Article(id=1157001741704192205, tenantId=1146029695717560320, journalId=1146120084050784272, issueId=1157001740768858346, articleNumber=null, orderNo=null, doi=10.19562/j.chinasae.qcgc.2024.07.014, pmid=null, cstr=null, oa=null, hot=null, price=null, onlineType=0, articleFormat=0, articleType=null, articleTypeStr=null, receivedDate=1695484800000, receivedDateStr=2023-09-24, revisedDate=1703779200000, revisedDateStr=2023-12-29, acceptedDate=null, acceptedDateStr=null, onlineDate=1753780311275, onlineDateStr=2025-07-29, pubDate=1721836800000, pubDateStr=2024-07-25, doiRegisterDate=null, doiRegisterDateStr=null, onlineIssueDate=1753780311275, onlineIssueDateStr=2025-07-29, onlineJustAcceptDate=null, onlineJustAcceptDateStr=null, onlineFirstDate=null, onlineFirstDateStr=null, sourceXml=null, magXml=null, createTime=1753780311275, creator=13701087609, updateTime=1753780311275, updator=13701087609, issue=Issue{id=1157001740768858346, tenantId=1146029695717560320, journalId=1146120084050784272, year='2024', volume='46', issue='7', pageStart='1137', pageEnd='1334', issueExtLink='null', onlineDate='null', pubDate='null', beforeIssueId=null, nextIssueId=null, price=null, status=0, issueComplete=1, articleOrder=1, issueType=-1, specialIssue=null, createTime=1753780311052, creator=13701087609, updateTime=1756792480363, updator=13701087609, preIssue=null, nextIssue=null, ext={EN=IssueExt(id=1169635694612853253, tenantId=1146029695717560320, journalId=1146120084050784272, issueId=1157001740768858346, language=EN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=), CN=IssueExt(id=1169635694612853254, tenantId=1146029695717560320, journalId=1146120084050784272, issueId=1157001740768858346, language=CN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=)}, issueFiles=null}, startPage=1273, endPage=1281, ext={EN=ArticleExt(id=1157001742245257425, articleId=1157001741704192205, tenantId=1146029695717560320, journalId=1146120084050784272, language=EN, title=Intelligent Design and Analysis of Body Structure Based on Data Drive, columnId=null, journalTitle=Automotive Engineering, columnName=null, runingTitle=null, highlight=null, articleAbstract=

As an important stage of the automotive design process, conceptual design requires rapid conceptual design and evaluation. The current methods generally use a combination of parametric design and CAE to achieve analysis based conceptual design of car body structures. With the development and maturity of machine learning and deep learning algorithms, intelligent design methods will become the main innovative technology for body structure design. In this article, a combination of data-driven and optimization design method is used to independently develop the vehicle structure intelligent design software tool (S-iVCD). Firstly, based on residual networks and thermal map regression algorithms, feature points of the vehicle body structure are extracted to achieve automated modeling of the conceptual model of the vehicle body structure. Secondly, based on Gaussian process sampling, a body structure dataset is collected and a fully connected neural network model is used to construct the body structure network model. The parameters of various components of the vehicle body can be input into the trained network model to obtain the overall performance results of the vehicle body. Finally, by combining data-driven computing with the moving asymptote algorithm, a multi-objective optimization design of the vehicle body structure that considers mass, bending stiffness, and torsional stiffness is quickly achieved. By comparing with finite element examples, the error of the calculation results is within the allowable range, with the optimization calculation time greatly shortened, and the lightweight rate reaching 7.4%. This indicates that the data-driven body structure optimization design method is effective in improving efficiency in the conceptual design stage of automobiles.

, 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=Rong Cao, Junwei Hua, Yongcheng Li, Fangli Guo, Wenbin Hou), CN=ArticleExt(id=1157001935304876214, articleId=1157001741704192205, tenantId=1146029695717560320, journalId=1146120084050784272, language=CN, title=基于数据驱动的车身结构智能设计与分析, columnId=null, journalTitle=汽车工程, columnName=null, runingTitle=null, highlight=null, articleAbstract=

概念设计作为汽车设计流程的重要阶段,需要快速地进行方案设计和方案评估。目前一般采用参数化设计和CAE相结合的方法,实现基于分析的车身结构概念设计。随着机器学习和深度学习算法的发展和成熟,智能设计方法将成为车身结构设计主要创新技术。本文使用数据驱动和优化设计相结合的方法,自主研发了车身结构智能设计软件工具(S-iVCD)。首先,基于残差网络和热力图回归算法提取车身结构特征点,实现车身结构概念模型的自动化建模。其次,基于高斯过程采样收集车身结构数据集,采用全连接神经网络模型构建了车身结构网络模型,通过将车身各部件参数输入训练好的网络模型,实时得到车身整体性能的结果。最后,将数据驱动计算与移动渐近线算法结合,快速实现考虑质量、弯曲刚度和扭转刚度的车身结构多目标优化设计。通过与有限元实例对比,计算结果的误差在允许范围内,优化计算时间大为缩短,轻量化率达到了7.4%。由此表明基于数据驱动的车身结构优化设计方法对于汽车概念设计阶段提高效率是有效的。

, correspAuthors=null, authorNote=null, correspAuthorsNote=
侯文彬,教授,博士,E-mail:
, copyrightStatement=null, copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=KGD6MAKmJ5ZHMV7s6KVBjA==, magXml=hg7lIAzd4EgNchuAoYjcJA==, pdfUrl=null, pdf=xkO8xLNf/8ThevaZlbbqzw==, pdfFileSize=null, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=null, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=KA862wHYm9NKyfWYh1YC/A==, mapNumber=null, authorCompany=null, fund=null, authors=null, authorsList=曹榕, 华钧伟, 李永成, 郭方俐, 侯文彬)}, authors=[Author(id=1157001942586188021, tenantId=1146029695717560320, journalId=1146120084050784272, articleId=1157001741704192205, 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=1157001942678462712, tenantId=1146029695717560320, journalId=1146120084050784272, articleId=1157001741704192205, authorId=1157001942586188021, language=EN, stringName=Rong Cao, firstName=Rong, middleName=null, lastName=Cao, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1. School of Automotive Engineering,Dalian University of Technology,Dalian  116024, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1157001942728794362, tenantId=1146029695717560320, journalId=1146120084050784272, articleId=1157001741704192205, authorId=1157001942586188021, language=CN, stringName=曹榕, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1. 大连理工大学汽车工程学院,大连 116024, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1157001942410027242, tenantId=1146029695717560320, journalId=1146120084050784272, articleId=1157001741704192205, xref=1., ext=[AuthorCompanyExt(id=1157001942422610155, tenantId=1146029695717560320, journalId=1146120084050784272, articleId=1157001741704192205, companyId=1157001942410027242, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1. School of Automotive Engineering,Dalian University of Technology,Dalian  116024), AuthorCompanyExt(id=1157001942430998764, tenantId=1146029695717560320, journalId=1146120084050784272, articleId=1157001741704192205, companyId=1157001942410027242, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1. 大连理工大学汽车工程学院,大连 116024)])]), Author(id=1157001942804291837, tenantId=1146029695717560320, journalId=1146120084050784272, articleId=1157001741704192205, 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=1157001942863012097, tenantId=1146029695717560320, journalId=1146120084050784272, articleId=1157001741704192205, authorId=1157001942804291837, language=EN, stringName=Junwei Hua, firstName=Junwei, middleName=null, lastName=Hua, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1. School of Automotive Engineering,Dalian University of Technology,Dalian  116024, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1157001942917538051, tenantId=1146029695717560320, journalId=1146120084050784272, articleId=1157001741704192205, authorId=1157001942804291837, language=CN, stringName=华钧伟, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1. 大连理工大学汽车工程学院,大连 116024, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1157001942410027242, tenantId=1146029695717560320, journalId=1146120084050784272, articleId=1157001741704192205, xref=1., ext=[AuthorCompanyExt(id=1157001942422610155, tenantId=1146029695717560320, journalId=1146120084050784272, articleId=1157001741704192205, companyId=1157001942410027242, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1. School of Automotive Engineering,Dalian University of Technology,Dalian  116024), AuthorCompanyExt(id=1157001942430998764, tenantId=1146029695717560320, journalId=1146120084050784272, articleId=1157001741704192205, companyId=1157001942410027242, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1. 大连理工大学汽车工程学院,大连 116024)])]), Author(id=1157001942980452615, tenantId=1146029695717560320, journalId=1146120084050784272, articleId=1157001741704192205, 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=1157001943051755786, tenantId=1146029695717560320, journalId=1146120084050784272, articleId=1157001741704192205, authorId=1157001942980452615, language=EN, stringName=Yongcheng Li, firstName=Yongcheng, middleName=null, lastName=Li, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1. School of Automotive Engineering,Dalian University of Technology,Dalian  116024, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1157001943102087437, tenantId=1146029695717560320, journalId=1146120084050784272, articleId=1157001741704192205, authorId=1157001942980452615, language=CN, stringName=李永成, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1. 大连理工大学汽车工程学院,大连 116024, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1157001942410027242, tenantId=1146029695717560320, journalId=1146120084050784272, articleId=1157001741704192205, xref=1., ext=[AuthorCompanyExt(id=1157001942422610155, tenantId=1146029695717560320, journalId=1146120084050784272, articleId=1157001741704192205, companyId=1157001942410027242, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1. School of Automotive Engineering,Dalian University of Technology,Dalian  116024), AuthorCompanyExt(id=1157001942430998764, tenantId=1146029695717560320, journalId=1146120084050784272, articleId=1157001741704192205, companyId=1157001942410027242, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1. 大连理工大学汽车工程学院,大连 116024)])]), Author(id=1157001943165002000, tenantId=1146029695717560320, journalId=1146120084050784272, articleId=1157001741704192205, 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=1157001943227916565, tenantId=1146029695717560320, journalId=1146120084050784272, articleId=1157001741704192205, authorId=1157001943165002000, language=EN, stringName=Fangli Guo, firstName=Fangli, middleName=null, lastName=Guo, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1. School of Automotive Engineering,Dalian University of Technology,Dalian  116024, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1157001943295025433, tenantId=1146029695717560320, journalId=1146120084050784272, articleId=1157001741704192205, authorId=1157001943165002000, language=CN, stringName=郭方俐, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1. 大连理工大学汽车工程学院,大连 116024, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1157001942410027242, tenantId=1146029695717560320, journalId=1146120084050784272, articleId=1157001741704192205, xref=1., ext=[AuthorCompanyExt(id=1157001942422610155, tenantId=1146029695717560320, journalId=1146120084050784272, articleId=1157001741704192205, companyId=1157001942410027242, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1. School of Automotive Engineering,Dalian University of Technology,Dalian  116024), AuthorCompanyExt(id=1157001942430998764, tenantId=1146029695717560320, journalId=1146120084050784272, articleId=1157001741704192205, companyId=1157001942410027242, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1. 大连理工大学汽车工程学院,大连 116024)])]), Author(id=1157001943349551388, tenantId=1146029695717560320, journalId=1146120084050784272, articleId=1157001741704192205, orderNo=4, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=houwb@dlut.edu.cn, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1157001945010495781, tenantId=1146029695717560320, journalId=1146120084050784272, articleId=1157001741704192205, authorId=1157001943349551388, language=EN, stringName=Wenbin Hou, firstName=Wenbin, middleName=null, lastName=Hou, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 2, address=1. School of Automotive Engineering,Dalian University of Technology,Dalian  116024
2. Ningbo Research Institute,Dalian University of Technology,Ningbo  315016, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1157001945081798952, tenantId=1146029695717560320, journalId=1146120084050784272, articleId=1157001741704192205, authorId=1157001943349551388, language=CN, stringName=侯文彬, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 2, address=1. 大连理工大学汽车工程学院,大连 116024
2. 大连理工大学宁波研究院,宁波 315016, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1157001942410027242, tenantId=1146029695717560320, journalId=1146120084050784272, articleId=1157001741704192205, xref=1., ext=[AuthorCompanyExt(id=1157001942422610155, tenantId=1146029695717560320, journalId=1146120084050784272, articleId=1157001741704192205, companyId=1157001942410027242, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1. School of Automotive Engineering,Dalian University of Technology,Dalian  116024), AuthorCompanyExt(id=1157001942430998764, tenantId=1146029695717560320, journalId=1146120084050784272, articleId=1157001741704192205, companyId=1157001942410027242, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1. 大连理工大学汽车工程学院,大连 116024)]), AuthorCompany(id=1157001942506496239, tenantId=1146029695717560320, journalId=1146120084050784272, articleId=1157001741704192205, xref=2., ext=[AuthorCompanyExt(id=1157001942510690544, tenantId=1146029695717560320, journalId=1146120084050784272, articleId=1157001741704192205, companyId=1157001942506496239, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2. Ningbo Research Institute,Dalian University of Technology,Ningbo  315016), AuthorCompanyExt(id=1157001942519079153, tenantId=1146029695717560320, journalId=1146120084050784272, articleId=1157001741704192205, companyId=1157001942506496239, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2. 大连理工大学宁波研究院,宁波 315016)])])], keywords=[Keyword(id=1157001946361061688, tenantId=1146029695717560320, journalId=1146120084050784272, articleId=1157001741704192205, language=EN, orderNo=1, keyword=body structure design), Keyword(id=1157001946432364857, tenantId=1146029695717560320, journalId=1146120084050784272, articleId=1157001741704192205, language=EN, orderNo=2, keyword=lightweighting), Keyword(id=1157001946474307898, tenantId=1146029695717560320, journalId=1146120084050784272, articleId=1157001741704192205, language=EN, orderNo=3, keyword=data-driven analysis), Keyword(id=1157001946528833851, tenantId=1146029695717560320, journalId=1146120084050784272, articleId=1157001741704192205, language=EN, orderNo=4, keyword=fully connected neural networks), Keyword(id=1157001946579165500, tenantId=1146029695717560320, journalId=1146120084050784272, articleId=1157001741704192205, language=CN, orderNo=1, keyword=车身结构设计), Keyword(id=1157001946621108541, tenantId=1146029695717560320, journalId=1146120084050784272, articleId=1157001741704192205, language=CN, orderNo=2, keyword=轻量化), Keyword(id=1157001946663051582, tenantId=1146029695717560320, journalId=1146120084050784272, articleId=1157001741704192205, language=CN, orderNo=3, keyword=数据驱动分析), Keyword(id=1157001946721771839, tenantId=1146029695717560320, journalId=1146120084050784272, articleId=1157001741704192205, language=CN, orderNo=4, keyword=全连接神经网络)], refs=[Reference(id=1157001955152323001, tenantId=1146029695717560320, journalId=1146120084050784272, articleId=1157001741704192205, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=1, rfOrder=0, authorNames=null, journalName=null, refType=null, unstructuredReference=韩景飞. 面向概念设计的车身结构智能建模方法的研究[D].大连:大连理工大学,2021., articleTitle=null, refAbstract=null), Reference(id=1157001955219431867, tenantId=1146029695717560320, journalId=1146120084050784272, articleId=1157001741704192205, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=1, rfOrder=1, authorNames=null, journalName=null, refType=null, unstructuredReference=HAN J F. Research on intelligent modeling methods of body structure for conceptual design[D]. Dalian: Dalian University of Technology, 2021., articleTitle=null, refAbstract=null), Reference(id=1157001955273957821, tenantId=1146029695717560320, journalId=1146120084050784272, articleId=1157001741704192205, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=2, rfOrder=2, authorNames=null, journalName=null, refType=null, unstructuredReference=余咏红. 概念设计与结构措施在建筑结构设计中的应用[J]. 房地产世界,2021(15):41-43., articleTitle=null, refAbstract=null), Reference(id=1157001955320095167, tenantId=1146029695717560320, journalId=1146120084050784272, articleId=1157001741704192205, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=2, rfOrder=3, authorNames=null, journalName=null, refType=null, unstructuredReference=YU Y H. Application of conceptual design and structural measures in building structural design[J]. The World of Real Estate, 2021(15):41-43., articleTitle=null, refAbstract=null), Reference(id=1157001955370426817, tenantId=1146029695717560320, journalId=1146120084050784272, articleId=1157001741704192205, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=3, rfOrder=4, authorNames=null, journalName=null, refType=null, unstructuredReference=ESFE M H, ESMAILY R, KHABAZ M K, et al. A novel integrated model to improve the dynamic viscosity of MWCNT-Al2O3 (40:60)/Oil 5W50 hybrid nano-lubricant using artificial neural networks (ANNs)[J]. Tribology International, 2023,178(14): 108-123., articleTitle=null, refAbstract=null), Reference(id=1157001955424952771, tenantId=1146029695717560320, journalId=1146120084050784272, articleId=1157001741704192205, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=4, rfOrder=5, authorNames=null, journalName=null, refType=null, unstructuredReference=BAGHOOLIZADEH M, DEHKORDI S A H H, ROSTAMZADEH-RENANI M, et al. Optimization of annual electricity consumption costs and the costs of insulation and phase change materials in the residential building using artificial neural network and genetic algorithm methods[J]. Journal of Energy Storage, 2023,62(14): 1178-1201., articleTitle=null, refAbstract=null), Reference(id=1157001955500450245, tenantId=1146029695717560320, journalId=1146120084050784272, articleId=1157001741704192205, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=5, rfOrder=6, authorNames=null, journalName=null, refType=null, unstructuredReference=方培俊,蔡英凤,陈龙,等. 基于车辆动力学混合模型的智能汽车轨迹跟踪控制方法[J]. 汽车工程,2022,44(10):1469-1483,1510., articleTitle=null, refAbstract=null), Reference(id=1157001955559170503, tenantId=1146029695717560320, journalId=1146120084050784272, articleId=1157001741704192205, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=5, rfOrder=7, authorNames=null, journalName=null, refType=null, unstructuredReference=FANG P J, CAI Y F, CHEN L, et al. Trajectory tracking control method based on vehicle dynamics hybrid model for intelligent vehicle [J].Automotive Engineering,2022,44(10):1469-1483,1510., articleTitle=null, refAbstract=null), Reference(id=1157001955626279369, tenantId=1146029695717560320, journalId=1146120084050784272, articleId=1157001741704192205, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=6, rfOrder=8, authorNames=null, journalName=null, refType=null, unstructuredReference=崔格格,吕超,李景行,等.数据驱动的智能车个性化场景风险图构建[J].汽车工程, 2023,45(2):231-242., articleTitle=null, refAbstract=null), Reference(id=1157001955693388235, tenantId=1146029695717560320, journalId=1146120084050784272, articleId=1157001741704192205, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=6, rfOrder=9, authorNames=null, journalName=null, refType=null, unstructuredReference=CUI G G, LV C, LI J X, et al. Data-driven personalized scenario risk map construction for intelligent vehicles[J].Automotive Engineering, 2023,45(2):231-242., articleTitle=null, refAbstract=null), Reference(id=1157001955756302797, tenantId=1146029695717560320, journalId=1146120084050784272, articleId=1157001741704192205, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=7, rfOrder=10, authorNames=null, journalName=null, refType=null, unstructuredReference=李达,邓钧君,张照生,等.电动车辆动力电池安全预警策略研究综述[J].汽车工程,2023,45(8):1392-1407., articleTitle=null, refAbstract=null), Reference(id=1157001955827605966, tenantId=1146029695717560320, journalId=1146120084050784272, articleId=1157001741704192205, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=7, rfOrder=11, authorNames=null, journalName=null, refType=null, unstructuredReference=LI D, DENG J J, ZHANG Z S, et al. Review on power battery safety warning strategy in electric vehicles[J].Automotive Engineering, 2023, 45(8): 1392-1407., articleTitle=null, refAbstract=null), Reference(id=1157001955894714832, tenantId=1146029695717560320, journalId=1146120084050784272, articleId=1157001741704192205, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=8, rfOrder=12, authorNames=null, journalName=null, refType=null, unstructuredReference=胡杰,余海,杨博闻,等.基于数据驱动的电动汽车电池安全风险预测[J].汽车工程,2023,45(5):814-824., articleTitle=null, refAbstract=null), Reference(id=1157001955945046485, tenantId=1146029695717560320, journalId=1146120084050784272, articleId=1157001741704192205, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=8, rfOrder=13, authorNames=null, journalName=null, refType=null, unstructuredReference=HU J, YU H, YANG B W, et al. Battery safety risk prediction for data-driven electric vehicles[J].Automotive Engineering, 2023,45(5):814-824., articleTitle=null, refAbstract=null), Reference(id=1157001956020543961, tenantId=1146029695717560320, journalId=1146120084050784272, articleId=1157001741704192205, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=9, rfOrder=14, authorNames=null, journalName=null, refType=null, unstructuredReference=YOSHIMURA M, NISHIWAKI S, IZUI K. A multiple cross-sectional shape optimization method for automotive body frames[J].Journal of Mechanical Design,2005,127 (8): 49-57., articleTitle=null, refAbstract=null), Reference(id=1157001956100235743, tenantId=1146029695717560320, journalId=1146120084050784272, articleId=1157001741704192205, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=10, rfOrder=15, authorNames=null, journalName=null, refType=null, unstructuredReference=LI H, LIU Z, ZHU P, et al. A data-driven self-adaptive parameter tuning framework for composite automobile part optimization design[J]. Proceedings of the Institution of Mechanical Engineers, Part D: Journal of Automobile Engineering,2023,237(10-11):2592-2604., articleTitle=null, refAbstract=null), Reference(id=1157001956179927522, tenantId=1146029695717560320, journalId=1146120084050784272, articleId=1157001741704192205, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=11, rfOrder=16, authorNames=null, journalName=null, refType=null, unstructuredReference=佟罡. 基于机器学习的车门协同设计冲突消解[D].大连:大连理工大学,2019., articleTitle=null, refAbstract=null), Reference(id=1157001956226064869, tenantId=1146029695717560320, journalId=1146120084050784272, articleId=1157001741704192205, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=11, rfOrder=17, authorNames=null, journalName=null, refType=null, unstructuredReference=TONG G. Machine learning-based door co-design conflict resolution[D]. Dalian :Dalian University of Technology,2019., articleTitle=null, refAbstract=null), Reference(id=1157001956268007913, tenantId=1146029695717560320, journalId=1146120084050784272, articleId=1157001741704192205, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=12, rfOrder=18, authorNames=null, journalName=null, refType=null, unstructuredReference=KONG Y S, ABDULLAH S, SCHRAMM D, et al. Optimization of spring fatigue life prediction model for vehicle ride using hybrid multi-layer perceptron artificial neural networks[J]. Mech Syst Signal Process,2019,122(24): 597-621., articleTitle=null, refAbstract=null), Reference(id=1157001956326728175, tenantId=1146029695717560320, journalId=1146120084050784272, articleId=1157001741704192205, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=13, rfOrder=19, authorNames=null, journalName=null, refType=null, unstructuredReference=TOPALOGLU A, KAYA N, ÖZTURK F. Predictions of the design decisions for vehicle alloy wheel rims using neural network[J]. Proceedings of the Institution of Mechanical Engineers, Part D: Journal of Automobile Engineering, 2022, 237 (12):2913-2927., articleTitle=null, refAbstract=null), Reference(id=1157001956385448434, tenantId=1146029695717560320, journalId=1146120084050784272, articleId=1157001741704192205, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=14, rfOrder=20, authorNames=null, journalName=null, refType=null, unstructuredReference=BAYKASOGLU A, BAYKASOGLU C, CETIN E. Multi-objective crashworthiness optimization of lattice structure filled thinwalled tubes[J]. Thin-Walled Struct,2020, 149(26): 617-630., articleTitle=null, refAbstract=null), Reference(id=1157001956435780085, tenantId=1146029695717560320, journalId=1146120084050784272, articleId=1157001741704192205, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=15, rfOrder=21, authorNames=null, journalName=null, refType=null, unstructuredReference=贾良跃,郝佳,商曦文,等. 基于长短期记忆网络的桁架车身结构轻量化设计优化[J]. 计算机集成制造系统,2022, 24 (2): 1-20., articleTitle=null, refAbstract=null), Reference(id=1157001956498694650, tenantId=1146029695717560320, journalId=1146120084050784272, articleId=1157001741704192205, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=15, rfOrder=22, authorNames=null, journalName=null, refType=null, unstructuredReference=JIA L Y,HAO J,SHANG X W, et al. Lightweight design optimization of truss body structure based on long short-term memory network[J]. Computer Integrated Manufacturing Systems,2022, 24(2): 1-20., articleTitle=null, refAbstract=null), Reference(id=1157001956553220604, tenantId=1146029695717560320, journalId=1146120084050784272, articleId=1157001741704192205, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=16, rfOrder=23, authorNames=null, journalName=null, refType=null, unstructuredReference=WANG X, SUN P, ZUO W, et al. Multi-objective optimization of automobile body frame considering weight, rigidity, and frequency for conceptual design[J]. Advances in Mechanical Engineering, 2022,14(2) :317-335., articleTitle=null, refAbstract=null), Reference(id=1157001956595163647, tenantId=1146029695717560320, journalId=1146120084050784272, articleId=1157001741704192205, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=17, rfOrder=24, authorNames=null, journalName=null, refType=null, unstructuredReference=ROSTAMZADEH-RENANI M, BAGHOOLIZADEH M, ROSTAMZADEH-RENANI R, et al. The effect of canard’s optimum geometric design on wake control behind the car using artificial neural network and genetic algorithm[J]. ISA Transactions, 2022,131: 427-443., articleTitle=null, refAbstract=null)], funds=[Fund(id=1157001955043271094, tenantId=1146029695717560320, journalId=1146120084050784272, articleId=1157001741704192205, awardId=52072057, language=CN, fundingSource=国家自然科学基金(52072057), fundOrder=null, country=null), Fund(id=1157001955093602743, tenantId=1146029695717560320, journalId=1146120084050784272, articleId=1157001741704192205, awardId=2023Z065, language=CN, fundingSource=宁波市重点研发计划项目(2023Z065), fundOrder=null, country=null)], companyList=[AuthorCompany(id=1157001942410027242, tenantId=1146029695717560320, journalId=1146120084050784272, articleId=1157001741704192205, xref=1., ext=[AuthorCompanyExt(id=1157001942422610155, tenantId=1146029695717560320, journalId=1146120084050784272, articleId=1157001741704192205, companyId=1157001942410027242, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1. School of Automotive Engineering,Dalian University of Technology,Dalian  116024), AuthorCompanyExt(id=1157001942430998764, tenantId=1146029695717560320, journalId=1146120084050784272, articleId=1157001741704192205, companyId=1157001942410027242, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1. 大连理工大学汽车工程学院,大连 116024)]), AuthorCompany(id=1157001942506496239, tenantId=1146029695717560320, journalId=1146120084050784272, articleId=1157001741704192205, xref=2., ext=[AuthorCompanyExt(id=1157001942510690544, tenantId=1146029695717560320, journalId=1146120084050784272, articleId=1157001741704192205, companyId=1157001942506496239, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2. Ningbo Research Institute,Dalian University of Technology,Ningbo  315016), AuthorCompanyExt(id=1157001942519079153, tenantId=1146029695717560320, journalId=1146120084050784272, articleId=1157001741704192205, companyId=1157001942506496239, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2. 大连理工大学宁波研究院,宁波 315016)])], figs=[ArticleFig(id=1157001951327117706, tenantId=1146029695717560320, journalId=1146120084050784272, articleId=1157001741704192205, language=EN, label=null, caption=null, figureFileSmall=ZE1AB61GeRT+Y1RUzzQwtw==, figureFileBig=jCmnUmeLLZXvKqsquLCuPg==, tableContent=null), ArticleFig(id=1157001951402615179, tenantId=1146029695717560320, journalId=1146120084050784272, articleId=1157001741704192205, language=CN, label=图1, caption=残差块结构, figureFileSmall=ZE1AB61GeRT+Y1RUzzQwtw==, figureFileBig=jCmnUmeLLZXvKqsquLCuPg==, tableContent=null), ArticleFig(id=1157001951452946828, tenantId=1146029695717560320, journalId=1146120084050784272, articleId=1157001741704192205, language=EN, label=null, caption=null, figureFileSmall=27AcFPCuPgEyWhw2Wel0Hw==, figureFileBig=bGmnxYUqDJuslcBwpHAYhQ==, tableContent=null), ArticleFig(id=1157001951507472781, tenantId=1146029695717560320, journalId=1146120084050784272, articleId=1157001741704192205, language=CN, label=图2, caption=基于热力图回归过程, figureFileSmall=27AcFPCuPgEyWhw2Wel0Hw==, figureFileBig=bGmnxYUqDJuslcBwpHAYhQ==, tableContent=null), ArticleFig(id=1157001951557804430, tenantId=1146029695717560320, journalId=1146120084050784272, articleId=1157001741704192205, language=EN, label=null, caption=null, figureFileSmall=N6nn0IH/LPO5KWpZz6NpKw==, figureFileBig=nqy6oEXXuROZYzRkTi4FWg==, tableContent=null), ArticleFig(id=1157001951603941775, tenantId=1146029695717560320, journalId=1146120084050784272, articleId=1157001741704192205, language=CN, label=图3, caption=车身结构智能建模, figureFileSmall=N6nn0IH/LPO5KWpZz6NpKw==, figureFileBig=nqy6oEXXuROZYzRkTi4FWg==, tableContent=null), ArticleFig(id=1157001951654273424, tenantId=1146029695717560320, journalId=1146120084050784272, articleId=1157001741704192205, language=EN, label=null, caption=null, figureFileSmall=VOL0tC3RGuOvxetC+3L3OA==, figureFileBig=0Cop6atshPPII3LIEb+dpg==, tableContent=null), ArticleFig(id=1157001951704605073, tenantId=1146029695717560320, journalId=1146120084050784272, articleId=1157001741704192205, language=CN, label=图4, caption=梁单元截面示意图, figureFileSmall=VOL0tC3RGuOvxetC+3L3OA==, figureFileBig=0Cop6atshPPII3LIEb+dpg==, tableContent=null), ArticleFig(id=1157001951771713938, tenantId=1146029695717560320, journalId=1146120084050784272, articleId=1157001741704192205, language=EN, label=null, caption=null, figureFileSmall=hMHbrDajwsJlOZhUs35PrQ==, figureFileBig=v1N9kRKRNGUF5aVL+DQytg==, tableContent=null), ArticleFig(id=1157001951822045587, tenantId=1146029695717560320, journalId=1146120084050784272, articleId=1157001741704192205, language=CN, label=图5, caption=概念车身结构框架弯曲工况模型, figureFileSmall=hMHbrDajwsJlOZhUs35PrQ==, figureFileBig=v1N9kRKRNGUF5aVL+DQytg==, tableContent=null), ArticleFig(id=1157001951863988628, tenantId=1146029695717560320, journalId=1146120084050784272, articleId=1157001741704192205, language=EN, label=null, caption=null, figureFileSmall=JAqHwwnEpGw9L00AjqQPxg==, figureFileBig=nNtE1mEgcTvrpCuG6jdfvA==, tableContent=null), ArticleFig(id=1157001951905931669, tenantId=1146029695717560320, journalId=1146120084050784272, articleId=1157001741704192205, language=CN, label=图6, caption=概念车身结构框架扭转工况模型, figureFileSmall=JAqHwwnEpGw9L00AjqQPxg==, figureFileBig=nNtE1mEgcTvrpCuG6jdfvA==, tableContent=null), ArticleFig(id=1157001951952069014, tenantId=1146029695717560320, journalId=1146120084050784272, articleId=1157001741704192205, language=EN, label=null, caption=null, figureFileSmall=xlwpgcR5MMO6YSoVXsNyzA==, figureFileBig=Vbgh3+FherF5sOLhgbkK4Q==, tableContent=null), ArticleFig(id=1157001951989817751, tenantId=1146029695717560320, journalId=1146120084050784272, articleId=1157001741704192205, language=CN, label=图7, caption=概念设计车身优化流程, figureFileSmall=xlwpgcR5MMO6YSoVXsNyzA==, figureFileBig=Vbgh3+FherF5sOLhgbkK4Q==, tableContent=null), ArticleFig(id=1157001952040149400, tenantId=1146029695717560320, journalId=1146120084050784272, articleId=1157001741704192205, language=EN, label=null, caption=null, figureFileSmall=wlYM4b6VRRHQI1jeDJ7JkA==, figureFileBig=39ae4GZhiaaSsLdNZVfRQw==, tableContent=null), ArticleFig(id=1157001952090481049, tenantId=1146029695717560320, journalId=1146120084050784272, articleId=1157001741704192205, language=CN, label=图8, caption=系统交互界面, figureFileSmall=wlYM4b6VRRHQI1jeDJ7JkA==, figureFileBig=39ae4GZhiaaSsLdNZVfRQw==, tableContent=null), ArticleFig(id=1157001952132424090, tenantId=1146029695717560320, journalId=1146120084050784272, articleId=1157001741704192205, language=EN, label=null, caption=null, figureFileSmall=LezZMC3fw5LnkFRRf97MOg==, figureFileBig=iU7s7beM8OzMGUioNhtgDQ==, tableContent=null), ArticleFig(id=1157001952174367131, tenantId=1146029695717560320, journalId=1146120084050784272, articleId=1157001741704192205, language=CN, label=图9, caption=数据驱动拟合预测, figureFileSmall=LezZMC3fw5LnkFRRf97MOg==, figureFileBig=iU7s7beM8OzMGUioNhtgDQ==, tableContent=null), ArticleFig(id=1157001952249864604, tenantId=1146029695717560320, journalId=1146120084050784272, articleId=1157001741704192205, language=EN, label=null, caption=null, figureFileSmall=ApFVhk9PlswVz3loyLB7Fw==, figureFileBig=K2YHL3qIcat0BoBuw7ix7w==, tableContent=null), ArticleFig(id=1157001954183438752, tenantId=1146029695717560320, journalId=1146120084050784272, articleId=1157001741704192205, language=CN, label=图10, caption=车身框架模型及其命名, figureFileSmall=ApFVhk9PlswVz3loyLB7Fw==, figureFileBig=K2YHL3qIcat0BoBuw7ix7w==, tableContent=null), ArticleFig(id=1157001954275713443, tenantId=1146029695717560320, journalId=1146120084050784272, articleId=1157001741704192205, language=EN, label=null, caption=null, figureFileSmall=CsC3Wp2kQjZyqAPkIVNhUw==, figureFileBig=KGYaoFR485NlrlzLX4c5gw==, tableContent=null), ArticleFig(id=1157001954326045092, tenantId=1146029695717560320, journalId=1146120084050784272, articleId=1157001741704192205, language=CN, label=图11, caption=质量迭代曲线, figureFileSmall=CsC3Wp2kQjZyqAPkIVNhUw==, figureFileBig=KGYaoFR485NlrlzLX4c5gw==, tableContent=null), ArticleFig(id=1157001954372182437, tenantId=1146029695717560320, journalId=1146120084050784272, articleId=1157001741704192205, language=EN, label=null, caption=null, figureFileSmall=null, figureFileBig=null, tableContent=
参数 数值
激活函数类型 ReLU激活函数
学习率 0.001
样本批次大小 500
迭代次数 100
损失函数类型 MSE
), ArticleFig(id=1157001954426708390, tenantId=1146029695717560320, journalId=1146120084050784272, articleId=1157001741704192205, language=CN, label=表1, caption=

全连接神经网络的超参数设置

, figureFileSmall=null, figureFileBig=null, tableContent=
参数 数值
激活函数类型 ReLU激活函数
学习率 0.001
样本批次大小 500
迭代次数 100
损失函数类型 MSE
), ArticleFig(id=1157001954477040039, tenantId=1146029695717560320, journalId=1146120084050784272, articleId=1157001741704192205, language=EN, label=null, caption=null, figureFileSmall=null, figureFileBig=null, tableContent=
项目 EI/(N·mm-1 GI/(N·m·(°)-1 t/s
求解器计算 31 755.86 21 630.26 30.20
数据驱动 31 632.32 21 769.83 0.93
误差/对比 0.389 0% 0.646 5% 32.40
), ArticleFig(id=1157001954539954600, tenantId=1146029695717560320, journalId=1146120084050784272, articleId=1157001741704192205, language=CN, label=表2, caption=

求解器计算结果和数据驱动计算对比

, figureFileSmall=null, figureFileBig=null, tableContent=
项目 EI/(N·mm-1 GI/(N·m·(°)-1 t/s
求解器计算 31 755.86 21 630.26 30.20
数据驱动 31 632.32 21 769.83 0.93
误差/对比 0.389 0% 0.646 5% 32.40
), ArticleFig(id=1157001954590286250, tenantId=1146029695717560320, journalId=1146120084050784272, articleId=1157001741704192205, language=EN, label=null, caption=null, figureFileSmall=null, figureFileBig=null, tableContent=
车身性能 M/kg EI/(N·mm-1 GI/(N·m·(°)-1
初始设计 442.46 30 867.52 21 205.42
优化设计 393.33 29 799.23 20 471.51
), ArticleFig(id=1157001954640617900, tenantId=1146029695717560320, journalId=1146120084050784272, articleId=1157001741704192205, language=CN, label=表3, caption=

车身结构性能优化结果

, figureFileSmall=null, figureFileBig=null, tableContent=
车身性能 M/kg EI/(N·mm-1 GI/(N·m·(°)-1
初始设计 442.46 30 867.52 21 205.42
优化设计 393.33 29 799.23 20 471.51
), ArticleFig(id=1157001954699338158, tenantId=1146029695717560320, journalId=1146120084050784272, articleId=1157001741704192205, language=EN, label=null, caption=null, figureFileSmall=null, figureFileBig=null, tableContent=
尺寸名称 初始尺寸/mm 优化尺寸/mm
B8_2H 176.00 142.82
B8_2W_T 0.99 0.80
LEN6_b2H 176.00 146.13
LEN6_b2W_T 0.99 0.85
LEN6_1_b2H 176.00 151.55
LEN6_1_b2W_T 0.99 0.82
CRO1_2_b1_H 176.00 152.82
CRO1_2_b1_W_T 0.99 0.86
LEN2_1_b1_W 176.00 155.19
LEN2_1_b1_H_T 0.99 0.87
B16_1_b4_H 176.00 156.07
B16_1_b4_W_T 0.99 0.90
LEN3_b3W 176.00 160.12
LEN3_b3H_T 0.99 0.90
), ArticleFig(id=1157001954749669808, tenantId=1146029695717560320, journalId=1146120084050784272, articleId=1157001741704192205, language=CN, label=表4, caption=

设计变量尺寸优化结果

, figureFileSmall=null, figureFileBig=null, tableContent=
尺寸名称 初始尺寸/mm 优化尺寸/mm
B8_2H 176.00 142.82
B8_2W_T 0.99 0.80
LEN6_b2H 176.00 146.13
LEN6_b2W_T 0.99 0.85
LEN6_1_b2H 176.00 151.55
LEN6_1_b2W_T 0.99 0.82
CRO1_2_b1_H 176.00 152.82
CRO1_2_b1_W_T 0.99 0.86
LEN2_1_b1_W 176.00 155.19
LEN2_1_b1_H_T 0.99 0.87
B16_1_b4_H 176.00 156.07
B16_1_b4_W_T 0.99 0.90
LEN3_b3W 176.00 160.12
LEN3_b3H_T 0.99 0.90
)], attaches=null, journal=Journal(id=1146119049450201092, delFlag=0, nameCn=汽车工程, nameEn=Automotive Engineering, nameHistory1=null, nameHistory2=null, issn=1000-680X, eissn=, cn=11-2221/U, coden=null, periodic=0, language=CN, oaType=否, 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=QBBRQev7wkMVPuUPGz0mFw==, journalPrice=null, startedYear=null, abbrevIsoEn=Auto Eng, journalRemark=null, publicationField=null, createdTime=null, updatedTime=1755587219741, createdBy=null, updatedBy=15831073675, firstLetterCn=A, firstLetterEn=A, subjectCode=Engineering, subjectName=工程, subjectCodeEn=Engineering, subjectNameEn=null, picCn=QBBRQev7wkMVPuUPGz0mFw==, picEn=p+MsLQKu3DZkDibBsTBu1Q==, jcr=null, cjcr=null, exts=[JournalExt(id=1164580465202643295, language=CN, name=汽车工程, nameHistory1=null, nameHistory2=null, managedBy=, sponsoredBy=, publishedBy=, editorOffice=, officeProv=null, officeCity=null, officeAddr=, officeZip=, editDirector=null, officeDirector=null, officePhone=null, coverPicUrl=null, journalRemark=, submitArticleUrl=null, websiteUrl=https://www.qichegongcheng.com/CN/1000-680X/home.shtml, createdTime=1755587219763, updatedTime=1755587219763, createdBy=15831073675, updatedBy=15831073675, submissionGuidelinesUrl=https://www.qichegongcheng.com/CN/column/column6.shtml, submissionAuthorUrl=https://journal03.magtechjournal.com/journalx_qcgc/authorLogOn.action, submissionEditorUrl=https://journal03.magtechjournal.com/journalx_qcgc/editorLogOn.action, submissionReviewUrl=https://journal03.magtechjournal.com/journalx_qcgc/expertLogOn.action, submissionCeEditorUrl=https://journal03.magtechjournal.com/journalx_qcgc/editorInChiefLogOn.action, submissionAeEditorUrl=, option={"copyright":""}), JournalExt(id=1164580465248780640, language=EN, name=Automotive Engineering, nameHistory1=null, nameHistory2=null, managedBy=, sponsoredBy=, publishedBy=, editorOffice=, officeProv=null, officeCity=null, officeAddr=, officeZip=, editDirector=null, officeDirector=null, officePhone=null, coverPicUrl=null, journalRemark=, submitArticleUrl=null, websiteUrl=https://www.qichegongcheng.com/EN/1000-680X/home.shtml, createdTime=1755587219774, updatedTime=1755587219774, createdBy=15831073675, updatedBy=15831073675, submissionGuidelinesUrl=https://www.qichegongcheng.com/EN/column/column6.shtml, submissionAuthorUrl=https://journal03.magtechjournal.com/journalx_qcgc/authorLogOn.action, submissionEditorUrl=https://journal03.magtechjournal.com/journalx_qcgc/editorLogOn.action, submissionReviewUrl=https://journal03.magtechjournal.com/journalx_qcgc/expertLogOn.action, submissionCeEditorUrl=https://journal03.magtechjournal.com/journalx_qcgc/editorInChiefLogOn.action, submissionAeEditorUrl=, option={"copyright":""})], databaseList=null, tenantJournalId=1146120084050784272, websiteList=[Website(id=1148243202387206565, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1146120084050784272, 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/qcygc/CN, language=CN, createTime=1751692112776, createBy=18614031015, updateTime=1753500958911, updateBy=18614031015, name=《汽车工程》中文站点, tplId=1146099689490845704, title=汽车工程, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1148622315115540535, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1148243202387206565, code=articleTextType, value=kx, createTime=1751782500294, updateTime=1751782500294, creator=18614031015, updator=18614031015), WebsiteProps(id=1148622315094569012, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1148243202387206565, code=banner, value=null, createTime=1751782500289, updateTime=1751782500289, creator=18614031015, updator=18614031015), WebsiteProps(id=1148622315081986099, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1148243202387206565, code=logo, value=https://castjournals.cast.org.cn/joweb/kjdb/CN/file/pic?fileId=+W0ZN6/p6N8AvZxnX71krg==, createTime=1751782500286, updateTime=1751782500286, creator=18614031015, updator=18614031015), WebsiteProps(id=1148622315107151926, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1148243202387206565, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/kjdb/CN/file/pic, createTime=1751782500292, updateTime=1751782500292, creator=18614031015, updator=18614031015), WebsiteProps(id=1148622315102957621, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1148243202387206565, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_cn_619/, createTime=1751782500291, updateTime=1751782500291, creator=18614031015, updator=18614031015)]), Website(id=1155829970321686531, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1146120084050784272, 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/qcygc/EN, language=EN, createTime=1753500939211, createBy=18614031015, updateTime=1753500939211, updateBy=18614031015, name=《汽车工程》英文站点, tplId=1146101810881728533, title=Automotive Engineering, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1155830904879702095, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1155829970321686531, code=articleTextType, value=kx, createTime=1753501162023, updateTime=1753501162023, creator=18614031015, updator=18614031015), WebsiteProps(id=1155830904858730572, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1155829970321686531, code=banner, value=null, createTime=1753501162018, updateTime=1753501162018, creator=18614031015, updator=18614031015), WebsiteProps(id=1155830904837759051, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1155829970321686531, code=logo, value=https://castjournals.cast.org.cn/joweb/kjdb/CN/file/pic?fileId=+W0ZN6/p6N8AvZxnX71krg==, createTime=1753501162013, updateTime=1753501162013, creator=18614031015, updator=18614031015), WebsiteProps(id=1155830904875507790, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1155829970321686531, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/kjdb/CN/file/pic, createTime=1753501162022, updateTime=1753501162022, creator=18614031015, updator=18614031015), WebsiteProps(id=1155830904867119181, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1155829970321686531, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_cn_619/, createTime=1753501162020, updateTime=1753501162020, creator=18614031015, updator=18614031015)])], journalTitle=汽车工程, weixinUrl=null, journalUrl=null, iacademicId=null, status=0, seqNo=null, journalTitleEn=Automotive Engineering, journalPhotoCn=QBBRQev7wkMVPuUPGz0mFw==, journalPhotoEn=p+MsLQKu3DZkDibBsTBu1Q==, journalFirstLetter=A, 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/qcygc/CN/10.19562/j.chinasae.qcgc.2024.07.014, detailUrlEn=https://castjournals.cast.org.cn/joweb/qcygc/EN/10.19562/j.chinasae.qcgc.2024.07.014, pdfUrlCn=https://castjournals.cast.org.cn/joweb/qcygc/CN/PDF/10.19562/j.chinasae.qcgc.2024.07.014, pdfUrlEn=https://castjournals.cast.org.cn/joweb/qcygc/EN/PDF/10.19562/j.chinasae.qcgc.2024.07.014, aliStartDate=null, aliEndDate=null, collectionFlag=false, citedCount=null, citedUrl=null, reference=null)
收藏切换
基于数据驱动的车身结构智能设计与分析
收藏切换
PDF下载
曹榕 1 , 华钧伟 1 , 李永成 1 , 郭方俐 1 , 侯文彬 1, 2
汽车工程 | 2024,46(7): 1273-1281
收起
收藏切换
汽车工程 | 2024, 46(7): 1273-1281
基于数据驱动的车身结构智能设计与分析
全屏
曹榕1, 华钧伟1, 李永成1, 郭方俐1, 侯文彬1, 2
作者信息
  • 1. 大连理工大学汽车工程学院,大连 116024
  • 2. 大连理工大学宁波研究院,宁波 315016

通讯作者:

侯文彬,教授,博士,E-mail:
Intelligent Design and Analysis of Body Structure Based on Data Drive
Rong Cao1, Junwei Hua1, Yongcheng Li1, Fangli Guo1, Wenbin Hou1, 2
Affiliations
  • 1. School of Automotive Engineering,Dalian University of Technology,Dalian  116024
  • 2. Ningbo Research Institute,Dalian University of Technology,Ningbo  315016
出版时间: 2024-07-25 doi: 10.19562/j.chinasae.qcgc.2024.07.014
文章导航
收藏切换

概念设计作为汽车设计流程的重要阶段,需要快速地进行方案设计和方案评估。目前一般采用参数化设计和CAE相结合的方法,实现基于分析的车身结构概念设计。随着机器学习和深度学习算法的发展和成熟,智能设计方法将成为车身结构设计主要创新技术。本文使用数据驱动和优化设计相结合的方法,自主研发了车身结构智能设计软件工具(S-iVCD)。首先,基于残差网络和热力图回归算法提取车身结构特征点,实现车身结构概念模型的自动化建模。其次,基于高斯过程采样收集车身结构数据集,采用全连接神经网络模型构建了车身结构网络模型,通过将车身各部件参数输入训练好的网络模型,实时得到车身整体性能的结果。最后,将数据驱动计算与移动渐近线算法结合,快速实现考虑质量、弯曲刚度和扭转刚度的车身结构多目标优化设计。通过与有限元实例对比,计算结果的误差在允许范围内,优化计算时间大为缩短,轻量化率达到了7.4%。由此表明基于数据驱动的车身结构优化设计方法对于汽车概念设计阶段提高效率是有效的。

车身结构设计  /  轻量化  /  数据驱动分析  /  全连接神经网络

As an important stage of the automotive design process, conceptual design requires rapid conceptual design and evaluation. The current methods generally use a combination of parametric design and CAE to achieve analysis based conceptual design of car body structures. With the development and maturity of machine learning and deep learning algorithms, intelligent design methods will become the main innovative technology for body structure design. In this article, a combination of data-driven and optimization design method is used to independently develop the vehicle structure intelligent design software tool (S-iVCD). Firstly, based on residual networks and thermal map regression algorithms, feature points of the vehicle body structure are extracted to achieve automated modeling of the conceptual model of the vehicle body structure. Secondly, based on Gaussian process sampling, a body structure dataset is collected and a fully connected neural network model is used to construct the body structure network model. The parameters of various components of the vehicle body can be input into the trained network model to obtain the overall performance results of the vehicle body. Finally, by combining data-driven computing with the moving asymptote algorithm, a multi-objective optimization design of the vehicle body structure that considers mass, bending stiffness, and torsional stiffness is quickly achieved. By comparing with finite element examples, the error of the calculation results is within the allowable range, with the optimization calculation time greatly shortened, and the lightweight rate reaching 7.4%. This indicates that the data-driven body structure optimization design method is effective in improving efficiency in the conceptual design stage of automobiles.

body structure design  /  lightweighting  /  data-driven analysis  /  fully connected neural networks
曹榕, 华钧伟, 李永成, 郭方俐, 侯文彬. 基于数据驱动的车身结构智能设计与分析. 汽车工程, 2024 , 46 (7) : 1273 -1281 . DOI: 10.19562/j.chinasae.qcgc.2024.07.014
Rong Cao, Junwei Hua, Yongcheng Li, Fangli Guo, Wenbin Hou. Intelligent Design and Analysis of Body Structure Based on Data Drive[J]. Automotive Engineering, 2024 , 46 (7) : 1273 -1281 . DOI: 10.19562/j.chinasae.qcgc.2024.07.014
随着汽车行业的竞争愈演愈烈,车辆的制造与设计也在不断地进步,在汽车车身的开发设计阶段,概念设计是十分重要的一环,在概念设计阶段,不仅可以缩短整个车身设计周期1,而且还能有效减少估算和计算错误,降低设计开发过程中的风险,同时还能使最终的结构设计更加科学合理、安全可靠,提高设计的经济性和合理性2
对于车身设计,框架模型在汽车产品设计的概念设计阶段被研究者们广泛使用,在满足精度且计算结果误差较小的前提下,可以节省计算时间。汽车减轻质量可以提高功率、降低燃油消耗和废气污染,所以在现代汽车车身设计中,在保证车辆整体的弯扭刚度性能满足设计要求的情况下,要尽可能减轻质量。
数据是产品设计过程的重要资源,现有很多研究者对已有数据基于神经网络进行指导设计,优化参数,提高设计效率。Esfe等3研究确定人工神经网络模拟预测的流体黏度的可靠性。Baghoolizadeh等4利用人工神经网络和遗传算法方法优化降低了住宅建筑年用电成本以及材料成本。方培俊等5提出一种数据驱动的混合动力学模型设计,实现了不同道路附着系数下控制量精确输出。崔格格等6提出一种数据驱动的智能车个性化场景风险图构建方法,使危险场景识别模型识别准确率可达95.8%。李达等7和胡杰等8都基于数据驱动的方法对电池安全进行分析和预测,可以为电池管理系统提供辅助决策信息。
Yoshimura等9提出了数据驱动的汽车车身零件制造过程优化方法,为车身零部件在实际制造过程中减少了误差。Li等10基于数据驱动建立DSPT框架将不同问题的特征和算法性能联系起来,对汽车零部件进行多尺度轻量化优化设计。佟罡11使用 BP神经网络,在不产生冲突的情况下,预测一套车门设计方案参数,大大提高车门的设计质量和效率。Kong等 12应用神经网络促进了汽车悬架系统的设计和开发,获得具有较高的预测精度的螺旋弹簧的疲劳寿命。Topaloglu等13和Baykasog等14通过神经网络能量吸收计算碰撞参数,改善了碰撞性能。贾良跃等15提出了一种基于长短期记忆网络的车身结构轻量化优化方法,对无人车车身桁架结构进行设计前期优化,进一步缩短汽车车身设计的周期。Wang等16则提出了一种创新的多目标优化方法,利用遗传算法结合人工神经网络来设计汽车的薄壁梁截面,优化了梁结构性能。Rostamzadeh-Renani等17以7个汽车的动力学附件的形状设计变量为结果导向,利用人工神经网络结合遗传算法对动力学附件进行设计,使得汽车阻力降低,提高了燃油效率。
数据驱动方法在车身结构设计软件上的研究较少,本文首先采用基于图像特征点识别和热力图回归的方法,实现了车身结构概念模型的自动建模,然后采用数据驱动方法,将神经网络与移动渐近线算法结合,实现同时考虑质量、弯曲刚度和扭转刚度的车身结构分析与优化设计,最后将其应用于自主研发的S-iVCD工业设计软件。
基于深度学习的关键点识别算法是一种通过神经网络模型来自动提取和匹配图像中的关键点的方法。传统的基于沙漏网络(hourglass network)的关键点检测模型通过堆叠多个卷积层以实现较高的预测准确度,因为图像特征的传递路径加深,越能够提取更加丰富的细节信息,但是同时会出现梯度消失或者梯度爆炸等问题,使得网络的训练变得更加困难。
本文使用基于改进的关键点检测网络,引入残差网络,解决深层网络易梯度消失问题,将沙漏网络和残差网络相结合实现更加准确的关键点检测。
S-iVCD软件工具中将沙漏残差神经网络结构用于实现车身结构关键点检测,残差块结构图如图1所示。沙漏残差网络结构分为上下两个通路,上通路通过残差块提取特征,下通路又分为左右对称两部分,左部分由残差块和下采样(池化)操作减少特征图尺寸,用于捕捉更加广阔的感受野,右部分通过上采样(反池化)操作增加特征图尺寸,并恢复空间分辨率,同时将其与上通路中尺寸相同的特征图进行特征融合,并利用最终输出的特征图信息预测车身结构关键点。
关键点识别目标是得到车身结构所有关键点的坐标信息,采用坐标值回归,输入车身结构设计草图,输出车身结构的关键点坐标值,因为关键点坐标值是离散的,进而导致这种端到端的回归方式具有较差的泛化能力,并且容易产生过拟合现象。因此本文关键点识别的神经网络采用热力图(heat map)回归的方式来输出关键点坐标信息,为车身结构的每个关键点生成一张对应的高斯热力图,热力图中每个像素点的值代表关键点出现的概率,距离关键点越近的像素点的值也会越大。热力图回归过程如图2所示,通过沙漏残差神经网络对输入的车身设计草图进行关键点的特征提取,在网络的最后一层输出关于每个关键点的热力图,通过取每张热力图中概率最大的像素点坐标位置作为对应关键点的预测结果。
关键点识别目标是得到车身结构所有关键点的坐标信息,采用坐标值回归,输入车身结构设计草图,输出车身结构的关键点坐标值,因为关键点坐标值是离散的,进而导致这种端到端的回归方式具有较差的泛化能力,并且容易产生过拟合现象。因此本文关键点识别的神经网络采用热力图回归的方式来输出关键点坐标信息,为车身结构的每个关键点生成一张对应的高斯热力图,热力图中每个像素点的值代表关键点出现的概率,距离关键点越近的像素点的值也会越大。
S-iVCD软件工具以开源三维建模几何内核Open CASCADE(OCC)作为底层建模引擎,结合1.1节的深度学习网络模型能够准确检测车身结构的关键点,并且可以快速地进行车身结构概念模型参数化建模操作。如图3所示,在该软件系统中,可由设计者导入车身结构设计草图,由沙漏残差神经网络检测得到关键点的相对坐标信息,底层建模引擎依据坐标位置创建各个关键点并显示于软件模型区域,同时软件系统依据所选车型类别信息读取数据库中车身结构模板数据库,得到硬点之间的连接关系,并自动生成具有梁板结构的车身概念模型。
同时S-iVCD软件工具具备全参数化的车身结构柔性建模功能,在由系统自动生成的模型基础之上,可由设计者根据需求对车身结构关键点、梁和板结构位置进行调整和增加或删除操作,同时可自由调整各个梁截面尺寸参数和板结构实现车身概念模型快速参数化设计,相应的设计参数信息以一定的数据结构自动存储于软件后台数据库中,并为后续的车身结构性能分析和优化奠定基础。
传统的车身结构分析方法常常依赖于经验规则和基于物理原理的数值模拟。这些方法在一定程度上可以提供有关材料强度、刚度和耐久性等方面的信息,但由于模型的简化和限制,其结果往往无法完全准确地反映真实的工况和边界条件。基于数据驱动的车身结构分析方法是一种将数据科学技术应用于汽车车身设计的创新方法,借助机器学习和统计分析的技术,可以从数据中提取出关键特征,识别出影响车身性能的因素,并根据这些信息进行优化和改进。基于数据驱动的车身结构分析方法则可以通过利用大量的真实数据进行建模和分析,更准确地了解车身结构在不同工况下的响应和行为,从而更加精确地进行设计和改进。随着数据处理和机器学习技术的迅猛发展,可以利用大量的现实数据来辅助汽车车身结构的分析、优化和创新。与此同时能够提高设计效率和精度,为汽车行业的创新和发展注入新的活力。
数据驱动分析需要大量的现有数据进行支撑,在S-iVCD软件中设置各车身结构参数的变化范围,改变结构参数大小,进行有限元计算,采用高斯过程采样,保存原始的车身结构参数和有限元计算结果作为数据集,为下一步的神经网络训练做准备。基于关键点识别后,完成自动化建立车身模型,采用高斯过程采样进行数据集的收集。汽车车身框架模型主要由薄壁梁、底板组成,在进行车身整体的结构性能计算时,薄壁梁的力学性能会很大程度影响整体。为了方便计算,在建模时默认采用矩形的梁截面,如图4所示。
图中: h为梁单元截面的高度; b为梁单元截面的宽度; t h为梁单元截面高度的厚度; t b为梁单元截面宽度的厚度。
横截面的面积计算公式为
A = h × b - ( b - 2 t h ) ( h - 2 t b )
x轴的惯性矩计算公式为
I x = b h 3 - ( b - 2 t h ) ( h - 2 t b ) 3 12
y轴的惯性矩计算公式为
I y = h b 3 - ( h - 2 t b ) ( b - 2 t h ) 3 12
高斯过程是一种用于建模随机函数的强大工具,在数据驱动中被广泛使用,高斯过程对于数据点的数目没有要求,因此可以适应多样的数据集大小和结构,还具有良好的可解释性、灵活性和泛化能力,能够提供置信区间和偏差-方差权衡等重要信息。具体来说,高斯过程将一个函数 f ( x )看作是无限维的高斯分布中的一个样本点。这个分布由其均值函数 μ ( x )式(4))和协方差函数 k ( x , x ' )式(5))完全确定:
μ x = E f x
k ( x , x ' ) = E [ f ( x ) - m ( x ) f ( x ' ) - m ( x ' ) ]
因此,高斯过程可以表示为
f ( x ) G P ( m ( x ) , k ( x , x ' ) )
对于任意给定的输入 x x ',它们之间的协方差 k ( x , x ' ) 描述了它们之间的相似性,即如果两个输入点越相似,它们对应的输出值之间的相关性就越强。
深度学习神经网络能够处理各种类型的高维度、非线性、大规模的数据,并从中自动地学习到有用的特征,具有较高的准确率、优秀的泛化能力和自适应的能力,对于设计变量较多且复杂的模型,其计算结果的精度和误差在工程上是可以接受的。神经网络的结构设计包含网络结构的设计和损失函数的选择,完成神经网络的设计后,选择适当的优化器,将2.1节获得的数据集传入网络模型中进行训练和验证测试,通过不断调整模型结构和权值大小,最终获得最优的网络模型并保存,为网络模型的使用做准备。
本文采用的全连接神经网络,对于一个具有 n个输入特征和 m个输出特征的问题,其输入样本为 x x R n,输出结果为 y y R m,那么全连接神经网络的基本操作可以表示为
y = σ ( W x + b )
式中:   σ为激活函数; W为权重矩阵; W R m × n b 为偏置向量, b R m
在全连接神经网络的训练过程中,采用正则化技术来防止网络出现过拟合现象。通过在损失函数中增加正则项,可以有效地控制网络的复杂度,从而提高其泛化能力。
使用的正则化包括 L 1正则化和 L 2正则化,可用式(8)式(9)表示:
L 1 = λ i = 1 n w i
L 2 = λ i = 1 n w i 2
式中: λ为超参数; w i为模型中第i个权重参数。
L 1正则化通过惩罚权重参数的绝对值之和来限制模型复杂度。当某些权重参数不重要时, L 1正则化会将其压缩至0,从而实现特征选择。 L 2正则化通过惩罚权重参数的平方和来限制模型复杂度,使得较小的权重参数接近于0,从而实现权重衰减的效果。
在车身的设计和开发过程中,弯曲刚度和扭转刚度是衡量车身结构整体性能的重要指标。二者对于车辆的行驶安全性和稳定性影响十分明显,同时还会影响到车辆的外观设计和车身质量。
弯曲工况下,对概念车身结构框架模型进行分析计算的载荷和边界条件默认设置如图5所示,在四轮悬挂处设置123自由度约束,在底盘接近乘员座椅位置,设置4个大小一样的z轴负向载荷。
弯曲刚度计算公式见式(10),即车身所受的所有弯曲载荷F与最大弯曲位移的比值:
K B = 1 n i = 1 n   F i u i
式中: K B为弯曲刚度,N/m;n为施加的集中力的个数; F i为所受载荷的等效集中; u i为该载荷下的位移。
扭转工况下,对概念车身结构框架模型进行分析计算的载荷和边界条件设置如图6所示,在后轮接近后悬挂的位置设置6个自由度的约束,在前轮接近悬挂的位置施加大小相等方向相反的载荷。
扭转刚度的计算公式见式(11),即车身所受的扭转力矩与载荷产生的扭转角的比值:
K T = M T θ = F × B a r c t a n   u B
式中: K T为扭转刚度,N·m/rad; M T为扭转力矩;   θ为扭转角; F为车身所受的扭转载荷; B为载荷位置与约束位置之间的距离; u为载荷产生的位移。
在概念设计的优化阶段,如何在保证车身各结构性能在满足一定要求下,尽可能减轻车身框架的质量,所以优化模型以车身的质量函数为目标函数,在车身整体的弯曲刚度和扭转刚度函数为约束:
m i n      M ( X ) s . t .     K B L K B ( X )             K T L K T ( X ) d . v .    X L X X U
式中: M ( X )为车身关于梁截面尺寸的质量函数; K B ( X )为车身关于梁截面尺寸的弯曲刚度函数; K B L为车身弯曲刚度下极限值; K T ( X )为车身关于梁截面尺寸的扭转刚度函数; K T L为车身扭转刚度下极限值; X为车身梁截面尺寸参数; X L X U分别为车身梁截面尺寸的上下限值。
汽车框架结构的质量计算公式为
M ( X ) = i n   ρ i l i A i
式中:n为梁单元总数; ρ i l i A i分别为第i根梁的密度、长度及截面积。
车身的弯曲和扭转刚度函数是隐函数,所以采用差分法计算刚度函数梯度,车身质量函数梯度、车身框架截面参数以及弯曲、扭转刚度函数梯度如式(14)~式(17)所示。
M ( X ) = M X 1 , M X 2 , M X 3 , , M X n
X A i = ( X 1 , X 2 , , X i + Δ i , , X n )
K B ( X ) = K B X 1 - K B X 1 , , K B X n - K B X n
K T ( X ) = K T X 1 - K T X 1 , , K T X n - K T X n
式中: M ( X )为车身结构质量函数; X i为各车身梁截面的尺寸函数。
数据驱动车身结构采用移动渐近线优化方法(method of moving asymptotes,MMA),具体优化步骤如下。
(1)默认车身截面尺寸为 X 0,令K=0;
(2)给出 X k,计算模型在第k步迭代下的梯度函数并将结果进行验证是否符合约束条件:
K B n o w ( X k ) = K B ( X k )
K T n o w ( X k ) = K T ( X k )
K B L K B n o w
K T L K T n o w
X L X k X U
(3)根据步骤(2)优化迭代所得的当前值结果,作为下一次迭代的初始值,令 k = k + 1
X k = X k + 1
更新参数后返回步骤(2),最终获得车身质量最优值。
整体的优化流程如图7所示。基本可以分为如下步骤。
(1)前期将默认的汽车车身框架的初始参数作为原始设计变量,以便在自主设计的S-iVCD设计软件中建立车身框架模型,在设计优化过程中,可以改变车身框架各设计变量参数来更改车架模型,同时在S-iVCD设计软件中施加载荷,计算结构性能。
(2)选择优化车身框架的设计变量,建立目标优化模型,设置约束条件,得到目标优化函数和约束函数,为下一步进行迭代优化做准备。
(3)数据驱动的车身结构性能计算,S-iVCD软件结合全连接神经网络,可以实现在某个特定工况下的车身框架整体性能计算。
(4)使用上述MMA优化步骤进行不断迭代优化,在设置的约束条件下,利用数据驱动的车身结构性能计算进行优化设计参数,最终获得符合设计要求的最优设计变量。
在自主开发的S-iVCD软件中添加全连接神经网络和移动渐近线优化程序,指导汽车车身框架结构参数的实际设计和优化。
S-iVCD软件系统基于Python开发语言构建3D CAD/CAE/PLM开发框架进行设计开发,用户和系统进行交互的界面利用PyQt5界面设计库中的用户界面图形设计器Qt Designer进行设计,图8所示为软件系统交互界面,包括菜单栏、用户操作区、结果可视化区,用户可以通过操作界面按钮触发对应槽函数,完成车身的关键点识别自动化建模和后续的优化设计。
在数据准备阶段,采用高斯过程采样,保存原始的车身结构参数和有限元计算结果将作为数据集,为神经网络训练做准备。
在网络训练阶段,对1 000组变量数据进行拟合,使用训练数据800组,验证数据100组,测试数据100组。经过多次调参,选择最优的神经网络模型,神经网络的一些超参数设置如表1所示,损失函数的类型选取的是均方误差(MSE),也就是网络的输出值与原始数据的期望值的误差的平方和的平均值,即
M S E = 1 n i = 1 n y i - y ^ i 2
式中: n为样本的个数; ω为权重。
数据驱动下网络模型的应用时,按照如图9所示的数据驱动拟合预测原理,将车身各结构参数输入已经保存的训练后的网络模型中,进行数据驱动计算,在2.3节的相同工况下,最终得出车身整体性能的结果。
相同工况下使用有限元求解器计算结果和数据驱动计算结果与所需时间对比如表2所示。
结果显示,基于数据驱动有限元计算对汽车车身框架进行计算所需0.93 s,与使用有限元求解器计算时间相比,大大缩短,相同的载荷工况条件下的计算结果误差也在可接受范围内,可以用来辅助汽车车身结构的分析、优化,缩短汽车设计周期。
选择图10所示的框架车身作为优化模型,选择车身质量作为优化目标,设置车身初始刚度作为约束条件和选择14个截面尺寸参数作为设计变量。通过上述的优化设计流程,在保证车身整体性能满足要求的情况下,优化结果减轻了概念车身的质量。表3为车身结构性能优化结果,优化前的车身质量为422.46 kg,优化后的车身质量为393.33 kg,轻量29.13 kg,轻量化率达到7.4%,车身整体弯扭刚度略有降低,弯曲刚度降低约3%,扭转刚度降低约3%,满足性能要求,达到了优化目标,此外,在同样的条件下,之前使用有限元求解器进行优化所需时间大约为14 h,使用数据驱动的优化程序计算时间仅需28.47 s,极大地提高了车身概念设计效率。
表4所示为设计变量尺寸优化前后对比,设计时梁的截面尺寸参数默认是相同的,基于数据驱动的方法结合MMA优化算法,将14个截面尺寸参数的设计变量进行优化后,各个设计变量均有不同程度的参数变化,本质上是截面尺寸变小。图11所示为应用数据驱动方法的车身弯扭刚度和质量的迭代优化曲线。根据优化结果可以看出,车身质量总体是呈下降趋势的,车身的弯扭刚度也随着车身质量整体呈下降趋势,依然能够满足车身性能要求,所以使用的数据驱动的车身优化方法是有效的。
综上,基于数据驱动的车身框架结构优化设计方法对于汽车概念设计阶段是有效的。在表2中也可看出,计算结果的误差在允许范围内,优化计算的迭代时间大为缩短,在汽车概念设计阶段的实际应用中能够提高设计效率,进而缩短汽车车身的设计周期。
本文将移动渐近线优化方法与全连接神经网络相结合,提出了一种以数据驱动的车身结构计算优化方法,对车身整体结构梁和板进行组合优化设计。首先介绍了基于图像的深度学习特征点识别算法,实现车身结构的自动化建模,在此基础上,采用高斯过程采样进行数据集的收集,构建车身结构网络模型,建立了综合考虑质量、弯曲刚度和扭转刚度的优化模型,对车身结构进行设计优化。
算例表明,在自主开发的S-iVCD软件中,通过高斯过程取样的方法,将先前车身有限元分析数据不断收集起来,通过全连接神经网络模型对数据集进行学习,在不降低计算准确率,满足弯曲刚度和扭转刚度的前提下,可以减轻车身结构的质量,提高车身结构设计效率。
  • 国家自然科学基金(52072057)
  • 宁波市重点研发计划项目(2023Z065)
参考文献 引证文献
排序方式:
1
韩景飞. 面向概念设计的车身结构智能建模方法的研究[D].大连:大连理工大学,2021.
HAN J F. Research on intelligent modeling methods of body structure for conceptual design[D]. Dalian: Dalian University of Technology, 2021.
2
余咏红. 概念设计与结构措施在建筑结构设计中的应用[J]. 房地产世界,2021(15):41-43.
YU Y H. Application of conceptual design and structural measures in building structural design[J]. The World of Real Estate, 2021(15):41-43.
3
ESFE M H, ESMAILY R, KHABAZ M K, et al. A novel integrated model to improve the dynamic viscosity of MWCNT-Al2O3 (40:60)/Oil 5W50 hybrid nano-lubricant using artificial neural networks (ANNs)[J]. Tribology International, 2023,178(14): 108-123.
4
BAGHOOLIZADEH M, DEHKORDI S A H H, ROSTAMZADEH-RENANI M, et al. Optimization of annual electricity consumption costs and the costs of insulation and phase change materials in the residential building using artificial neural network and genetic algorithm methods[J]. Journal of Energy Storage, 2023,62(14): 1178-1201.
5
方培俊,蔡英凤,陈龙,等. 基于车辆动力学混合模型的智能汽车轨迹跟踪控制方法[J]. 汽车工程,2022,44(10):1469-1483,1510.
FANG P J, CAI Y F, CHEN L, et al. Trajectory tracking control method based on vehicle dynamics hybrid model for intelligent vehicle [J].Automotive Engineering,2022,44(10):1469-1483,1510.
6
崔格格,吕超,李景行,等.数据驱动的智能车个性化场景风险图构建[J].汽车工程, 2023,45(2):231-242.
CUI G G, LV C, LI J X, et al. Data-driven personalized scenario risk map construction for intelligent vehicles[J].Automotive Engineering, 2023,45(2):231-242.
7
李达,邓钧君,张照生,等.电动车辆动力电池安全预警策略研究综述[J].汽车工程,2023,45(8):1392-1407.
LI D, DENG J J, ZHANG Z S, et al. Review on power battery safety warning strategy in electric vehicles[J].Automotive Engineering, 2023, 45(8): 1392-1407.
8
胡杰,余海,杨博闻,等.基于数据驱动的电动汽车电池安全风险预测[J].汽车工程,2023,45(5):814-824.
HU J, YU H, YANG B W, et al. Battery safety risk prediction for data-driven electric vehicles[J].Automotive Engineering, 2023,45(5):814-824.
9
YOSHIMURA M, NISHIWAKI S, IZUI K. A multiple cross-sectional shape optimization method for automotive body frames[J].Journal of Mechanical Design,2005,127 (8): 49-57.
10
LI H, LIU Z, ZHU P, et al. A data-driven self-adaptive parameter tuning framework for composite automobile part optimization design[J]. Proceedings of the Institution of Mechanical Engineers, Part D: Journal of Automobile Engineering,2023,237(10-11):2592-2604.
11
佟罡. 基于机器学习的车门协同设计冲突消解[D].大连:大连理工大学,2019.
TONG G. Machine learning-based door co-design conflict resolution[D]. Dalian :Dalian University of Technology,2019.
12
KONG Y S, ABDULLAH S, SCHRAMM D, et al. Optimization of spring fatigue life prediction model for vehicle ride using hybrid multi-layer perceptron artificial neural networks[J]. Mech Syst Signal Process,2019,122(24): 597-621.
13
TOPALOGLU A, KAYA N, ÖZTURK F. Predictions of the design decisions for vehicle alloy wheel rims using neural network[J]. Proceedings of the Institution of Mechanical Engineers, Part D: Journal of Automobile Engineering, 2022, 237 (12):2913-2927.
14
BAYKASOGLU A, BAYKASOGLU C, CETIN E. Multi-objective crashworthiness optimization of lattice structure filled thinwalled tubes[J]. Thin-Walled Struct,2020, 149(26): 617-630.
15
贾良跃,郝佳,商曦文,等. 基于长短期记忆网络的桁架车身结构轻量化设计优化[J]. 计算机集成制造系统,2022, 24 (2): 1-20.
JIA L Y,HAO J,SHANG X W, et al. Lightweight design optimization of truss body structure based on long short-term memory network[J]. Computer Integrated Manufacturing Systems,2022, 24(2): 1-20.
16
WANG X, SUN P, ZUO W, et al. Multi-objective optimization of automobile body frame considering weight, rigidity, and frequency for conceptual design[J]. Advances in Mechanical Engineering, 2022,14(2) :317-335.
17
ROSTAMZADEH-RENANI M, BAGHOOLIZADEH M, ROSTAMZADEH-RENANI R, et al. The effect of canard’s optimum geometric design on wake control behind the car using artificial neural network and genetic algorithm[J]. ISA Transactions, 2022,131: 427-443.
2024年第46卷第7期
PDF下载
309
121
引用本文
BibTeX
文章信息
doi: 10.19562/j.chinasae.qcgc.2024.07.014
  • 接收时间:2023-09-24
  • 首发时间:2025-07-29
  • 出版时间:2024-07-25
补充材料
相关文章
文章信息
作者
出版历史
  • 收稿日期:2023-09-24
  • 修回日期:2023-12-29
基金
国家自然科学基金(52072057)
宁波市重点研发计划项目(2023Z065)
作者信息
    1. 大连理工大学汽车工程学院,大连 116024
    2. 大连理工大学宁波研究院,宁波 315016

通讯作者:

侯文彬,教授,博士,E-mail:
参考文献
分享链接
https://castjournals.cast.org.cn/joweb/qcygc/CN/10.19562/j.chinasae.qcgc.2024.07.014
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