063200
参考文献
分享链接
https://castjournals.cast.org.cn/joweb/kygczz/CN/10.3969/j.issn.0253-6099.2024.06.031
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