Article(id=1228282191663268510, tenantId=1146029695717560320, journalId=1227999626482147330, issueId=1228282191159952029, articleNumber=null, orderNo=null, doi=10.16579/j.issn.1001.9669.2025.10.001, pmid=null, cstr=null, oa=null, hot=null, price=null, onlineType=0, articleFormat=0, articleType=null, articleTypeStr=null, receivedDate=1701100800000, receivedDateStr=2023-11-28, revisedDate=1705161600000, revisedDateStr=2024-01-14, acceptedDate=null, acceptedDateStr=null, onlineDate=1770774894871, onlineDateStr=2026-02-11, pubDate=1760457600000, pubDateStr=2025-10-15, doiRegisterDate=null, doiRegisterDateStr=null, onlineIssueDate=1770774894871, onlineIssueDateStr=2026-02-11, onlineJustAcceptDate=null, onlineJustAcceptDateStr=null, onlineFirstDate=null, onlineFirstDateStr=null, sourceXml=null, magXml=null, createTime=1770774894871, creator=13701087609, updateTime=1770774894871, updator=13701087609, issue=Issue{id=1228282191159952029, tenantId=1146029695717560320, journalId=1227999626482147330, year='2025', volume='47', issue='10', pageStart='1', pageEnd='157', issueExtLink='null', onlineDate='null', pubDate='null', beforeIssueId=null, nextIssueId=null, price=null, status=1, issueComplete=1, articleOrder=1, issueType=1, specialIssue=null, createTime=1770774894751, creator=13701087609, updateTime=1770775890381, updator=13701087609, preIssue=null, nextIssue=null, ext={EN=IssueExt(id=1228286367227118244, tenantId=1146029695717560320, journalId=1227999626482147330, issueId=1228282191159952029, language=EN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=), CN=IssueExt(id=1228286367227118245, tenantId=1146029695717560320, journalId=1227999626482147330, issueId=1228282191159952029, language=CN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=)}, issueFiles=null}, startPage=1, endPage=15, ext={EN=ArticleExt(id=1228282191986229922, articleId=1228282191663268510, tenantId=1146029695717560320, journalId=1227999626482147330, language=EN, title=Data-driven method for rapid prediction of vehicle road load, columnId=1228282191914926752, journalTitle=Journal of Mechanical Strength, columnName=Vibration·Noise·Monitoring·Diagnosis, runingTitle=null, highlight=null, articleAbstract=

The six-component forces at the wheel-road interaction represent the sole coupling between the vehicle and the road surface, and obtaining these forces is critical for conducting reliability and durability assessments of the entire vehicle. In response to the high cost, long cycle, and low efficiency associated with traditional methods for obtaining wheel six-component forces, a data-driven approach for rapidly predicting wheel loads was proposed. Firstly, for the non-stationary random signals on real vehicle roads, a joint method of the complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN), permutation entropy (PE), and wavelet threshold denoising (WTD) was applied for the data denoising.Secondly, the easily obtainable and low-cost data, such as wheel center acceleration, damper displacement, and center of mass acceleration, were used as inputs. Various neural network architectures with nonlinear transfer relationships were designed for multi-surface wheel six-component force prediction. A multi-dimensional load prediction evaluation system was established in the time domain, frequency domain, and damage domain. Finally, in order to overcome the challenges of a large and costly training dataset, an input channel compression method based on the correlation and coherence analysis of neural network inputs and outputs was proposed. Minimum load signal segment division criteria were introduced, and the minimum segment duration for each road surface was determined to compress the training dataset. Through continuous model iterations, the predicted values of the wheel six-component forces closely match the measured values, and the load characteristics are preserved. This demonstrates that the minimal dataset model can achieve a high level of prediction accuracy with fewer input channels and shorter load segment durations, resulting in a 28.85% improvement in computational efficiency.

, correspAuthors=null, authorNote=null, correspAuthorsNote=
ZHAO Lihui, E-mail:
, 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=Jinzhi FENG, Zenghong LI, Dongdong ZHANG, Dongjian LIU, Lihui ZHAO), CN=ArticleExt(id=1228282202421658622, articleId=1228282191663268510, tenantId=1146029695717560320, journalId=1227999626482147330, language=CN, title=数据驱动的整车道路载荷快速预测方法, columnId=1228282192078504611, journalTitle=机械强度, columnName=振动·噪声·监测·诊断, runingTitle=null, highlight=null, articleAbstract=

车辆与路面间相互作用力中的车轮六分力是车路间的唯一耦合,获取车轮六分力是开展整车可靠性与耐久性评价的关键。针对传统的车轮六分力获取方法成本高、周期长、效率低的问题,提出数据驱动的车轮载荷快速预测的方法。首先,针对实车道路非平稳随机信号,采用基于自适应噪声完备集合经验模态分解(Complete Ensemble Empirical Mode Decomposition with Adaptive Noise, CEEMDAN)、排列熵(Permutation Entropy, PE)以及小波阈值降噪(Wavelet Threshold Denoising, WTD)的联合方法进行数据去噪;其次,以轮心加速度、减振器位移、质心加速度等容易获取且获取成本低的数据为输入,设计包含非线性传递关系的不同神经网络架构进行多路面下车轮六分力预测,并建立时域、频域、损伤域多维度载荷预测评估体系;最后,为克服训练样本大且获取代价高的缺点,提出基于神经网络输入与输出相关性-相干性分析的输入通道压缩方法,提出最小载荷信号片段划分指标并确定各路面最小片段时长,进行训练集压缩。经过模型不断迭代,车轮六分力的预测值与实测值较为接近,载荷特征也得以保留,计算效率提高28.85%,证明了最小数据集模型能够以较少的输入通道数量、较短的载荷片段时长复现较高期望的预测精度。

, correspAuthors=null, authorNote=null, correspAuthorsNote=
赵礼辉,男,1985年生,山东青岛人,博士,副教授,硕士研究生导师;主要研究方向为车辆强度可靠性设计与评价、车辆载荷特征建模与快速试验;E-mail:
, copyrightStatement=null, copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=TH7IF61/eIxjdj3gbxyk2g==, magXml=SQGct+NwTpBGCSdsDkTmOg==, pdfUrl=null, pdf=4kZGrCHdzTIkOeVFkB//Bg==, pdfFileSize=18445392, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=JUiXI5Fz5hgQebjmzpb/FA==, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=JHjNEqri6th0xHUQBIXi2w==, mapNumber=null, authorCompany=null, fund=null, authors=

冯金芝,女,1973年生,山东诸城人,博士,副教授,硕士研究生导师;主要研究方向为现代汽车设计理论;E-mail:

, authorsList=冯金芝, 李增宏, 张东东, 刘东俭, 赵礼辉)}, authors=[Author(id=1228282204325871665, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1228282191663268510, orderNo=0, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=jzfeng99@163.com, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1228282204439117882, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1228282191663268510, authorId=1228282204325871665, language=EN, stringName=Jinzhi FENG, firstName=Jinzhi, middleName=null, lastName=FENG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 2, 3, address=1.School of Mechanical Engineering, University of Shanghai for Science and Technology, Shanghai 200093, China
2.CMIF Key Laboratory for Strength and Reliability Evaluation of Automotive Structures, Shanghai 200093, China
3.Shanghai Technical Service Platform for Reliability Evaluation of New Energy Vehicles, Shanghai 200093, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1228282204514615361, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1228282191663268510, authorId=1228282204325871665, language=CN, stringName=冯金芝, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 2, 3, address=1.上海理工大学 机械工程学院,上海 200093
2.机械工业汽车机械零部件强度与可靠性评价重点实验室,上海 200093
3.上海市新能源汽车可靠性评价专业技术服务平台,上海 200093, bio={"content":"

冯金芝,女,1973年生,山东诸城人,博士,副教授,硕士研究生导师;主要研究方向为现代汽车设计理论;E-mail:

"}, bioImg=null, bioContent=

冯金芝,女,1973年生,山东诸城人,博士,副教授,硕士研究生导师;主要研究方向为现代汽车设计理论;E-mail:

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1228282202656538635, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1228282191663268510, xref=1., ext=[AuthorCompanyExt(id=1228282202664927244, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1228282191663268510, companyId=1228282202656538635, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.School of Mechanical Engineering, University of Shanghai for Science and Technology, Shanghai 200093, China), AuthorCompanyExt(id=1228282202673315854, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1228282191663268510, companyId=1228282202656538635, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.上海理工大学 机械工程学院,上海 200093)]), AuthorCompany(id=1228282202765590550, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1228282191663268510, xref=2., ext=[AuthorCompanyExt(id=1228282202773979156, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1228282191663268510, companyId=1228282202765590550, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.CMIF Key Laboratory for Strength and Reliability Evaluation of Automotive Structures, Shanghai 200093, China), AuthorCompanyExt(id=1228282202782367766, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1228282191663268510, companyId=1228282202765590550, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.机械工业汽车机械零部件强度与可靠性评价重点实验室,上海 200093)]), AuthorCompany(id=1228282202887225373, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1228282191663268510, xref=3., ext=[AuthorCompanyExt(id=1228282202895613982, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1228282191663268510, companyId=1228282202887225373, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3.Shanghai Technical Service Platform for Reliability Evaluation of New Energy Vehicles, Shanghai 200093, China), AuthorCompanyExt(id=1228282202904002591, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1228282191663268510, companyId=1228282202887225373, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3.上海市新能源汽车可靠性评价专业技术服务平台,上海 200093)])]), Author(id=1228282204585918536, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1228282191663268510, 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=1228282204690776144, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1228282191663268510, authorId=1228282204585918536, language=EN, stringName=Zenghong LI, firstName=Zenghong, middleName=null, lastName=LI, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1.School of Mechanical Engineering, University of Shanghai for Science and Technology, Shanghai 200093, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1228282204770467925, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1228282191663268510, authorId=1228282204585918536, language=CN, stringName=李增宏, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1.上海理工大学 机械工程学院,上海 200093, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1228282202656538635, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1228282191663268510, xref=1., ext=[AuthorCompanyExt(id=1228282202664927244, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1228282191663268510, companyId=1228282202656538635, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.School of Mechanical Engineering, University of Shanghai for Science and Technology, Shanghai 200093, China), AuthorCompanyExt(id=1228282202673315854, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1228282191663268510, companyId=1228282202656538635, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.上海理工大学 机械工程学院,上海 200093)])]), Author(id=1228282204879519839, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1228282191663268510, 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=1228282204980183144, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1228282191663268510, authorId=1228282204879519839, language=EN, stringName=Dongdong ZHANG, firstName=Dongdong, middleName=null, lastName=ZHANG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 2, 3, address=1.School of Mechanical Engineering, University of Shanghai for Science and Technology, Shanghai 200093, China
2.CMIF Key Laboratory for Strength and Reliability Evaluation of Automotive Structures, Shanghai 200093, China
3.Shanghai Technical Service Platform for Reliability Evaluation of New Energy Vehicles, Shanghai 200093, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1228282205059874925, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1228282191663268510, authorId=1228282204879519839, language=CN, stringName=张东东, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 2, 3, address=1.上海理工大学 机械工程学院,上海 200093
2.机械工业汽车机械零部件强度与可靠性评价重点实验室,上海 200093
3.上海市新能源汽车可靠性评价专业技术服务平台,上海 200093, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1228282202656538635, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1228282191663268510, xref=1., ext=[AuthorCompanyExt(id=1228282202664927244, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1228282191663268510, companyId=1228282202656538635, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.School of Mechanical Engineering, University of Shanghai for Science and Technology, Shanghai 200093, China), AuthorCompanyExt(id=1228282202673315854, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1228282191663268510, companyId=1228282202656538635, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.上海理工大学 机械工程学院,上海 200093)]), AuthorCompany(id=1228282202765590550, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1228282191663268510, xref=2., ext=[AuthorCompanyExt(id=1228282202773979156, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1228282191663268510, companyId=1228282202765590550, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.CMIF Key Laboratory for Strength and Reliability Evaluation of Automotive Structures, Shanghai 200093, China), AuthorCompanyExt(id=1228282202782367766, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1228282191663268510, companyId=1228282202765590550, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.机械工业汽车机械零部件强度与可靠性评价重点实验室,上海 200093)]), AuthorCompany(id=1228282202887225373, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1228282191663268510, xref=3., ext=[AuthorCompanyExt(id=1228282202895613982, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1228282191663268510, companyId=1228282202887225373, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3.Shanghai Technical Service Platform for Reliability Evaluation of New Energy Vehicles, Shanghai 200093, China), AuthorCompanyExt(id=1228282202904002591, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1228282191663268510, companyId=1228282202887225373, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3.上海市新能源汽车可靠性评价专业技术服务平台,上海 200093)])]), Author(id=1228282205143761010, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1228282191663268510, 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=1228282205240230014, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1228282191663268510, authorId=1228282205143761010, language=EN, stringName=Dongjian LIU, firstName=Dongjian, middleName=null, lastName=LIU, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=4, address=4.CATARC Automotive Proving Ground Co., Ltd., Yancheng 224100, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1228282205332504706, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1228282191663268510, authorId=1228282205143761010, language=CN, stringName=刘东俭, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=4, address=4.中汽研汽车试验场股份有限公司,盐城 224100, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1228282204233596970, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1228282191663268510, xref=4., ext=[AuthorCompanyExt(id=1228282204237791275, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1228282191663268510, companyId=1228282204233596970, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=4.CATARC Automotive Proving Ground Co., Ltd., Yancheng 224100, China), AuthorCompanyExt(id=1228282204246179884, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1228282191663268510, companyId=1228282204233596970, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=4.中汽研汽车试验场股份有限公司,盐城 224100)])]), Author(id=1228282205424779401, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1228282191663268510, orderNo=4, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=pheigoe@126.com, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1228282205542219921, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1228282191663268510, authorId=1228282205424779401, language=EN, stringName=Lihui ZHAO, firstName=Lihui, middleName=null, lastName=ZHAO, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 2, 3, address=1.School of Mechanical Engineering, University of Shanghai for Science and Technology, Shanghai 200093, China
2.CMIF Key Laboratory for Strength and Reliability Evaluation of Automotive Structures, Shanghai 200093, China
3.Shanghai Technical Service Platform for Reliability Evaluation of New Energy Vehicles, Shanghai 200093, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1228282205626106005, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1228282191663268510, authorId=1228282205424779401, language=CN, stringName=赵礼辉, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 2, 3, address=1.上海理工大学 机械工程学院,上海 200093
2.机械工业汽车机械零部件强度与可靠性评价重点实验室,上海 200093
3.上海市新能源汽车可靠性评价专业技术服务平台,上海 200093, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1228282202656538635, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1228282191663268510, xref=1., ext=[AuthorCompanyExt(id=1228282202664927244, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1228282191663268510, companyId=1228282202656538635, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.School of Mechanical Engineering, University of Shanghai for Science and Technology, Shanghai 200093, China), AuthorCompanyExt(id=1228282202673315854, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1228282191663268510, companyId=1228282202656538635, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.上海理工大学 机械工程学院,上海 200093)]), AuthorCompany(id=1228282202765590550, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1228282191663268510, xref=2., ext=[AuthorCompanyExt(id=1228282202773979156, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1228282191663268510, companyId=1228282202765590550, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.CMIF Key Laboratory for Strength and Reliability Evaluation of Automotive Structures, Shanghai 200093, China), AuthorCompanyExt(id=1228282202782367766, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1228282191663268510, companyId=1228282202765590550, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.机械工业汽车机械零部件强度与可靠性评价重点实验室,上海 200093)]), AuthorCompany(id=1228282202887225373, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1228282191663268510, xref=3., ext=[AuthorCompanyExt(id=1228282202895613982, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1228282191663268510, companyId=1228282202887225373, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3.Shanghai Technical Service Platform for Reliability Evaluation of New Energy Vehicles, Shanghai 200093, China), AuthorCompanyExt(id=1228282202904002591, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1228282191663268510, companyId=1228282202887225373, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3.上海市新能源汽车可靠性评价专业技术服务平台,上海 200093)])])], keywords=[Keyword(id=1228282205730963610, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1228282191663268510, language=EN, orderNo=1, keyword=Six-component force of the wheel center), Keyword(id=1228282205823238303, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1228282191663268510, language=EN, orderNo=2, keyword=Load prediction), Keyword(id=1228282205894541475, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1228282191663268510, language=EN, orderNo=3, keyword=Neural network), Keyword(id=1228282205978427557, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1228282191663268510, language=EN, orderNo=4, keyword=Damage assessment), Keyword(id=1228282206083285164, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1228282191663268510, language=EN, orderNo=5, keyword=Fatigue durability analysis), Keyword(id=1228282206179754161, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1228282191663268510, language=CN, orderNo=1, keyword=轮心六分力), Keyword(id=1228282206276223157, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1228282191663268510, language=CN, orderNo=2, keyword=载荷预测), Keyword(id=1228282206385275064, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1228282191663268510, language=CN, orderNo=3, keyword=神经网络), Keyword(id=1228282206481744064, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1228282191663268510, language=CN, orderNo=4, keyword=损伤评估), Keyword(id=1228282206561435843, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1228282191663268510, language=CN, orderNo=5, keyword=疲劳耐久分析)], refs=[Reference(id=1228282214736134631, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1228282191663268510, doi=null, pmid=null, pmcid=null, year=2020, volume=42, issue=1, pageStart=127, pageEnd=133, url=null, language=null, rfNumber=[1], rfOrder=0, authorNames=赵礼辉, 李佳欣, 井清, journalName=汽车工程, refType=null, unstructuredReference=赵礼辉,李佳欣,井清,等. 关联用户的汽车试验场耐久性评价路况循环确定方法研究[J]. 汽车工程202042(1):127-133., articleTitle=关联用户的汽车试验场耐久性评价路况循环确定方法研究, refAbstract=null), Reference(id=1228282214811632107, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1228282191663268510, doi=null, pmid=null, pmcid=null, year=2020, volume=42, issue=1, pageStart=127, pageEnd=133, url=null, language=null, rfNumber=[1], rfOrder=1, authorNames=ZHAO Lihui, LI Jiaxin, JING Qing, journalName=Automotive Engineering, refType=null, unstructuredReference=ZHAO LihuiLI JiaxinJING Qing,et al. Research on the method of determining road condition cycles of durability test of correlated user automobile test field[J]. Automotive Engineering202042(1):127-133.(In Chinese), articleTitle=Research on the method of determining road condition cycles of durability test of correlated user automobile test field, refAbstract=null), Reference(id=1228282214887129583, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1228282191663268510, doi=null, pmid=null, pmcid=null, year=2022, volume=33, issue=14, pageStart=1670, pageEnd=1679, url=null, language=null, rfNumber=[2], rfOrder=2, authorNames=邹喜红, 凌龙, 陈静, journalName=中国机械工程, refType=null, unstructuredReference=邹喜红,凌龙,陈静,等. 用户关联的驱动桥试验场耐久性试验规范研究[J]. 中国机械工程202233(14):1670-1679., articleTitle=用户关联的驱动桥试验场耐久性试验规范研究, refAbstract=null), Reference(id=1228282214971015665, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1228282191663268510, doi=null, pmid=null, pmcid=null, year=2022, volume=33, issue=14, pageStart=1670, pageEnd=1679, url=null, language=null, rfNumber=[2], rfOrder=3, authorNames=ZOU Xihong, LING Long, CHEN Jing, journalName=China Mechanical Engineering, refType=null, unstructuredReference=ZOU XihongLING LongCHEN Jing,et al. Research on durability test specifications of user-association drive axle test fields[J].China Mechanical Engineering202233(14):1670-1679.(In Chinese), articleTitle=Research on durability test specifications of user-association drive axle test fields, refAbstract=null), Reference(id=1228282215080067573, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1228282191663268510, doi=null, pmid=null, pmcid=null, year=2022, volume=44, issue=4, pageStart=965, pageEnd=971, url=null, language=null, rfNumber=[3], rfOrder=4, authorNames=冯金芝, 付道琪, 郑松林, journalName=机械强度, refType=null, unstructuredReference=冯金芝,付道琪,郑松林,等. 悬架动态K&C试验典型激励谱的编制研究[J]. 机械强度202244(4):965-971., articleTitle=悬架动态K&C试验典型激励谱的编制研究, refAbstract=null), Reference(id=1228282215184925181, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1228282191663268510, doi=null, pmid=null, pmcid=null, year=2022, volume=44, issue=4, pageStart=965, pageEnd=971, url=null, language=null, rfNumber=[3], rfOrder=5, authorNames=FENG Jinzhi, FU Daoqi, ZHENG Songlin, journalName=Journal of Mechanical Strength, refType=null, unstructuredReference=FENG JinzhiFU DaoqiZHENG Songlin,et al. Study on the compilation of typical excitation spectrum of suspension dynamic K&C test[J]. Journal of Mechanical Strength202244(4):965-971.(In Chinese), articleTitle=Study on the compilation of typical excitation spectrum of suspension dynamic K&C test, refAbstract=null), Reference(id=1228282215281394175, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1228282191663268510, doi=null, pmid=null, pmcid=null, year=2017, volume=null, issue=null, pageStart=56, pageEnd=null, url=null, language=null, rfNumber=[4], rfOrder=6, authorNames=熊飞, journalName=null, refType=null, unstructuredReference=熊飞. 基于实车道路谱的车身疲劳寿命预测[D]. 广州:华南理工大学,2017:56., articleTitle=基于实车道路谱的车身疲劳寿命预测, refAbstract=null), Reference(id=1228282215373668868, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1228282191663268510, doi=null, pmid=null, pmcid=null, year=2017, volume=null, issue=null, pageStart=56, pageEnd=null, url=null, language=null, rfNumber=[4], rfOrder=7, authorNames=XIONG Fei, journalName=null, refType=null, unstructuredReference=XIONG Fei. The fatigue life prediction of car body structure based on real road spectrum[D]. Guangzhou:South China University of Technology,2017:56.(In Chinese), articleTitle=The fatigue life prediction of car body structure based on real road spectrum, refAbstract=null), Reference(id=1228282215470137862, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1228282191663268510, doi=null, pmid=null, pmcid=null, year=2018, volume=null, issue=null, pageStart=28, pageEnd=null, url=null, language=null, rfNumber=[5], rfOrder=8, authorNames=徐春, journalName=null, refType=null, unstructuredReference=徐春. 汽车变速器道路载荷谱的采集和应用研究[D]. 北京:北京理工大学,2018:28., articleTitle=汽车变速器道路载荷谱的采集和应用研究, refAbstract=null), Reference(id=1228282215537246729, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1228282191663268510, doi=null, pmid=null, pmcid=null, year=2018, volume=null, issue=null, pageStart=28, pageEnd=null, url=null, language=null, rfNumber=[5], rfOrder=9, authorNames=XU Chun, journalName=null, refType=null, unstructuredReference=XU Chun. Research for acquisition and application of vehicle transmission road load spectrum[D]. Beijing:Beijing Institute of Technology,2018:28.(In Chinese), articleTitle=Research for acquisition and application of vehicle transmission road load spectrum, refAbstract=null), Reference(id=1228282215591772684, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1228282191663268510, doi=null, pmid=null, pmcid=null, year=2022, volume=null, issue=null, pageStart=55, pageEnd=null, url=null, language=null, rfNumber=[6], rfOrder=10, authorNames=王超, journalName=null, refType=null, unstructuredReference=王超. 基于虚拟试验场的车轮六分力提取方法研究[D]. 重庆:重庆理工大学,2022:55., articleTitle=基于虚拟试验场的车轮六分力提取方法研究, refAbstract=null), Reference(id=1228282215650492943, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1228282191663268510, doi=null, pmid=null, pmcid=null, year=2022, volume=null, issue=null, pageStart=55, pageEnd=null, url=null, language=null, rfNumber=[6], rfOrder=11, authorNames=WANG Chao, journalName=null, refType=null, unstructuredReference=WANG Chao. Research on wheel six-component force extraction method based on virtual proving ground[D]. Chongqing:Chongqing University of Technology,2022:55.(In Chinese), articleTitle=Research on wheel six-component force extraction method based on virtual proving ground, refAbstract=null), Reference(id=1228282215751156245, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1228282191663268510, doi=null, pmid=null, pmcid=null, year=2023, volume=23, issue=18, pageStart=8011, pageEnd=8017, url=null, language=null, rfNumber=[7], rfOrder=12, authorNames=李荣强, 连小锋, 朱睿, journalName=科学技术与工程, refType=null, unstructuredReference=李荣强,连小锋,朱睿,等. 基于机器学习的飞机起落架着陆载荷预测模型[J]. 科学技术与工程202323(18):8011-8017., articleTitle=基于机器学习的飞机起落架着陆载荷预测模型, refAbstract=null), Reference(id=1228282215839236629, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1228282191663268510, doi=null, pmid=null, pmcid=null, year=2023, volume=23, issue=18, pageStart=8011, pageEnd=8017, url=null, language=null, rfNumber=[7], rfOrder=13, authorNames=LI Rongqiang, LIAN Xiaofeng, ZHU Rui, journalName=Science Technology and Engineering, refType=null, unstructuredReference=LI RongqiangLIAN XiaofengZHU Rui,et al. Prediction model of landing load of aircraft landing gear based on machine learning[J]. Science Technology and Engineering202323(18):8011-8017.(In Chinese), articleTitle=Prediction model of landing load of aircraft landing gear based on machine learning, refAbstract=null), Reference(id=1228282215918928410, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1228282191663268510, doi=null, pmid=null, pmcid=null, year=2023, volume=44, issue=10, pageStart=414, pageEnd=419, url=null, language=null, rfNumber=[8], rfOrder=14, authorNames=牟哲岳, 孙勇, 王瑞良, journalName=太阳能学报, refType=null, unstructuredReference=牟哲岳,孙勇,王瑞良,等. 基于实测数据和机器学习的风电机组载荷预测模型[J]. 太阳能学报202344(10):414-419., articleTitle=基于实测数据和机器学习的风电机组载荷预测模型, refAbstract=null), Reference(id=1228282215990231581, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1228282191663268510, doi=null, pmid=null, pmcid=null, year=2023, volume=44, issue=10, pageStart=414, pageEnd=419, url=null, language=null, rfNumber=[8], rfOrder=15, authorNames=MOU Zheyue, SUN Yong, WANG Ruiliang, journalName=Acta Energiae Solaris Sinica, refType=null, unstructuredReference=MOU ZheyueSUN YongWANG Ruiliang,et al. Prediction model for wind turbine loads based on experimental data and machine learning[J]. Acta Energiae Solaris Sinica202344(10):414-419.(In Chinese), articleTitle=Prediction model for wind turbine loads based on experimental data and machine learning, refAbstract=null), Reference(id=1228282216048951841, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1228282191663268510, doi=null, pmid=null, pmcid=null, year=2022, volume=43, issue=4, pageStart=541, pageEnd=550, url=null, language=null, rfNumber=[9], rfOrder=16, authorNames=杨博文, 霍军周, 张伟, journalName=东北大学学报(自然科学版), refType=null, unstructuredReference=杨博文,霍军周,张伟,等. 服役结构超前载荷实时预测方法的研究[J]. 东北大学学报(自然科学版)202243(4):541-550., articleTitle=服役结构超前载荷实时预测方法的研究, refAbstract=null), Reference(id=1228282216183169574, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1228282191663268510, doi=null, pmid=null, pmcid=null, year=2022, volume=43, issue=4, pageStart=541, pageEnd=550, url=null, language=null, rfNumber=[9], rfOrder=17, authorNames=YANG Bowen, HUO Junzhou, ZHANG Wei, journalName=Journal of Northeastern University (Natural Science), refType=null, unstructuredReference=YANG BowenHUO JunzhouZHANG Wei,et al. Research on real-time overload prediction method of in-service structures[J].Journal of Northeastern University (Natural Science)202243(4):541-550.(In Chinese), articleTitle=Research on real-time overload prediction method of in-service structures, refAbstract=null), Reference(id=1228282216254472745, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1228282191663268510, doi=null, pmid=null, pmcid=null, year=2021, volume=null, issue=7, pageStart=46, pageEnd=51, url=null, language=null, rfNumber=[10], rfOrder=18, authorNames=罗欢, 胡浩炬, 余家皓, journalName=汽车技术, refType=null, unstructuredReference=罗欢,胡浩炬,余家皓. 基于深度卷积-长短期记忆神经网络的整车道路载荷预测[J]. 汽车技术2021(7):46-51., articleTitle=基于深度卷积-长短期记忆神经网络的整车道路载荷预测, refAbstract=null), Reference(id=1228282217600844331, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1228282191663268510, doi=null, pmid=null, pmcid=null, year=2021, volume=null, issue=7, pageStart=46, pageEnd=51, url=null, language=null, rfNumber=[10], rfOrder=19, authorNames=LUO Huan, HU Haoju, YU Jiahao, journalName=Automobile Technology, refType=null, unstructuredReference=LUO HuanHU HaojuYU Jiahao,et al. Prediction of vehicle road load based on deep convolution neutral network-long-short term memory[J]. Automobile Technology2021(7):46-51.(In Chinese), articleTitle=Prediction of vehicle road load based on deep convolution neutral network-long-short term memory, refAbstract=null), Reference(id=1228282217701507630, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1228282191663268510, doi=null, pmid=null, pmcid=null, year=2023, volume=133, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[11], rfOrder=20, authorNames=WANG Y, ZHENG X K, WANG L, journalName=Control Engineering Practice, refType=null, unstructuredReference=WANG YZHENG X KWANG L,et al. Edge-computing based soft sensors with local Finite Impulse Response models for vehicle wheel center loads estimation under multiple working conditions[J]. Control Engineering Practice2023133:105447., articleTitle=Edge-computing based soft sensors with local Finite Impulse Response models for vehicle wheel center loads estimation under multiple working conditions, refAbstract=null), Reference(id=1228282217852502576, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1228282191663268510, doi=null, pmid=null, pmcid=null, year=2021, volume=43, issue=5, pageStart=1041, pageEnd=1049, url=null, language=null, rfNumber=[12], rfOrder=21, authorNames=韩雪飞, 施展, 华云松, journalName=机械强度, refType=null, unstructuredReference=韩雪飞,施展,华云松. 基于参数优化MOMEDA与CEEMDAN的滚动轴承微弱故障特征提取研究[J]. 机械强度202143(5):1041-1049., articleTitle=基于参数优化MOMEDA与CEEMDAN的滚动轴承微弱故障特征提取研究, refAbstract=null), Reference(id=1228282218003497525, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1228282191663268510, doi=null, pmid=null, pmcid=null, year=2021, volume=43, issue=5, pageStart=1041, pageEnd=1049, url=null, language=null, rfNumber=[12], rfOrder=22, authorNames=HAN Xuefei, SHI Zhan, HUA Yunsong, journalName=Journal of Mechanical Strength, refType=null, unstructuredReference=HAN XuefeiSHI ZhanHUA Yunsong,et al. Weak fault feature extraction of rolling bearing based on parameter optimized MOMEDA and CEEMDAN[J]. Journal of Mechanical Strength202143(5):1041-1049.(In Chinese), articleTitle=Weak fault feature extraction of rolling bearing based on parameter optimized MOMEDA and CEEMDAN, refAbstract=null), Reference(id=1228282218099966519, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1228282191663268510, doi=null, pmid=null, pmcid=null, year=2023, volume=88, issue=4, pageStart=1015, pageEnd=1038, url=null, language=null, rfNumber=[13], rfOrder=23, authorNames=ZHAO J W, NIE G Z, YAN M, journalName=Water Science & Technology, refType=null, unstructuredReference=ZHAO J WNIE G ZYAN M,et al. A novel approach to precipitation prediction using a coupled CEEMDAN-GRU-Transformer model with permutation entropy algorithm[J]. Water Science & Technology202388(4):1015-1038., articleTitle=A novel approach to precipitation prediction using a coupled CEEMDAN-GRU-Transformer model with permutation entropy algorithm, refAbstract=null), Reference(id=1228282218192241210, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1228282191663268510, doi=null, pmid=null, pmcid=null, year=2002, volume=88, issue=17, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[14], rfOrder=24, authorNames=BANDT C, POMPE B, journalName=Physical Review Letters, refType=null, unstructuredReference=BANDT CPOMPE B.Permutation entropy:a natural complexity measure for time series[J].Physical Review Letters200288(17):174102., articleTitle=Permutation entropy:a natural complexity measure for time series, refAbstract=null), Reference(id=1228282218309681724, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1228282191663268510, doi=null, pmid=null, pmcid=null, year=2020, volume=24, issue=12, pageStart=120, pageEnd=129, url=null, language=null, rfNumber=[15], rfOrder=25, authorNames=李志军, 张鸿鹏, 王亚楠, journalName=电机与控制学报, refType=null, unstructuredReference=李志军,张鸿鹏,王亚楠,等. 排列熵—CEEMD分解下的新型小波阈值去噪谐波检测方法[J]. 电机与控制学报202024(12):120-129., articleTitle=排列熵—CEEMD分解下的新型小波阈值去噪谐波检测方法, refAbstract=null), Reference(id=1228282218414539325, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1228282191663268510, doi=null, pmid=null, pmcid=null, year=2020, volume=24, issue=12, pageStart=120, pageEnd=129, url=null, language=null, rfNumber=[15], rfOrder=26, authorNames=LI Zhijun, ZHANG Hongpeng, WANG Yanan, journalName=Electric Machines and Control, refType=null, unstructuredReference=LI ZhijunZHANG HongpengWANG Yanan,et al. Wavelet threshold denoising harmonic detection method based on permutation entropy-CEEMD decomposition[J]. Electric Machines and Control202024(12):120-129.(In Chinese), articleTitle=Wavelet threshold denoising harmonic detection method based on permutation entropy-CEEMD decomposition, refAbstract=null), Reference(id=1228282218498425410, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1228282191663268510, doi=null, pmid=null, pmcid=null, year=2018, volume=31, issue=5, pageStart=902, pageEnd=908, url=null, language=null, rfNumber=[16], rfOrder=27, authorNames=陈祥龙, 张兵志, 冯辅周, journalName=振动工程学报, refType=null, unstructuredReference=陈祥龙,张兵志,冯辅周,等. 基于改进排列熵的滚动轴承故障特征提取[J]. 振动工程学报201831(5):902-908., articleTitle=基于改进排列熵的滚动轴承故障特征提取, refAbstract=null), Reference(id=1228282218603283014, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1228282191663268510, doi=null, pmid=null, pmcid=null, year=2018, volume=31, issue=5, pageStart=902, pageEnd=908, url=null, language=null, rfNumber=[16], rfOrder=28, authorNames=CHEN Xianglong, ZHANG Bingzhi, FENG Fuzhou, journalName=Journal of Vibration Engineering, refType=null, unstructuredReference=CHEN XianglongZHANG BingzhiFENG Fuzhou,et al. Fault feature extraction of rolling bearings based on an improved permutation entropy[J]. Journal of Vibration Engineering201831(5):902-908.(In Chinese), articleTitle=Fault feature extraction of rolling bearings based on an improved permutation entropy, refAbstract=null), Reference(id=1228282218666197579, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1228282191663268510, doi=null, pmid=null, pmcid=null, year=2022, volume=19, issue=1, pageStart=65, pageEnd=80, url=null, language=null, rfNumber=[17], rfOrder=29, authorNames=ZHANG X L, CAO L Y, CHEN Y, journalName=Applied Geophysics, refType=null, unstructuredReference=ZHANG X LCAO L YCHEN Y,et al. Microseismic signal denoising by combining variational mode decomposition with permutation entropy[J]. Applied Geophysics202219(1):65-80., articleTitle=Microseismic signal denoising by combining variational mode decomposition with permutation entropy, refAbstract=null), Reference(id=1228282218741695053, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1228282191663268510, doi=null, pmid=null, pmcid=null, year=2022, volume=41, issue=10, pageStart=39, pageEnd=46, url=null, language=null, rfNumber=[18], rfOrder=30, authorNames=徐隆, 杨军, 周龙, journalName=国外电子测量技术, refType=null, unstructuredReference=徐隆,杨军,周龙,等. PE-VMD与小波阈值的干涉型光纤联合去噪方法[J]. 国外电子测量技术202241(10):39-46., articleTitle=PE-VMD与小波阈值的干涉型光纤联合去噪方法, refAbstract=null), Reference(id=1228282218880107089, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1228282191663268510, doi=null, pmid=null, pmcid=null, year=2022, volume=41, issue=10, pageStart=39, pageEnd=46, url=null, language=null, rfNumber=[18], rfOrder=31, authorNames=XU Long, YANG Jun, ZHOU Long, journalName=Foreign Electronic Measurement Technology, refType=null, unstructuredReference=XU LongYANG JunZHOU Long,et al. Joint denoising method for interferic fibers with PE-VMD and wavelet thresholds[J].Foreign Electronic Measurement Technology202241(10):39-46.(In Chinese), articleTitle=Joint denoising method for interferic fibers with PE-VMD and wavelet thresholds, refAbstract=null), Reference(id=1228282218972381780, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1228282191663268510, doi=null, pmid=null, pmcid=null, year=2022, volume=42, issue=7, pageStart=62, pageEnd=73, url=null, language=null, rfNumber=[19], rfOrder=32, authorNames=于淼, 张耀鲁, 何禹潼, journalName=光学学报, refType=null, unstructuredReference=于淼,张耀鲁,何禹潼,等. 变分模态分解-排列熵方法用于分布式光纤振动传感系统去噪[J]. 光学学报202242(7):62-73., articleTitle=变分模态分解-排列熵方法用于分布式光纤振动传感系统去噪, refAbstract=null), Reference(id=1228282219056267864, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1228282191663268510, doi=null, pmid=null, pmcid=null, year=2022, volume=42, issue=7, pageStart=62, pageEnd=73, url=null, language=null, rfNumber=[19], rfOrder=33, authorNames=YU Miao, ZHANG Yaolu, HE Yutong, journalName=Acta Optica Sinica, refType=null, unstructuredReference=YU MiaoZHANG YaoluHE Yutong,et al. Variational mode decomposition and permutation entropy method for denoising of distributed optical fiber vibration sensing system[J]. Acta Optica Sinica202242(7):62-73.(In Chinese), articleTitle=Variational mode decomposition and permutation entropy method for denoising of distributed optical fiber vibration sensing system, refAbstract=null), Reference(id=1228282219131765339, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1228282191663268510, doi=null, pmid=null, pmcid=null, year=2023, volume=35, issue=2, pageStart=52, pageEnd=58, url=null, language=null, rfNumber=[20], rfOrder=34, authorNames=李冬毅, 覃方君, 李安, journalName=海军工程大学学报, refType=null, unstructuredReference=李冬毅,覃方君,李安,等.强噪声条件下原子重力仪小波降噪适应性研究[J]. 海军工程大学学报202335(2):52-58., articleTitle=强噪声条件下原子重力仪小波降噪适应性研究, refAbstract=null), Reference(id=1228282219207262816, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1228282191663268510, doi=null, pmid=null, pmcid=null, year=2023, volume=35, issue=2, pageStart=52, pageEnd=58, url=null, language=null, rfNumber=[20], rfOrder=35, authorNames=LI Dongyi, QIN Fangjun, LI An, journalName=Journal of Naval University of Engineering, refType=null, unstructuredReference=LI DongyiQIN FangjunLI An,et al. Research on adaptability of wavelet denoising algorithm of atom gravimeter under strong noise conditions[J]. Journal of Naval University of Engineering202335(2):52-58.(In Chinese), articleTitle=Research on adaptability of wavelet denoising algorithm of atom gravimeter under strong noise conditions, refAbstract=null), Reference(id=1228282219282760288, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1228282191663268510, doi=null, pmid=null, pmcid=null, year=2023, volume=57, issue=8, pageStart=1636, pageEnd=1643, url=null, language=null, rfNumber=[21], rfOrder=36, authorNames=宋秀兰, 董兆航, 单杭冠, journalName=浙江大学学报(工学版), refType=null, unstructuredReference=宋秀兰,董兆航,单杭冠,等. 基于时空融合的多头注意力车辆轨迹预测[J]. 浙江大学学报(工学版)202357(8):1636-1643., articleTitle=基于时空融合的多头注意力车辆轨迹预测, refAbstract=null), Reference(id=1228282219379229283, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1228282191663268510, doi=null, pmid=null, pmcid=null, year=2023, volume=57, issue=8, pageStart=1636, pageEnd=1643, url=null, language=null, rfNumber=[21], rfOrder=37, authorNames=SONG Xiulan, DONG Zhaohang, SHAN Hangguan, journalName=Journal of Zhejiang University(Engineering Science), refType=null, unstructuredReference=SONG XiulanDONG ZhaohangSHAN Hangguan,et al. Vehicle trajectory prediction based on temporal-spatial multi-head attention mechanism[J]. Journal of Zhejiang University(Engineering Science)202357(8):1636-1643.(In Chinese), articleTitle=Vehicle trajectory prediction based on temporal-spatial multi-head attention mechanism, refAbstract=null), Reference(id=1228282219500864106, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1228282191663268510, doi=null, pmid=null, pmcid=null, year=2021, volume=43, issue=4, pageStart=509, pageEnd=517, url=null, language=null, rfNumber=[22], rfOrder=38, authorNames=梁冠群, 赵通, 王岩, journalName=汽车工程, refType=null, unstructuredReference=梁冠群,赵通,王岩,等. 基于LSTM网络的路面不平度辨识方法[J]. 汽车工程202143(4):509-517., articleTitle=基于LSTM网络的路面不平度辨识方法, refAbstract=null), Reference(id=1228282219643470446, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1228282191663268510, doi=null, pmid=null, pmcid=null, year=2021, volume=43, issue=4, pageStart=509, pageEnd=517, url=null, language=null, rfNumber=[22], rfOrder=39, authorNames=LIANG Guanqun, ZHAO Tong, WANG Yan, journalName=Automotive Engineering, refType=null, unstructuredReference=LIANG GuanqunZHAO TongWANG Yan,et al. Road unevenness identification based on LSTM network[J].Automotive Engineering202143(4):509-517.(In Chinese), articleTitle=Road unevenness identification based on LSTM network, refAbstract=null), Reference(id=1228282219739939441, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1228282191663268510, doi=null, pmid=null, pmcid=null, year=2022, volume=44, issue=3, pageStart=380, pageEnd=388, url=null, language=null, rfNumber=[23], rfOrder=40, authorNames=魏孟, 王桥, 叶敏, journalName=工程科学学报, refType=null, unstructuredReference=魏孟,王桥,叶敏,等. 基于NARX动态神经网络的锂离子电池剩余寿命间接预测[J]. 工程科学学报202244(3):380-388., articleTitle=基于NARX动态神经网络的锂离子电池剩余寿命间接预测, refAbstract=null), Reference(id=1228282219853185652, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1228282191663268510, doi=null, pmid=null, pmcid=null, year=2022, volume=44, issue=3, pageStart=380, pageEnd=388, url=null, language=null, rfNumber=[23], rfOrder=41, authorNames=WEI Meng, WANG Qiao, YE Min, journalName=Chinese Journal of Engineering, refType=null, unstructuredReference=WEI MengWANG QiaoYE Min,et al. An indirect remaining useful life prediction of lithiumion batteries based on a NARX dynamic neural network[J].Chinese Journal of Engineering202244(3):380-388.(In Chinese), articleTitle=An indirect remaining useful life prediction of lithiumion batteries based on a NARX dynamic neural network, refAbstract=null), Reference(id=1228282219966431863, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1228282191663268510, doi=null, pmid=null, pmcid=null, year=2023, volume=45, issue=2, pageStart=504, pageEnd=508, url=null, language=null, rfNumber=[24], rfOrder=42, authorNames=文昌俊, 陈哲, 邵明颖, journalName=机械强度, refType=null, unstructuredReference=文昌俊,陈哲,邵明颖,等. 基于改进PSO_BP神经网络的干燥机可靠性预测[J]. 机械强度202345(2):504-508., articleTitle=基于改进PSO_BP神经网络的干燥机可靠性预测, refAbstract=null), Reference(id=1228282220054512251, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1228282191663268510, doi=null, pmid=null, pmcid=null, year=2023, volume=45, issue=2, pageStart=504, pageEnd=508, url=null, language=null, rfNumber=[24], rfOrder=43, authorNames=WEN Changjun, CHEN Zhe, SHAO Mingying, journalName=Journal of Mechanical Strength, refType=null, unstructuredReference=WEN ChangjunCHEN ZheSHAO Mingying,et al. Reliability prediction of dryer based on improved PSO_BP neural network[J]. Journal of Mechanical Strength202345(2):504-508.(In Chinese), articleTitle=Reliability prediction of dryer based on improved PSO_BP neural network, refAbstract=null), Reference(id=1228282220171952765, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1228282191663268510, doi=null, pmid=null, pmcid=null, year=2023, volume=136, issue=1, pageStart=421, pageEnd=445, url=null, language=null, rfNumber=[25], rfOrder=44, authorNames=LI D H, TIAN J W, SHI S W, journalName=Computer Modeling in Engineering & Sciences, refType=null, unstructuredReference=LI D HTIAN J WSHI S W,et al. Lightweight design of commercial vehicle cab based on fatigue durability[J]. Computer Modeling in Engineering & Sciences2023136(1):421-445., articleTitle=Lightweight design of commercial vehicle cab based on fatigue durability, refAbstract=null)], funds=[Fund(id=1228282214186680791, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1228282191663268510, awardId=51705322, language=EN, fundingSource=National Natural Science Foundation of China(51705322), fundOrder=null, country=null), Fund(id=1228282214304121307, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1228282191663268510, awardId=51705322, language=CN, fundingSource=国家自然科学基金项目(51705322), fundOrder=null, country=null), Fund(id=1228282214379618783, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1228282191663268510, awardId=H-2022-304-042, language=EN, fundingSource=Industry-Academia-Research Collaboration Project(H-2022-304-042), fundOrder=null, country=null), Fund(id=1228282214652248549, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1228282191663268510, awardId=H-2022-304-042, language=CN, fundingSource=产学研合作项目(H-2022-304-042), fundOrder=null, country=null)], companyList=[AuthorCompany(id=1228282202656538635, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1228282191663268510, xref=1., ext=[AuthorCompanyExt(id=1228282202664927244, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1228282191663268510, companyId=1228282202656538635, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.School of Mechanical Engineering, University of Shanghai for Science and Technology, Shanghai 200093, China), AuthorCompanyExt(id=1228282202673315854, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1228282191663268510, companyId=1228282202656538635, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.上海理工大学 机械工程学院,上海 200093)]), AuthorCompany(id=1228282202765590550, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1228282191663268510, xref=2., ext=[AuthorCompanyExt(id=1228282202773979156, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1228282191663268510, companyId=1228282202765590550, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.CMIF Key Laboratory for Strength and Reliability Evaluation of Automotive Structures, Shanghai 200093, China), AuthorCompanyExt(id=1228282202782367766, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1228282191663268510, companyId=1228282202765590550, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.机械工业汽车机械零部件强度与可靠性评价重点实验室,上海 200093)]), AuthorCompany(id=1228282202887225373, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1228282191663268510, xref=3., ext=[AuthorCompanyExt(id=1228282202895613982, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1228282191663268510, companyId=1228282202887225373, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3.Shanghai Technical Service Platform for Reliability Evaluation of New Energy Vehicles, Shanghai 200093, China), AuthorCompanyExt(id=1228282202904002591, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1228282191663268510, companyId=1228282202887225373, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3.上海市新能源汽车可靠性评价专业技术服务平台,上海 200093)]), AuthorCompany(id=1228282204233596970, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1228282191663268510, xref=4., ext=[AuthorCompanyExt(id=1228282204237791275, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1228282191663268510, companyId=1228282204233596970, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=4.CATARC Automotive Proving Ground Co., Ltd., Yancheng 224100, China), AuthorCompanyExt(id=1228282204246179884, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1228282191663268510, companyId=1228282204233596970, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=4.中汽研汽车试验场股份有限公司,盐城 224100)])], figs=[ArticleFig(id=1228282206733402315, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1228282191663268510, language=EN, label=Fig.1, caption=Schematic diagram of the sensor and the driving route, figureFileSmall=y1A+dqY6Lz7Ygxf6wkSmOg==, figureFileBig=JUiXI5Fz5hgQebjmzpb/FA==, tableContent=null), ArticleFig(id=1228282206825677006, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1228282191663268510, language=CN, label=图1, caption=传感器示意图及行驶路线, figureFileSmall=y1A+dqY6Lz7Ygxf6wkSmOg==, figureFileBig=JUiXI5Fz5hgQebjmzpb/FA==, tableContent=null), ArticleFig(id=1228282207094112475, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1228282191663268510, language=EN, label=Fig.2, caption=Satellite map of road load collection, figureFileSmall=KzwIrcBR10XsvrksQeUmHA==, figureFileBig=cEVOiA79KlinExX8H10GJg==, tableContent=null), ArticleFig(id=1228282207182192866, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1228282191663268510, language=CN, label=图2, caption=道路载荷采集卫星图, figureFileSmall=KzwIrcBR10XsvrksQeUmHA==, figureFileBig=cEVOiA79KlinExX8H10GJg==, tableContent=null), ArticleFig(id=1228282207261884648, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1228282191663268510, language=EN, label=Fig.3, caption=Measured wheel center force load, figureFileSmall=eo9kkDsd2d8JB28RGMqdbg==, figureFileBig=LpQfTAWe3FQYIuFuz6aLUA==, tableContent=null), ArticleFig(id=1228282208654393587, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1228282191663268510, language=CN, label=图3, caption=实测轮心力载荷, figureFileSmall=eo9kkDsd2d8JB28RGMqdbg==, figureFileBig=LpQfTAWe3FQYIuFuz6aLUA==, tableContent=null), ArticleFig(id=1228282208746668285, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1228282191663268510, language=EN, label=Fig.4, caption=Validation testing of the load, figureFileSmall=foYkTFhSK97MFNz7HdvK2g==, figureFileBig=TGFvcvjqFyQUCZr/K+JSmg==, tableContent=null), ArticleFig(id=1228282208847331588, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1228282191663268510, language=CN, label=图4, caption=载荷有效性检验, figureFileSmall=foYkTFhSK97MFNz7HdvK2g==, figureFileBig=TGFvcvjqFyQUCZr/K+JSmg==, tableContent=null), ArticleFig(id=1228282208922829064, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1228282191663268510, language=EN, label=Fig.5, caption=Comparison of load resampling, figureFileSmall=yo9UEuoIGj4TLnocTEZ8qg==, figureFileBig=5oADlHPFp2m4iFP5gZNclQ==, tableContent=null), ArticleFig(id=1228282209015103759, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1228282191663268510, language=CN, label=图5, caption=载荷重采样对比, figureFileSmall=yo9UEuoIGj4TLnocTEZ8qg==, figureFileBig=5oADlHPFp2m4iFP5gZNclQ==, tableContent=null), ArticleFig(id=1228282209098989844, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1228282191663268510, language=EN, label=Fig.6, caption=Original load and its IMF component, figureFileSmall=+ywOzb0UeM5SI5z5E6IbJQ==, figureFileBig=5EneBxtiRCgWB5cbNq6PlA==, tableContent=null), ArticleFig(id=1228282209195458838, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1228282191663268510, language=CN, label=图6, caption=原始载荷及其本征模态函数分量, figureFileSmall=+ywOzb0UeM5SI5z5E6IbJQ==, figureFileBig=5EneBxtiRCgWB5cbNq6PlA==, tableContent=null), ArticleFig(id=1228282209287733532, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1228282191663268510, language=EN, label=Fig.7, caption=Comparison of original load noise reduction, figureFileSmall=BgJ4/BmWS2ApAmfi8SPZhQ==, figureFileBig=2xBR+L8J3ey+frmqSkK7iw==, tableContent=null), ArticleFig(id=1228282209375813925, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1228282191663268510, language=CN, label=图7, caption=原始载荷降噪对比, figureFileSmall=BgJ4/BmWS2ApAmfi8SPZhQ==, figureFileBig=2xBR+L8J3ey+frmqSkK7iw==, tableContent=null), ArticleFig(id=1228282209489060138, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1228282191663268510, language=EN, label=Fig.8, caption=LSTM neural network, figureFileSmall=e03d2eCCPytl2Aj4IozYmA==, figureFileBig=92Xjz/kVDaoCsKVBUIz7lw==, tableContent=null), ArticleFig(id=1228282209585529135, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1228282191663268510, language=CN, label=图8, caption=长短期记忆神经网络, figureFileSmall=e03d2eCCPytl2Aj4IozYmA==, figureFileBig=92Xjz/kVDaoCsKVBUIz7lw==, tableContent=null), ArticleFig(id=1228282209711358263, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1228282191663268510, language=EN, label=Fig.9, caption=Training error of LSTM neural network, figureFileSmall=eQdwCtXztp58+PeOgs/dvQ==, figureFileBig=jm5nw/+kkkHN7YtaB3KgDQ==, tableContent=null), ArticleFig(id=1228282209799438650, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1228282191663268510, language=CN, label=图9, caption=长短期记忆神经网络训练误差, figureFileSmall=eQdwCtXztp58+PeOgs/dvQ==, figureFileBig=jm5nw/+kkkHN7YtaB3KgDQ==, tableContent=null), ArticleFig(id=1228282209874936127, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1228282191663268510, language=EN, label=Fig.10, caption=Time-domain comparison between predicted loads and actual loads, figureFileSmall=9/eDQ5TgRBJtQfFm4oFYrg==, figureFileBig=/L0ATrzuar5vDnwOIvQ3Rw==, tableContent=null), ArticleFig(id=1228282209967210820, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1228282191663268510, language=CN, label=图10, caption=预测载荷与真实载荷时域对比, figureFileSmall=9/eDQ5TgRBJtQfFm4oFYrg==, figureFileBig=/L0ATrzuar5vDnwOIvQ3Rw==, tableContent=null), ArticleFig(id=1228282210067874121, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1228282191663268510, language=EN, label=Fig.11, caption=Frequency-domain comparison between predicted loads and actual loads, figureFileSmall=2Ux6pludcisPYVa6eM29YA==, figureFileBig=J55Hs3utXX/wfg90yrJYBg==, tableContent=null), ArticleFig(id=1228282210206286162, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1228282191663268510, language=CN, label=图11, caption=预测载荷与真实载荷频域对比, figureFileSmall=2Ux6pludcisPYVa6eM29YA==, figureFileBig=J55Hs3utXX/wfg90yrJYBg==, tableContent=null), ArticleFig(id=1228282210340503895, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1228282191663268510, language=EN, label=Fig.12, caption=Comparison of rain flow matrices between predicted loads and actual loads, figureFileSmall=BYh+DnIUFcki4SNfvEicZA==, figureFileBig=zOT3GBWJqtN4sTxn3roTHg==, tableContent=null), ArticleFig(id=1228282210432778591, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1228282191663268510, language=CN, label=图12, caption=预测载荷与真实载荷雨流矩阵对比, figureFileSmall=BYh+DnIUFcki4SNfvEicZA==, figureFileBig=zOT3GBWJqtN4sTxn3roTHg==, tableContent=null), ArticleFig(id=1228282210495693156, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1228282191663268510, language=EN, label=Fig.13, caption=Comparison of LSTM and NARX neural networks in multiple dimensions, figureFileSmall=zwSsG5bHAp7iNnbyQnXCqg==, figureFileBig=Dx4y1vG6fQVJ3r5jf9+z0Q==, tableContent=null), ArticleFig(id=1228282210571190633, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1228282191663268510, language=CN, label=图13, caption=长短期记忆神经网络与带外部输入的非线性自回归神经网络的多维度对比, figureFileSmall=zwSsG5bHAp7iNnbyQnXCqg==, figureFileBig=Dx4y1vG6fQVJ3r5jf9+z0Q==, tableContent=null), ArticleFig(id=1228282210663465329, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1228282191663268510, language=EN, label=Fig.14, caption=Schematic diagram of the load signal segmentation, figureFileSmall=3+RdbjAFntCtAP35hIBniA==, figureFileBig=p7ODaE5EDbBEy1UKdFPBbA==, tableContent=null), ArticleFig(id=1228282210726379891, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1228282191663268510, language=CN, label=图14, caption=载荷信号片段划分原理图, figureFileSmall=3+RdbjAFntCtAP35hIBniA==, figureFileBig=p7ODaE5EDbBEy1UKdFPBbA==, tableContent=null), ArticleFig(id=1228282210801877367, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1228282191663268510, language=EN, label=Fig.15, caption=Schematic and results of load segmentation, figureFileSmall=I3dJnFG4CWbh8ybTI65Aig==, figureFileBig=1YkMJXB3afAZyisJHMWSIQ==, tableContent=null), ArticleFig(id=1228282210877374845, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1228282191663268510, language=CN, label=图15, caption=载荷片段划分示意及结果, figureFileSmall=I3dJnFG4CWbh8ybTI65Aig==, figureFileBig=1YkMJXB3afAZyisJHMWSIQ==, tableContent=null), ArticleFig(id=1228282210978038147, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1228282191663268510, language=EN, label=Tab.1, caption=

Comparison of load resampling damage

, figureFileSmall=null, figureFileBig=null, tableContent=
采样频率
Sampling frequency fs /Hz
5122561005025
损伤值
Damage value/10-11
4.534.494.283.712.44
重采样损伤值
Resampling damage value/10-11
4.534.454.083.211.31
损伤复现比
Damage replication ratio/%
100.0099.1295.3286.6853.86
), ArticleFig(id=1228282211040952711, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1228282191663268510, language=CN, label=表1, caption=

载荷重采样损伤对比

, figureFileSmall=null, figureFileBig=null, tableContent=
采样频率
Sampling frequency fs /Hz
5122561005025
损伤值
Damage value/10-11
4.534.494.283.712.44
重采样损伤值
Resampling damage value/10-11
4.534.454.083.211.31
损伤复现比
Damage replication ratio/%
100.0099.1295.3286.6853.86
), ArticleFig(id=1228282211133227405, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1228282191663268510, language=EN, label=Tab.2, caption=

PE value of each IMF component

, figureFileSmall=null, figureFileBig=null, tableContent=
本征模态函数分量
IMF component
IMF1IMF2IMF3IMF4IMF5IMF6IMF7IMF8IMF9IMF10IMF11IMF12IMF13
排列熵值PE value0.9880.9150.8370.6390.3990.2690.2100.1620.1360.1250.1160.1110.108
), ArticleFig(id=1228282211221307791, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1228282191663268510, language=CN, label=表2, caption=

各本征模态函数分量排列熵值

, figureFileSmall=null, figureFileBig=null, tableContent=
本征模态函数分量
IMF component
IMF1IMF2IMF3IMF4IMF5IMF6IMF7IMF8IMF9IMF10IMF11IMF12IMF13
排列熵值PE value0.9880.9150.8370.6390.3990.2690.2100.1620.1360.1250.1160.1110.108
), ArticleFig(id=1228282211309388181, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1228282191663268510, language=EN, label=Tab.3, caption=

MSE and signal to noise ratio of different threshold calculation methods

, figureFileSmall=null, figureFileBig=null, tableContent=
不同阈值方法
Different threshold methods
均方误差
Mean square error
信噪比
Signal to noise ratio
固定阈值
Fixed threshold
2.3641.05
无偏风险估计阈值
Unbiased risk estimation threshold
2.4340.93
启发式阈值
Heuristic threshold
2.3940.98
极大极小阈值
Maximum minimum threshold
89.2825.27
), ArticleFig(id=1228282211414245788, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1228282191663268510, language=CN, label=表3, caption=

不同阈值计算方法的均方误差和信噪比

, figureFileSmall=null, figureFileBig=null, tableContent=
不同阈值方法
Different threshold methods
均方误差
Mean square error
信噪比
Signal to noise ratio
固定阈值
Fixed threshold
2.3641.05
无偏风险估计阈值
Unbiased risk estimation threshold
2.4340.93
启发式阈值
Heuristic threshold
2.3940.98
极大极小阈值
Maximum minimum threshold
89.2825.27
), ArticleFig(id=1228282211527492003, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1228282191663268510, language=EN, label=Tab.4, caption=

Different test results of neural networks

, figureFileSmall=null, figureFileBig=null, tableContent=
序号
No.
学习率
Learning rate
隐藏层节点数
Number of hidden layer node
迭代次数
Number of iterations
数据批量大小
Data batch size
时间步长
Time step
训练集决定系数
Training set determination coefficient R2/%
训练集平均绝对误差
MAE of training set EMAE
训练集均方根误差
RMSE of training set ERMSE
测试集决定系数
Testing set determination coefficient R2/%
测试集平均绝对误差
MAE of testing set EMAE
测试集均方根误差
RMSE of testing
set ERMSE
10.001801891 024792.39291.21405.3590.98325.43443.59
20.005801891 024791.04317.88440.0289.04357.48489.1
30.008801891 024793.21276.9382.9690.87324.277446.39
40.01801891 024792.72283.23396.4790.93320.95445.05
50.05801891 02474.96974.931 433.125.38964.871 437.48
60.01161891 024791.06313.13439.4690.94305.69444.81
70.01321891 024793.21269.29382.8592.30281.80409.99
80.01641891 024789.15323.06484.1887.97346.12512.52
90.01801891 024792.72283.23396.4790.93320.95445.05
100.011281891 024794.80235.54335.0093.31258.10381.99
110.01801001 024791.15309.51437.2391.15304.82439.6
120.01801891 024792.72283.23396.4790.93320.95445.05
130.01803001 024792.03290.49414.8191.22299.5437.72
140.01804001 024793.33263.09379.5291.99281.27418.23
150.01805001 024794.05251.95358.4691.84293.56421.93
160.0180189128794.92232.57331.3192.17258.52413.42
170.0180189256795.66216.05306.1593.01266.02390.61
180.0180189512794.22251.81353.3191.83302.14422.17
190.01801891 024792.72283.23396.4790.93320.95445.05
200.01801892 048791.08307.19439.0589.81335.08471.52
210.01801891 024591.70304.36423.5090.30334.98460.21
220.01801891 024693.53264.10373.7491.52303.06430.22
230.01801891 024792.72283.23396.4790.93320.95445.05
240.01801891 024892.84282.61393.2091.02320.66442.77
250.01801891 024990.81319.61445.4289.97340.35467.82
), ArticleFig(id=1228282211628155301, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1228282191663268510, language=CN, label=表4, caption=

神经网络不同试验结果

, figureFileSmall=null, figureFileBig=null, tableContent=
序号
No.
学习率
Learning rate
隐藏层节点数
Number of hidden layer node
迭代次数
Number of iterations
数据批量大小
Data batch size
时间步长
Time step
训练集决定系数
Training set determination coefficient R2/%
训练集平均绝对误差
MAE of training set EMAE
训练集均方根误差
RMSE of training set ERMSE
测试集决定系数
Testing set determination coefficient R2/%
测试集平均绝对误差
MAE of testing set EMAE
测试集均方根误差
RMSE of testing
set ERMSE
10.001801891 024792.39291.21405.3590.98325.43443.59
20.005801891 024791.04317.88440.0289.04357.48489.1
30.008801891 024793.21276.9382.9690.87324.277446.39
40.01801891 024792.72283.23396.4790.93320.95445.05
50.05801891 02474.96974.931 433.125.38964.871 437.48
60.01161891 024791.06313.13439.4690.94305.69444.81
70.01321891 024793.21269.29382.8592.30281.80409.99
80.01641891 024789.15323.06484.1887.97346.12512.52
90.01801891 024792.72283.23396.4790.93320.95445.05
100.011281891 024794.80235.54335.0093.31258.10381.99
110.01801001 024791.15309.51437.2391.15304.82439.6
120.01801891 024792.72283.23396.4790.93320.95445.05
130.01803001 024792.03290.49414.8191.22299.5437.72
140.01804001 024793.33263.09379.5291.99281.27418.23
150.01805001 024794.05251.95358.4691.84293.56421.93
160.0180189128794.92232.57331.3192.17258.52413.42
170.0180189256795.66216.05306.1593.01266.02390.61
180.0180189512794.22251.81353.3191.83302.14422.17
190.01801891 024792.72283.23396.4790.93320.95445.05
200.01801892 048791.08307.19439.0589.81335.08471.52
210.01801891 024591.70304.36423.5090.30334.98460.21
220.01801891 024693.53264.10373.7491.52303.06430.22
230.01801891 024792.72283.23396.4790.93320.95445.05
240.01801891 024892.84282.61393.2091.02320.66442.77
250.01801891 024990.81319.61445.4289.97340.35467.82
), ArticleFig(id=1228282211741401515, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1228282191663268510, language=EN, label=Tab.5, caption=

Comparison of accuracy in predicting wheel center forces by different neural network models

, figureFileSmall=null, figureFileBig=null, tableContent=
神经网络模型
Neural network model
轮心力
Wheel center force
决定系数
Determination coefficient R2
均方根误差
RMSE ERMSE
平均绝对误差
MAE EMAE
计算时间
Computational time/s
神经网络模型
Neural network model
轮心力
Wheel center force
决定系数
Determination coefficient R2
均方根误差
RMSE ERMSE
平均绝对误差
MAE EMAE
计算时间
Computational time/s
长短期记忆LSTMFx0.872 5403.95282.09186.01长短期记忆-自注意力机制
LSTM-self-attention mechanism
Fx0.850 7437.18290.24213.45
Fy0.838 4334.57234.49Fy0.839 2333.82220.06
Fz0.975 6230.37161.32Fz0.966 7269.50175.09
Mx0.877 3107.9171.05Mx0.852 1118.5481.01
My0.903 0109.3375.66My0.879 7121.8281.87
Mz0.796 480.0846.98Mz0.743 468.5543.29
长短期记忆-多头注意力机制
LSTM-multi-head attention mechanism
Fx0.871 0406.39384.84221.92带有外部输入的非线性自回
归模型
NARX model
Fx0.794 8929.09487.82295.21
Fy0.776 6393.43260.70Fy0.695 7663.80391.56
Fz0.971 6248.92177.37Fz0.990 3219.58147.04
Mx0.875 9108.5673.02Mx0.676 3165.43103.14
My0.899 8111.1774.32My0.429 0228.22113.95
Mz0.734 669.7145.32Mz0.799 575.7752.45
多层感知机
MLP
Fx0.761 1553.02362.37659.39反向传播模型
BP model
Fx0.761 1553.02362.372 523.23
Fy0.663 8656.0645.07Fy0.778 4391.85263.99
Fz0.629 2506.86391.75Fz0.491 61 053.63565.93
Mx0.431 21 114.50595.60Mx0.767 5148.6195.82
My0.694 4170.38109.18My0.888 8117.0872.08
Mz0.807 1154.2397.81Mz0.801 760.2737.31
), ArticleFig(id=1228282213146493360, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1228282191663268510, language=CN, label=表5, caption=

不同神经网络模型预测轮心力精度对比

, figureFileSmall=null, figureFileBig=null, tableContent=
神经网络模型
Neural network model
轮心力
Wheel center force
决定系数
Determination coefficient R2
均方根误差
RMSE ERMSE
平均绝对误差
MAE EMAE
计算时间
Computational time/s
神经网络模型
Neural network model
轮心力
Wheel center force
决定系数
Determination coefficient R2
均方根误差
RMSE ERMSE
平均绝对误差
MAE EMAE
计算时间
Computational time/s
长短期记忆LSTMFx0.872 5403.95282.09186.01长短期记忆-自注意力机制
LSTM-self-attention mechanism
Fx0.850 7437.18290.24213.45
Fy0.838 4334.57234.49Fy0.839 2333.82220.06
Fz0.975 6230.37161.32Fz0.966 7269.50175.09
Mx0.877 3107.9171.05Mx0.852 1118.5481.01
My0.903 0109.3375.66My0.879 7121.8281.87
Mz0.796 480.0846.98Mz0.743 468.5543.29
长短期记忆-多头注意力机制
LSTM-multi-head attention mechanism
Fx0.871 0406.39384.84221.92带有外部输入的非线性自回
归模型
NARX model
Fx0.794 8929.09487.82295.21
Fy0.776 6393.43260.70Fy0.695 7663.80391.56
Fz0.971 6248.92177.37Fz0.990 3219.58147.04
Mx0.875 9108.5673.02Mx0.676 3165.43103.14
My0.899 8111.1774.32My0.429 0228.22113.95
Mz0.734 669.7145.32Mz0.799 575.7752.45
多层感知机
MLP
Fx0.761 1553.02362.37659.39反向传播模型
BP model
Fx0.761 1553.02362.372 523.23
Fy0.663 8656.0645.07Fy0.778 4391.85263.99
Fz0.629 2506.86391.75Fz0.491 61 053.63565.93
Mx0.431 21 114.50595.60Mx0.767 5148.6195.82
My0.694 4170.38109.18My0.888 8117.0872.08
Mz0.807 1154.2397.81Mz0.801 760.2737.31
), ArticleFig(id=1228282213301682613, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1228282191663268510, language=EN, label=Tab.6, caption=

Prediction accuracy of wheel center forces

, figureFileSmall=null, figureFileBig=null, tableContent=
轮心力
Wheel center force
数据集
Data set
预测值损伤
Prediction value damage
真实值损伤
Actual value
damage
损伤相对误差
Relative error of damage/%
Fx训练集
Training set
4.82×10-54.96×10-52.80
测试集
Testing set
2.73×10-53.11×10-512.17
Fy训练集
Training set
5.65×10-76.08×10-76.98
测试集
Testing set
6.95×10-77.90×10-712.00
Fz训练集
Training set
1.71×10-41.76×10-43.14
测试集
Testing set
1.90×10-41.97×10-43.43
Mx训练集
Training set
3.81×10-94.57×10-916.66
测试集
Testing set
6.09×10-96.35×10-94.07
My训练集
Training set
6.17×10-97.10×10-912.99
测试集
Testing set
1.16×10-81.44×10-818.98
Mz训练集
Training set
1.52×10-101.77×10-1013.83
测试集
Testing set
2.97×10-103.20×10-106.94
), ArticleFig(id=1228282213419123130, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1228282191663268510, language=CN, label=表6, caption=

轮心力预测精度

, figureFileSmall=null, figureFileBig=null, tableContent=
轮心力
Wheel center force
数据集
Data set
预测值损伤
Prediction value damage
真实值损伤
Actual value
damage
损伤相对误差
Relative error of damage/%
Fx训练集
Training set
4.82×10-54.96×10-52.80
测试集
Testing set
2.73×10-53.11×10-512.17
Fy训练集
Training set
5.65×10-76.08×10-76.98
测试集
Testing set
6.95×10-77.90×10-712.00
Fz训练集
Training set
1.71×10-41.76×10-43.14
测试集
Testing set
1.90×10-41.97×10-43.43
Mx训练集
Training set
3.81×10-94.57×10-916.66
测试集
Testing set
6.09×10-96.35×10-94.07
My训练集
Training set
6.17×10-97.10×10-912.99
测试集
Testing set
1.16×10-81.44×10-818.98
Mz训练集
Training set
1.52×10-101.77×10-1013.83
测试集
Testing set
2.97×10-103.20×10-106.94
), ArticleFig(id=1228282213486231999, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1228282191663268510, language=EN, label=Tab.7, caption=

Correlation coefficients and coherence coefficients between input channels and six-component forces

, figureFileSmall=null, figureFileBig=null, tableContent=
输入通道
Input channel
相关系数Correlation coefficient相干系数Coherence coefficient
FxFyFzMxMyMzFxFyFzMxMyMz
Acc1@A_X_WC_LF0.06-0.020.110.040.090.050.600.090.140.120.390.20
Acc1@A_Y_WC_LF0.09-0.27-0.02-0.210.02-0.210.130.200.100.120.070.14
Acc1@A_Z_WC_LF0.060.090.210.07-0.01-0.120.120.190.670.260.060.14
Acc1@A_X_WC_RF-0.090.02-0.06-0.020.100.050.060.020.030.030.060.04
Acc1@A_Y_WC_RF0.06-0.19-0.03-0.22-0.01-0.090.040.090.040.070.020.08
Acc1@A_Z_WC_RF-0.040.03-0.030.00-0.010.000.020.030.050.050.030.03
Acc1@A_X_WC_LR-0.090.00-0.02-0.020.100.030.080.050.050.050.050.04
Acc1@A_Y_WC_LR0.05-0.14-0.03-0.150.00-0.140.040.060.070.060.030.05
Acc1@A_Z_WC_LR0.01-0.020.03-0.01-0.010.010.040.060.090.070.020.04
Acc1@A_X_WC_RR-0.090.02-0.030.020.080.030.030.030.020.020.030.02
Acc1@A_Y_WC_RR0.07-0.16-0.02-0.17-0.01-0.120.020.030.030.030.020.03
Acc1@A_Z_WC_RR-0.010.020.000.02-0.01-0.010.010.030.020.020.010.01
Acc2@A_X_CMass0.66-0.080.15-0.03-0.78-0.260.140.040.050.030.100.05
Acc2@A_Y_CMass-0.090.570.180.62-0.060.410.020.110.060.090.010.06
Acc2@A_Z_CMass0.09-0.020.190.03-0.05-0.070.040.040.070.050.030.04
DIS@DIS_LF-0.32-0.16-0.58-0.270.370.090.130.160.560.240.060.14
DIS@DIS_RF-0.400.230.090.260.390.340.020.040.070.050.040.03
DIS@DIS_LR0.29-0.240.24-0.16-0.30-0.270.040.060.090.060.030.04
DIS@DIS_RR0.220.23-0.070.20-0.290.090.010.030.040.030.020.01
), ArticleFig(id=1228282213578506690, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1228282191663268510, language=CN, label=表7, caption=

输入通道与六分力的相关系数与相干系数

, figureFileSmall=null, figureFileBig=null, tableContent=
输入通道
Input channel
相关系数Correlation coefficient相干系数Coherence coefficient
FxFyFzMxMyMzFxFyFzMxMyMz
Acc1@A_X_WC_LF0.06-0.020.110.040.090.050.600.090.140.120.390.20
Acc1@A_Y_WC_LF0.09-0.27-0.02-0.210.02-0.210.130.200.100.120.070.14
Acc1@A_Z_WC_LF0.060.090.210.07-0.01-0.120.120.190.670.260.060.14
Acc1@A_X_WC_RF-0.090.02-0.06-0.020.100.050.060.020.030.030.060.04
Acc1@A_Y_WC_RF0.06-0.19-0.03-0.22-0.01-0.090.040.090.040.070.020.08
Acc1@A_Z_WC_RF-0.040.03-0.030.00-0.010.000.020.030.050.050.030.03
Acc1@A_X_WC_LR-0.090.00-0.02-0.020.100.030.080.050.050.050.050.04
Acc1@A_Y_WC_LR0.05-0.14-0.03-0.150.00-0.140.040.060.070.060.030.05
Acc1@A_Z_WC_LR0.01-0.020.03-0.01-0.010.010.040.060.090.070.020.04
Acc1@A_X_WC_RR-0.090.02-0.030.020.080.030.030.030.020.020.030.02
Acc1@A_Y_WC_RR0.07-0.16-0.02-0.17-0.01-0.120.020.030.030.030.020.03
Acc1@A_Z_WC_RR-0.010.020.000.02-0.01-0.010.010.030.020.020.010.01
Acc2@A_X_CMass0.66-0.080.15-0.03-0.78-0.260.140.040.050.030.100.05
Acc2@A_Y_CMass-0.090.570.180.62-0.060.410.020.110.060.090.010.06
Acc2@A_Z_CMass0.09-0.020.190.03-0.05-0.070.040.040.070.050.030.04
DIS@DIS_LF-0.32-0.16-0.58-0.270.370.090.130.160.560.240.060.14
DIS@DIS_RF-0.400.230.090.260.390.340.020.040.070.050.040.03
DIS@DIS_LR0.29-0.240.24-0.16-0.30-0.270.040.060.090.060.030.04
DIS@DIS_RR0.220.23-0.070.20-0.290.090.010.030.040.030.020.01
), ArticleFig(id=1228282213662392775, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1228282191663268510, language=EN, label=Tab.8, caption=

Wheel center force results predicted by the compressed input channels model

, figureFileSmall=null, figureFileBig=null, tableContent=
轮心力
Wheel center force
决定系数
Determination coefficient R2
均方根误差
RMSE ERMSE
平均绝对误差
MAE EMAE
损伤相对误差
Relative
error of
damage/%
计算时间
Computational time/s
Fx0.898 6360.16250.201.28150.30
Fy0.794 6377.20249.643.29
Fz0.916 8426.07292.917.61
Mx0.832 8125.9982.7715.29
My0.962 468.0648.5913.28
Mz0.825 056.6035.6213.16
), ArticleFig(id=1228282213763056072, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1228282191663268510, language=CN, label=表8, caption=

压缩输入通道模型预测轮心力结果

, figureFileSmall=null, figureFileBig=null, tableContent=
轮心力
Wheel center force
决定系数
Determination coefficient R2
均方根误差
RMSE ERMSE
平均绝对误差
MAE EMAE
损伤相对误差
Relative
error of
damage/%
计算时间
Computational time/s
Fx0.898 6360.16250.201.28150.30
Fy0.794 6377.20249.643.29
Fz0.916 8426.07292.917.61
Mx0.832 8125.9982.7715.29
My0.962 468.0648.5913.28
Mz0.825 056.6035.6213.16
), ArticleFig(id=1228282213914051022, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1228282191663268510, language=EN, label=Tab.9, caption=

Wheel center force accuracy predicted by minimum dataset model

, figureFileSmall=null, figureFileBig=null, tableContent=
数据集
Data set
轮心力
Wheel center force
决定系数
Coefficient of determination R2
均方根误差
RMSE ERMSE
平均绝对误差
MAE EMAE
损伤相对误差
Relative
error of
damage/%
计算时间
Computational time/s
原始行驶路线
Original driving route
Fx0.879 6392.57261.898.03132.33
Fy0.746 4419.122680.51
Fz0.912 1438.13293.8017.25
Mx0.793 3110.9590.878.51
My0.958 271.7753.1218.18
Mz0.793 661.4836.728.46
随机行驶路线1
Random driving route 1
Fx0.880 0391.94261.79-6.74134.23
Fy0.746 6419.06268.074.13
Fz0.912 0438.26300.7817.25
Mx0.793 5140.0590.866.14
My0.958 671.4353.1018.75
Mz0.793 461.5136.745.53
随机行驶路线2
Random driving route 2
Fx0.878 7394.03262.625.77135.41
Fy0.745 6419.83268.212.44
Fz0.911 6439.48301.1816.75
Mx0.792 9140.2490.8910.26
My0.956 373.3853.4318.49
Mz0.792 161.7036.808.54
随机行驶路线3
Random driving route 3
Fx0.878 6394.23262.584.93137.02
Fy0.746 4419.26268.211.62
Fz0.911 4439.76301.2517.17
Mx0.793 3140.1390.923.19
My0.955 873.8753.4418.05
Mz0.792 961.5936.79-14.19
), ArticleFig(id=1228282214035685843, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1228282191663268510, language=CN, label=表9, caption=

最小数据集模型预测轮心力精度

, figureFileSmall=null, figureFileBig=null, tableContent=
数据集
Data set
轮心力
Wheel center force
决定系数
Coefficient of determination R2
均方根误差
RMSE ERMSE
平均绝对误差
MAE EMAE
损伤相对误差
Relative
error of
damage/%
计算时间
Computational time/s
原始行驶路线
Original driving route
Fx0.879 6392.57261.898.03132.33
Fy0.746 4419.122680.51
Fz0.912 1438.13293.8017.25
Mx0.793 3110.9590.878.51
My0.958 271.7753.1218.18
Mz0.793 661.4836.728.46
随机行驶路线1
Random driving route 1
Fx0.880 0391.94261.79-6.74134.23
Fy0.746 6419.06268.074.13
Fz0.912 0438.26300.7817.25
Mx0.793 5140.0590.866.14
My0.958 671.4353.1018.75
Mz0.793 461.5136.745.53
随机行驶路线2
Random driving route 2
Fx0.878 7394.03262.625.77135.41
Fy0.745 6419.83268.212.44
Fz0.911 6439.48301.1816.75
Mx0.792 9140.2490.8910.26
My0.956 373.3853.4318.49
Mz0.792 161.7036.808.54
随机行驶路线3
Random driving route 3
Fx0.878 6394.23262.584.93137.02
Fy0.746 4419.26268.211.62
Fz0.911 4439.76301.2517.17
Mx0.793 3140.1390.923.19
My0.955 873.8753.4418.05
Mz0.792 961.5936.79-14.19
)], attaches=null, journal=Journal(id=1227999351742652416, delFlag=0, nameCn=机械强度, nameEn=Journal of Mechanical Strength, nameHistory1=null, nameHistory2=null, issn=1001-9669, eissn=null, cn=41-1134/TH, coden=null, periodic=0, 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=9ETNXOzwmuGm49pLRqXxWw==, journalPrice=null, startedYear=null, abbrevIsoEn=Journal of Mechanical Strength, journalRemark=null, publicationField=null, createdTime=1770707460585, updatedTime=1770707700588, createdBy=18614031015, updatedBy=13701087609, firstLetterCn=J, firstLetterEn=J, subjectCode=Engineering, subjectName=null, subjectCodeEn=Engineering, subjectNameEn=null, picCn=9ETNXOzwmuGm49pLRqXxWw==, picEn=sS2ogjwdwM8GMbFtuWTIkA==, jcr=null, cjcr=null, exts=[JournalExt(id=1228000358505578506, language=CN, name=机械强度, 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=1770707700611, updatedTime=1770707700611, createdBy=13701087609, updatedBy=13701087609, submissionGuidelinesUrl=, submissionAuthorUrl=https://journal.ids.fzyun.cn/auth/realms/journal/protocol/openid-connect/auth?client_id=journal-jxqd-author&redirect_uri=https%3A%2F%2Fjxqd.portal.founderss.cn%2Foauth%2Fcallback&response_type=code&scope=phone+openid+email+profile&state=aa1eff81-489d-4951, submissionEditorUrl=https://journal.ids.fzyun.cn/auth/realms/journal/protocol/openid-connect/auth?client_id=journal-portal&redirect_uri=https%3A%2F%2Fjournal.portal.founderss.cn%2Foauth%2Fcallback&response_type=code&scope=phone+openid+email+profile&state=df5d5e38-1d45-4fcd-b, submissionReviewUrl=https://journal.ids.fzyun.cn/auth/realms/journal/protocol/openid-connect/auth?client_id=journal-jxqd-author&redirect_uri=https%3A%2F%2Fjxqd.portal.founderss.cn%2Foauth%2Fcallback&response_type=code&scope=phone+openid+email+profile&state=49f73d27-439e-4d5b, submissionCeEditorUrl=, submissionAeEditorUrl=, option={"copyright":""}), JournalExt(id=1228000358551715851, language=EN, name=Journal of Mechanical Strength, 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=1770707700622, updatedTime=1770707700622, createdBy=13701087609, updatedBy=13701087609, submissionGuidelinesUrl=, submissionAuthorUrl=https://journal.ids.fzyun.cn/auth/realms/journal/protocol/openid-connect/auth?client_id=journal-jxqd-author&redirect_uri=https%3A%2F%2Fjxqd.portal.founderss.cn%2Foauth%2Fcallback&response_type=code&scope=phone+openid+email+profile&state=aa1eff81-489d-4951, submissionEditorUrl=https://journal.ids.fzyun.cn/auth/realms/journal/protocol/openid-connect/auth?client_id=journal-portal&redirect_uri=https%3A%2F%2Fjournal.portal.founderss.cn%2Foauth%2Fcallback&response_type=code&scope=phone+openid+email+profile&state=df5d5e38-1d45-4fcd-b, submissionReviewUrl=https://journal.ids.fzyun.cn/auth/realms/journal/protocol/openid-connect/auth?client_id=journal-jxqd-author&redirect_uri=https%3A%2F%2Fjxqd.portal.founderss.cn%2Foauth%2Fcallback&response_type=code&scope=phone+openid+email+profile&state=49f73d27-439e-4d5b, submissionCeEditorUrl=, submissionAeEditorUrl=, option={"copyright":""})], databaseList=null, tenantJournalId=1227999626482147330, websiteList=[Website(id=1228000871984853626, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1227999626482147330, 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/jxqd/CN, language=CN, createTime=1770707823034, createBy=18614031015, updateTime=1770707851936, updateBy=18614031015, name=机械强度-中文, tplId=1146099689490845704, title=机械强度, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1228001259580486284, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1228000871984853626, code=articleTextType, value=kx, createTime=1770707915444, updateTime=1770707915444, creator=18614031015, updator=18614031015), WebsiteProps(id=1228001259555320457, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1228000871984853626, code=banner, value=null, createTime=1770707915438, updateTime=1770707915438, creator=18614031015, updator=18614031015), WebsiteProps(id=1228001259605652111, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1228000871984853626, code=grayFlag, value=0, createTime=1770707915450, updateTime=1770707915450, creator=18614031015, updator=18614031015), WebsiteProps(id=1228001259542737544, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1228000871984853626, code=logo, value=https://castjournals.cast.org.cn/joweb/jxqd/CN/file/pic?fileId=wrginrTxTIens2Yn6gXaKA==, createTime=1770707915435, updateTime=1770707915435, creator=18614031015, updator=18614031015), WebsiteProps(id=1228001259622429329, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1228000871984853626, code=minRunFlag, value=0, createTime=1770707915454, updateTime=1770707915454, creator=18614031015, updator=18614031015), WebsiteProps(id=1228001259572097675, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1228000871984853626, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/jxqd/CN/file/pic, createTime=1770707915442, updateTime=1770707915442, creator=18614031015, updator=18614031015), WebsiteProps(id=1228001259614040720, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1228000871984853626, code=silenceFlag, value=0, createTime=1770707915452, updateTime=1770707915452, creator=18614031015, updator=18614031015), WebsiteProps(id=1228001259567903370, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1228000871984853626, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_cn_619/, createTime=1770707915441, updateTime=1770707915441, creator=18614031015, updator=18614031015), WebsiteProps(id=1228001259588874893, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1228000871984853626, code=themeColor, value=null, createTime=1770707915446, updateTime=1770707915446, creator=18614031015, updator=18614031015), WebsiteProps(id=1228001259597263502, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1228000871984853626, code=themeStyle, value=null, createTime=1770707915448, updateTime=1770707915448, creator=18614031015, updator=18614031015)]), Website(id=1228000872056156796, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1227999626482147330, 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/jxqd/EN, language=EN, createTime=1770707823051, createBy=18614031015, updateTime=1770707871019, updateBy=18614031015, name=机械强度-英文, tplId=1146101810881728533, title=Journal of Mechanical Strength, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1228001314525868694, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1228000872056156796, code=articleTextType, value=kx, createTime=1770707928544, updateTime=1770707928544, creator=18614031015, updator=18614031015), WebsiteProps(id=1228001314504897171, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1228000872056156796, code=banner, value=null, createTime=1770707928539, updateTime=1770707928539, creator=18614031015, updator=18614031015), WebsiteProps(id=1228001314542645913, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1228000872056156796, code=grayFlag, value=0, createTime=1770707928548, updateTime=1770707928548, creator=18614031015, updator=18614031015), WebsiteProps(id=1228001314496508562, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1228000872056156796, code=logo, value=https://castjournals.cast.org.cn/joweb/jxqd/EN/file/pic?fileId=wrginrTxTIens2Yn6gXaKA==, createTime=1770707928537, updateTime=1770707928537, creator=18614031015, updator=18614031015), WebsiteProps(id=1228001314555228827, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1228000872056156796, code=minRunFlag, value=0, createTime=1770707928551, updateTime=1770707928551, creator=18614031015, updator=18614031015), WebsiteProps(id=1228001314517480085, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1228000872056156796, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/jxqd/EN/file/pic, createTime=1770707928542, updateTime=1770707928542, creator=18614031015, updator=18614031015), WebsiteProps(id=1228001314551034522, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1228000872056156796, code=silenceFlag, value=0, createTime=1770707928550, updateTime=1770707928550, creator=18614031015, updator=18614031015), WebsiteProps(id=1228001314513285780, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1228000872056156796, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_en_623/, createTime=1770707928541, updateTime=1770707928541, creator=18614031015, updator=18614031015), WebsiteProps(id=1228001314530062999, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1228000872056156796, code=themeColor, value=null, createTime=1770707928545, updateTime=1770707928545, creator=18614031015, updator=18614031015), WebsiteProps(id=1228001314538451608, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1228000872056156796, code=themeStyle, value=null, createTime=1770707928547, updateTime=1770707928547, creator=18614031015, updator=18614031015)])], journalTitle=机械强度, weixinUrl=null, journalUrl=https://www.jxqd.net.cn/, iacademicId=null, status=1, seqNo=null, journalTitleEn=Journal of Mechanical Strength, journalPhotoCn=9ETNXOzwmuGm49pLRqXxWw==, journalPhotoEn=sS2ogjwdwM8GMbFtuWTIkA==, journalFirstLetter=J, 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/jxqd/CN/10.16579/j.issn.1001.9669.2025.10.001, detailUrlEn=https://castjournals.cast.org.cn/joweb/jxqd/EN/10.16579/j.issn.1001.9669.2025.10.001, pdfUrlCn=https://castjournals.cast.org.cn/joweb/jxqd/CN/PDF/10.16579/j.issn.1001.9669.2025.10.001, pdfUrlEn=https://castjournals.cast.org.cn/joweb/jxqd/EN/PDF/10.16579/j.issn.1001.9669.2025.10.001, aliStartDate=null, aliEndDate=null, collectionFlag=false, citedCount=null, citedUrl=null, reference=null)
收藏切换
数据驱动的整车道路载荷快速预测方法
收藏切换
PDF下载
冯金芝 1, 2, 3 , 李增宏 1 , 张东东 1, 2, 3 , 刘东俭 4 , 赵礼辉 1, 2, 3
机械强度 | 振动·噪声·监测·诊断 2025,47(10): 1-15
收起
收藏切换
机械强度 | 振动·噪声·监测·诊断 2025, 47(10): 1-15
数据驱动的整车道路载荷快速预测方法
全屏
冯金芝1, 2, 3 , 李增宏1, 张东东1, 2, 3, 刘东俭4, 赵礼辉1, 2, 3
作者信息
  • 1.上海理工大学 机械工程学院,上海 200093
  • 2.机械工业汽车机械零部件强度与可靠性评价重点实验室,上海 200093
  • 3.上海市新能源汽车可靠性评价专业技术服务平台,上海 200093
  • 4.中汽研汽车试验场股份有限公司,盐城 224100
  • 冯金芝,女,1973年生,山东诸城人,博士,副教授,硕士研究生导师;主要研究方向为现代汽车设计理论;E-mail:

通讯作者:

赵礼辉,男,1985年生,山东青岛人,博士,副教授,硕士研究生导师;主要研究方向为车辆强度可靠性设计与评价、车辆载荷特征建模与快速试验;E-mail:
Data-driven method for rapid prediction of vehicle road load
Jinzhi FENG1, 2, 3 , Zenghong LI1, Dongdong ZHANG1, 2, 3, Dongjian LIU4, Lihui ZHAO1, 2, 3
Affiliations
  • 1.School of Mechanical Engineering, University of Shanghai for Science and Technology, Shanghai 200093, China
  • 2.CMIF Key Laboratory for Strength and Reliability Evaluation of Automotive Structures, Shanghai 200093, China
  • 3.Shanghai Technical Service Platform for Reliability Evaluation of New Energy Vehicles, Shanghai 200093, China
  • 4.CATARC Automotive Proving Ground Co., Ltd., Yancheng 224100, China
出版时间: 2025-10-15 doi: 10.16579/j.issn.1001.9669.2025.10.001
文章导航
收藏切换

车辆与路面间相互作用力中的车轮六分力是车路间的唯一耦合,获取车轮六分力是开展整车可靠性与耐久性评价的关键。针对传统的车轮六分力获取方法成本高、周期长、效率低的问题,提出数据驱动的车轮载荷快速预测的方法。首先,针对实车道路非平稳随机信号,采用基于自适应噪声完备集合经验模态分解(Complete Ensemble Empirical Mode Decomposition with Adaptive Noise, CEEMDAN)、排列熵(Permutation Entropy, PE)以及小波阈值降噪(Wavelet Threshold Denoising, WTD)的联合方法进行数据去噪;其次,以轮心加速度、减振器位移、质心加速度等容易获取且获取成本低的数据为输入,设计包含非线性传递关系的不同神经网络架构进行多路面下车轮六分力预测,并建立时域、频域、损伤域多维度载荷预测评估体系;最后,为克服训练样本大且获取代价高的缺点,提出基于神经网络输入与输出相关性-相干性分析的输入通道压缩方法,提出最小载荷信号片段划分指标并确定各路面最小片段时长,进行训练集压缩。经过模型不断迭代,车轮六分力的预测值与实测值较为接近,载荷特征也得以保留,计算效率提高28.85%,证明了最小数据集模型能够以较少的输入通道数量、较短的载荷片段时长复现较高期望的预测精度。

轮心六分力  /  载荷预测  /  神经网络  /  损伤评估  /  疲劳耐久分析

The six-component forces at the wheel-road interaction represent the sole coupling between the vehicle and the road surface, and obtaining these forces is critical for conducting reliability and durability assessments of the entire vehicle. In response to the high cost, long cycle, and low efficiency associated with traditional methods for obtaining wheel six-component forces, a data-driven approach for rapidly predicting wheel loads was proposed. Firstly, for the non-stationary random signals on real vehicle roads, a joint method of the complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN), permutation entropy (PE), and wavelet threshold denoising (WTD) was applied for the data denoising.Secondly, the easily obtainable and low-cost data, such as wheel center acceleration, damper displacement, and center of mass acceleration, were used as inputs. Various neural network architectures with nonlinear transfer relationships were designed for multi-surface wheel six-component force prediction. A multi-dimensional load prediction evaluation system was established in the time domain, frequency domain, and damage domain. Finally, in order to overcome the challenges of a large and costly training dataset, an input channel compression method based on the correlation and coherence analysis of neural network inputs and outputs was proposed. Minimum load signal segment division criteria were introduced, and the minimum segment duration for each road surface was determined to compress the training dataset. Through continuous model iterations, the predicted values of the wheel six-component forces closely match the measured values, and the load characteristics are preserved. This demonstrates that the minimal dataset model can achieve a high level of prediction accuracy with fewer input channels and shorter load segment durations, resulting in a 28.85% improvement in computational efficiency.

Six-component force of the wheel center  /  Load prediction  /  Neural network  /  Damage assessment  /  Fatigue durability analysis
冯金芝, 李增宏, 张东东, 刘东俭, 赵礼辉. 数据驱动的整车道路载荷快速预测方法. 机械强度, 2025 , 47 (10) : 1 -15 . DOI: 10.16579/j.issn.1001.9669.2025.10.001
Jinzhi FENG, Zenghong LI, Dongdong ZHANG, Dongjian LIU, Lihui ZHAO. Data-driven method for rapid prediction of vehicle road load[J]. Journal of Mechanical Strength, 2025 , 47 (10) : 1 -15 . DOI: 10.16579/j.issn.1001.9669.2025.10.001
汽车实际行驶过程所处环境复杂,承受载荷多,而车轮作为支撑车重、获取地面作用力、调节车辆行驶性能的重要部件,其六分力对整车及零部件的可靠性和耐久性开发非常重要。车轮六分力作为耐久性分析最重要的基本数据,其准确快速获取能缩短试验周期、提高开发效率、降低开发成本。目前车轮六分力的获取方法有3类。第1类是试验场道路载荷实车采集的方法[1-4],如徐春[5]通过制定试验场道路载荷采集方案,为采集试验场整车数据提供了参考。由于采集前期需要零件拆解、装车调试、应变片传感器制作、传感器安装和线缆布置等工作,耗费大量人力物力,而且专用六分力采集传感器价格昂贵,研发成本高。第2类是通过虚拟试验场技术建立多体动力学模型进行载荷虚拟迭代,如王超[6]针对三维路面建模困难,提出“人-车-路”虚拟试验场系统,通过仿真提取了车轮六分力,这在一定程度上缩短了试验周期。这两种方法是基于试验场道路实施的,试验场环境相对封闭,对便于安装各类传感器的车辆进行试验,而且试验场路面可用激光扫描技术进行虚拟路面建模。但对于用户道路实车采集,安装的各类传感器会限制车辆全方位的试验,甚至无法上路;对于数字路面,用户道路随机扫描建模难度大。而第3类是在载荷预测领域运用比较活跃的机器学习方法,借助部分实测数据对目标载荷进行预测,其本质上是通过机器学习找到输入与输出的复杂映射关系。在载荷预测方面,李荣强等[7]基于飞机的飞行数据,建立XGBoost、随机森林、反向传播(Back Propagation, BP)神经网络等机器学习模型对飞机左起落架垂向载荷进行预测研究,验证了XGBoost模型的优越性。牟哲岳等[8]通过Pearson相关系数评价机组状态数据、气象数据与机组载荷之间的相关性,采用极端随机森林算法建立风电机组载荷预测模型,对机组载荷进行了预测。杨博文等[9]基于当前已有数据,建立了概率密度参数外推法载荷预测模型,并结合机器学习BP神经网络对全断面硬岩隧道掘进机(Tunnel Boring Machine, TBM)主机系统关键部件超前载荷谱进行预测。而在车轮六分力获取方面,罗欢等[10]以车型数据库建立深度卷积神经网络-长短期记忆(Deep Convolutional Neural Network-Long Short Term Memory, DCNN-LSTM)神经网络,以转向盘转角、整车形式、悬架形式等为输入,在特定场景下实现了轮心力预测并以决定系数R2、平均绝对误差(Mean Absolute Error, MAE)与均方误差(Mean Square Error,MSE)的比值评价了神经网络模型的可用性。WANG等[11]通过离线训练一组有限脉冲响应模型,利用最大似然估计分类器确定车辆当前所处的工况,从而估计车轮垂向轮心力,该方法在公共道路、街区道路实现了车轮垂向力预测。
已有研究证实了基于机器学习的数据驱动方法在载荷预测方面的可行性。在整车道路载荷预测研究上仍需进一步完善,如数据前处理工作繁杂,载荷预测评价指标单一,预测模型适用路面类型少;普适性强、精度高的驱动模型往往依赖大量的训练样本,而大量训练样本可能导致模型复杂度提升等。
综上所述,通过试验场载荷谱采集获取轮心力的方法周期长、成本高;虚拟迭代技术受限于实车行驶道路的随机性;基于部分已有数据预测轮心载荷的方法难以广泛适用于多种路面特征,这使得以车轮六分力为基础数据对整车及零部件的可靠性与耐久性开发不尽如人意。
为此,本文提出数据驱动的整车道路载荷快速预测方法,以乘用车四车轮为主要研究载体,以左前轮为主要预测对象,将加速度、减振器位移等易于获得的数据作为输入,进行左前轮多路况车轮六分力预测,并对比几种非线性网络的预测精度。同时构建载荷预测多维度评价体系,将预测载荷与实测值进行时域、频域、损伤域多维度的对比,对比分析表明轮心垂向力预测精度最高,其他分力也具有较高的精度且相对损伤误差均在20%以内,验证了该模型(记为初始模型)对多路面类型的普适性;并进一步分析输入载荷特征与输出载荷特征的时域相关性与频域相干性,将输入特征数量压缩后继续训练模型(记为压缩输入通道模型)预测六分力。最后,在压缩输入通道模型的基础上,将基于加速度、位移等载荷信号提取的原始载荷片段与划分后载荷片段的频域拟合程度参数及两片段的平均相对距离之和(P-value, P)等作为载荷谱最小片段划分的依据,通过压缩各路况时长,实现以最小数据集所训练的模型(记为最小数据集模型)复现初始模型的预测精度,且计算效率得到提升。这有助于实时快速预测局部危险部位载荷、提高损伤评估效率。
由于实车行驶路面随机、复杂,而典型试验场道路是提取50多种社会用户道路的优化组合,覆盖面广。因此,为实现神经网络对车轮六分力(xyz 3个方向的力和力矩)精准预测,进行试验场道路载荷采集。考虑到数据驱动模型预测精度与输入通道特征相关,采集信号主要包括轮心六分力、减振器位移,以及轮心、轴头、车身的三向加速度信号等。道路类型主要涉及石块路、卵石路、扭曲路、锯齿路、砂石路等32种。试验车辆为乘用车,传感器布置及行驶路线如图1所示。试验工况为满载2.73 t,在T8跑道上进行3次循环试验,以消除驾驶习惯、突发情况等造成的数据差异。而为保证载荷信号采集完整,采样频率一般较高,采样频率为512 Hz。其中,3次试验循环时间分别为678、710、700 s。图2为道路载荷采集卫星图,图3为前两次试验循环载荷信号。
对采集数据进行时间历程、载荷幅值分布、功率谱密度(Power Spectral Density, PSD)和雨流计数等载荷特征的对比分析。如图4所示,以左前轮垂向加速度为例,将3次循环试验中的过渡路段一致化,各通道载荷信号在时间历程上均完整,幅值范围基本一致,没有数据缺失通道;在PSD上,载荷信号的能量分布主要集中在20 Hz以内,符合预期;在幅值分布上,载荷数据在路面不平度激励下产生随机振动响应,均基本符合高斯正态分布规律;载荷幅值分布和雨流计数结果是损伤等效计算的重要影响因素,3次试验循环载荷信号的幅值分布和雨流计数基本一致,进一步验证了本次采集数据的有效性。
由于采样频率较高,神经网络数据集样本量庞大。理论上,大量数据会使神经网络的泛化能力和训练效果得到提升,但增加了训练时间、内存消耗以及数据预处理的复杂性,因此对数据进行重采样。以左前轮减振器位移为例,为尽可能降低采样频率且重采样后的信号能保留原始信号95%以上的伪损伤,分别取采样频率为256、100、50、25 Hz进行重采样。重采样前、后的时域载荷信号局部放大对比如图5所示。随着采样频率的降低,信号失真程度加剧,且主要出现在峰谷值部位,而伪损伤的贡献率主要是峰谷值载荷提供的。进一步计算256、100、50、25 Hz损伤复现比,结果如表1所示。在满足95%伪损伤复现比的前提下,选用尽可能低的采样频率,因此本文采样频率为100 Hz。
车辆行驶过程中车速、路面不平度的变化导致载荷是非平稳的随机信号,且采集设备的可靠性和采集环境都会对采集信号的质量造成影响。为明确采集信号中是否有噪声,首先采用自适应噪声完备集合经验模态分解(Complete Ensemble Empirical Mode Decomposition with Adaptive Noise, CEEMDAN)技术对载荷信号进行模态分解,得到各个本征模态函数(Intrinsic Mode Functions, IMF)分量;其次计算各个IMF分量的排列熵(Permutation Entropy, PE)值[12-13];进而根据噪声PE值大的特点对含噪信号进行筛选,并对含噪信号进行小波阈值降噪(Wavekt Threshold Denoising, WTD);最后将纯净信号和小波降噪后的信号进行重构,得到降噪后的信号。以路况较为复杂的卵石路垂向力Fz为例,对其进行CEEMDAN,其原始信号及各IMF分量如图6所示,各个分量的PE值如表2所示。
通过CEEMDAN得到13个IMF分量和1个残差项,对这些分量分别计算PE值,PE值越大的IMF分量噪声信号越多,反之PE值小的IMF分量纯净信号越多。PE的算法如下:
1)对一时间序列长度为n的信号X={xii=1、2、…、n}进行相空间重构,得到矩阵为
式中,r为嵌入维数;τ为时间延迟;k为重构分量的个数。
2)将Y中的每一行看作1个重构分量,对每个重构分量的各个元素按照升序重新排列,如果出现数值相同的元素,则按照索引顺序排列。对Y的第m个分量{xmxm+τ) … x[m +(r-1)τ]}进行排序,即有索引序列:
式中,l=1、2、3、…、LLr!;xm)为重构矩阵的第m行分量。
3)若维度为r的相空间一共有r!种符号序列,计算每一个序列的概率,记为Pg,则序列X的PE为
式中,Hpr)最大值是ln(r!),此时Pg=1/r!。将Hpr)归一化后有
式中,rτ的一般取值范围分别为3~7与1~8。如果r过大,在捕捉时间序列复杂结构的同时增加了计算复杂度,r过小会导致重构矩阵中的状态丢失,使PE算法无效[14];在相同嵌入维度下,τ对PE值的影响较小[15]。而高斯白噪声的PE值基本在0.9以上[16-17],建议PE阈值的范围为0.55~0.60[18-19],结合车辆实际行驶时会产生随机噪声的特点,本文取r=6,τ=1,PE阈值为0.6。将PE值大于0.6的IMF分量进行小波阈值降噪,根据本文载荷信号特征,选取“db4”为小波基函数,阈值计算方法选择固定阈值方法[20],分解层数为2。表3为不同阈值规则的计算结果。图7(a)为原始载荷信号与降噪后信号的对比。由图7(b)可知,损伤贡献在20 Hz以内。而图7(c)中该频段内降噪数据与原始数据基本一致,20~50 Hz频段带噪信息得到明显减少,因此去噪效果良好。
汽车实际行驶时,车轮载荷变化复杂、非线性较高,传统自回归线性模型结构简单,预测此类时序数据存在局限性。对于时序数据预测,往往要考虑不同时间维度之间的依赖关系,而长短期记忆(Long Short-Term Memory, LSTM)神经网络基于遗忘门、输入门、输出门对输入信息记忆或遗忘,能够提取长序列之间的关联关系。因此,基于多维度输入时序特征,采用LSTM神经网络,针对输入载荷特征构建一个最优车轮六分力预测方法。其中,遗忘门的输入是当前t时刻的xt和前一时刻的Ct-1,对历史信息进行筛选并抛弃不重要的信息;输入门是决定输入中的哪些值需要更新记忆状态,并通过传入tanh函数中的历史信息和当前信息生成1个候选值͂,之后进行候选值的更新;输出门是根据输入和记忆状态决定输出的值,将前一个隐藏状态ht-1和当前输入xt传递到sigmoid函数中得到ot,最后将t时刻tanh的输出与sigmoid的输出相乘得到最终的输出。LSTM神经网络的输出过程为
式中,ftt时刻的遗忘门;itt时刻的输入门;t时刻的候选值;Ctt时刻的单元状态;Ct-1t-1时刻的单元状态;ott时刻的输出门的输出;htt时刻的最终输出值;ht-1t-1时刻的最终输出值;W代表各权重;b代表各偏置;σ为sigmoid函数。LSTM神经网络的结构如图8所示。
将前2次试验循环数据分别作为训练集、测试集,神经网络的初始输入通道是16个,分别为四车轮的减振器位移以及4个轮心三向加速度,预测车轮六分力,即FxFyFzMxMyMz。在上文中已经对数据集进行了去噪处理,还需要进一步对数据集进行归一化处理,以消除因数据间数量级相差很大而对训练过程产生的过拟合或者不稳定。由于数据集庞大,使用传统或改进的优化算法需要大量的算力与时间,所以使用顺序优化方法从对神经网络影响最大的参数开始,逐一确定各个参数,并总结LSTM神经网络不同参数对预测效果的影响。将R2、均方根误差(Root Mean Square Error, RMSE)、MAE作为评价神经网络预测拟合程度的指标,其表达式为
式中,y为神经网络输入的真实值;为神经网络输出的预测值;为神经网络输入真实值的均值;n为样本量。不同试验结果如表4所示,并总结不同结构参数对神经网络预测精度的影响。
表4中的1~5号试验结果可知,学习率决定了权重更新的幅度,较大的学习率可以加快收敛速度。然而,过大的学习率可能导致训练过程不稳定,错过全局最优解。较小的学习率会减缓收敛速度,但更稳定。由6~10号试验结果可知,隐藏层节点数的增加可以提高神经网络的预测能力,但也会增加神经网络的过拟合风险。通常当训练数据较少时,较少的隐藏层节点数可以更好地应对过拟合问题。当训练数据较大时,增加隐藏层节点数可以提高神经网络的学习能力。因此,需要根据训练数据的规模和复杂性来平衡隐藏层节点数的选择。由11~15号试验结果可知,增加迭代次数可以使神经网络更充分地学习训练数据中的模式和关系,有助于提高模型的收敛性。通过更多的迭代次数,神经网络可以逐渐减小训练误差并接近最优解。然而过多的迭代次数可能导致过拟合问题,即在训练数据上表现良好但在未见过的数据上表现较差。由16~20号试验结果可知,数据批量偏小会引入更多的随机性,偏大可能会更好地利用批次内样本之间的统计信息,从而提高训练的稳定性和泛化能力,但如果数据批量过大,可能导致模型过于依赖批次内的样本之间的相关性,从而降低了模型的泛化能力。由21~25号试验结果可知,较长的时间步长可以提供更长的历史信息窗口,使神经网络能够更好地捕捉时间序列数据中的长期依赖关系。然而如果时间步长过长,会降低网络对数据全部信息特征的获取精度。
通过上述训练结果,最终确定以下网络结构参数:1个输入层,1个隐藏层,80个神经元,激活函数为ReLU,迭代次数为200,批量大小为1 024,学习率为0.01,添加0.001的Dropout层,损失函数为MSE,优化器选择Adam。
为避免单一神经网络的局限性,选择既有普适性又有高精度的神经网络模型,构建并对比LSTM、LSTM融合多头注意力机制[21]、LSTM融合多头结构、带有外部输入的非线性自回归(Nonlinear Auto-Regressive with Exogenous Inputs, NARX)神经网络、反向传播、多层感知机(Multilayer Perceptron, MLP)等多路况六分力的预测模型[22-24]。通过决定系数、均方根误差以及绝对平均误差初步判断预测模型的精度,表5所示为不同数据模型的六分力预测精度及效率。
在预测精度上,BP神经网络除Fz外,其余分力预测精度均在76%以上;MLP神经网络除FzMx外,其余分力预测精度均在66%以上;NARX神经网络除My外,其余分力预测精度均在67%以上;LSTM神经网络六分力预测精度均在79%以上。
在预测效率上,LSTM与NARX数据模型在非线性动态载荷预测上的优势较大,计算效率高;而LSTM-自注意力机制模型以及LSTM-多头注意力机制模型,由于添加了注意力机制结构,整体模型较复杂,计算效率及精度有所降低。综合车轮六分力预测精度、效率以及稳定性表现,LSTM神经网络是最优的。因此选择LSTM神经网络对车轮六分力的预测进行深入研究。
将上文得到的LSTM神经网络模型记为初始模型,3个评价指标在可接受范围内,但是其预测的载荷是否符合工程要求仍需要比较原始载荷与预测载荷的时间历程趋势、功率谱密度和损伤域的相对误差。因此建立载荷预测多维度评价体系,同时为确保上述训练过程的正确性以及训练模型的稳定性,将每次最佳参数的神经网络进行多次训练预测,避免偶然性。
图9为神经网络训练误差,图10为预测载荷与真实载荷在时域历程上的对比。在六分力预测上,预测模型对于Fz的拟合程度比较高,波形趋势基本一致,基本没有突起载荷;而对于其他分力预测,在峰值上的预测载荷与真实载荷存在微小误差。在各个路况上,对于石块路和卵石路等载荷随机的路况预测效果稍有不足,而对于扭曲路和振动路等具有载荷规律性的路况预测效果较好。从整体上看,时域预测效果较好,与各自的决定系数和均方根误差能够相互体现。
PSD是对时域信号进行傅里叶变换转换成频域信号,描述信号在频域上的功率分布的度量。而在汽车实际行驶过程中,车辆经常面临的是低频振动和冲击载荷,如路面不平、起伏、过坑、过凸起等,汽车整车或零部件的耐久性评价主要关注能量集中的0~20 Hz主频带内的分布情况。如图11所示,只有预测的My在13~20 Hz的预测值PSD偏高,其余分力主频带基本吻合;而在34~42 Hz,FyMx预测的PSD偏低,但都在一个数量级内,预测载荷与真实载荷在频域上的分布特征基本一致。
预测载荷与真实载荷在时域和频域上较相符的情况下,还需要进一步确认预测载荷的伪损伤是否能够复现80%以上的真实载荷的伪损伤。Miner线性累积损伤理论常用于损伤评估与寿命预测中。一个循环载荷的总损伤计算式为
式中,D为总损伤;Ni为第i个载荷作用下的疲劳寿命[25]表6为真实载荷与预测载荷的伪损伤及损伤相对误差。损伤相对误差计算式为
图12为预测载荷与真实载荷在雨流矩阵上的对比。由图12可知,FxFyFzMxMyMz预测的大幅值载荷比真实载荷少,而预测的小幅值载荷与真实载荷相当,使得预测载荷损伤小于真实载荷;从总体来看,轮心六分力的损伤相对误差都在20%以内,在可接受范围内。
根据构建的多维度评价体系,对NARX神经网络与LSTM神经网络进行垂向力预测对比分析,如图13所示。由上文知,NARX神经网络模型的3个评价指标均要优于LSTM,从整体时频域上两者预测效果相当,而LSTM在峰值预测上略优于NARX;同时NARX预测载荷的损伤值为1.85×10-4,其损伤略小于LSTM预测的载荷损伤,损伤相对误差为6.09%。因此,对于整车道路载荷预测,其预测精度是否准确并不能绝对依赖于神经网络的回归指标,仍需要判别其载荷损伤特征是否能够满足工程要求。
通过上文研究得出多道路形式的最优车轮六分力预测模型,但是数据集样本量较为庞大。考虑到对车轮六分力的快速预测,期望能够以较小的数据集复现初始预测模型的精度。因此,基于神经网络输入与输出的时域相关性与频域相干性进行输入通道压缩;提出最小载荷信号片段划分指标,并以此确定各路面最小片段时长,从而得到压缩后的数据集。
初始输入通道是根据车载传感器的安装数量确定的,并且经过训练评估验证了初始模型的可用性。为确定哪些输入通道与左前轮轮心六分力有强相关性,求解四轮三向加速度、减振器位移、3个整车质心加速度与六分力各通道的相关系数和相干系数,结果如表7所示。表7中相关系数结果表明,六分力与四轮减振器位移有较强相关性,也与各自所在方向的质心加速度有关。而由相干性结果可知,六分力与左前轮三向加速度、减振器位移以及各自所在方向的质心加速度有关。综合相关、相干系数,输入通道取左前轮三向加速度、左前轮减振器位移以及相关最大方向的质心加速度,共5个输入通道。
根据选取的5个输入通道数据进行模型训练,该模型为压缩输入通道模型,预测结果如表8所示。由表8可知,与初始模型的神经网络评价指标相比,计算效率提高19.19%;FxMyMz预测精度较高,FyFzMx精度偏低。其中,除Fz外,其余分力的16个输入通道与六分力的相关系数之和有所增大;压缩后5个输入通道与FyMx的相关系数中为负值的占比较大,而My与16个输入通道的相关系数之和负值较大。因此,解释了压缩输入通道模型所预测六分力的精度提升或下降。同时综合整体损伤相对误差,误差大小均低于20%,符合工程需要,能够复现期望的预测精度。
为了以较小的数据集实现较优的预测效果,减少样本量,提高耐久性分析效率,需要进一步确定某个路况的某个片段时长为多少时,方可通过神经网络预测出其原始载荷。因此对采集到的载荷信号进行片段划分,载荷信号片段划分的基本原理如图14所示。从信号零点开始,分别采用不同的时间片段划分长度。为选出的每个路况最小的时间片段选用4个参数来进行评价,分别是P值、R2R2PSD,以及δDP值与R2PSD的计算式分别为
式中,P值为划分片段所预测出六分力的值与真实六分力的值之间的平均相对距离之和;P预测为划分片段所预测出的六分力值;R真实为划分片段六分力的真实值;n为片段长度;R2PSD为原始片段与划分片段两者在相同频域上的拟合程度;为原始片段在某一频带下的功率;为划分片段在该频带下的功率;为原始片段所有频带下的平均功率。以波形路[图15(a)]、比利时路[图15(b)]为例,P值与伪损伤误差(六个分力总和)会随着片段长度的不断增加出现减小的趋势,而R2R2PSD呈不断增加的趋势。进而根据较小的伪损伤误差与P值以及较高的决定系数来确定某个路况需要多长的片段载荷作为该路况的训练集。对其余路况进行相同计算,得到各路况片段划分的最短时长,片段划分前、后对比如图15(c)所示。原始载荷信号长度总和为678 s,最小载荷信号长度总和为502 s,载荷数据样本量减少26%。
将各路况最短片段时长按照原始行驶路线进行拼接,拼接后训练集时长为502 s,经过训练得到最小数据集模型,且各个六分力的预测精度如表9所示。同时,为确定该模型的普适性,随机打乱测试集各个路况的拼接顺序,并抽取3组示例。由表9可知,训练集减少,导致预测精度略有下降,相应的计算时间进一步缩短9%左右,而预测损伤仍能够复现原始载荷80%以上的损伤,甚至90%以上的损伤,且3次预测结果基本一致。这证明了构造的特征参数可确定各路况最小载荷谱片段时长,也验证了最小数据集模型对不同路况行驶顺序具有较高的泛化能力。
为克服试验场道路载荷实测及虚拟迭代技术获取轮心六分力方法的局限性,以轮心加速度、减振器位移和质心加速度为输入,设计了基于数据驱动的整车道路载荷快速预测模型,并对该模型进行了普适性验证。主要结论如下:
1)基于IMF排列熵,确定了原始载荷中存在白噪声;针对噪声干扰对载荷信号进行CEEMDAN-PE-WTD。20~50 Hz频带噪声信息得到明显减少,低频带有效载荷信号基本得到了保留。
2)构建载荷预测多维度评价体系,并对多路况初始预测模型进行了评估,六分力预测值与实测值在时域、功率谱密度和损伤域上基本一致,初始预测模型整体适用于各个路况,载荷损伤误差均在20%以内,符合工程要求。
3)对16个输入通道特征与车轮六分力进行相关性、相干性分析。结果表明,容易获取且成本低的输入通道特征与轮心力相关度较低,但基于数据驱动的方法克服了这一局限性。进一步将16个输入通道压缩至5个输入通道,减少数据冗余,得到的压缩输入通道模型较好地复现了初始模型的预测精度。
4)基于构造特征参数确定各路况的最小载荷信号片段,划分片段后的训练集样本数量下降了26%,计算效率提高28.85%。虽然预测精度略有降低,但最小数据集模型在多维度评价体系中仍达到了期望的预测精度。同时,变换车辆行驶路况顺序对于最小数据集模型预测六分力的精度影响几乎可以忽略,验证了该模型具有较高的泛化能力。
5)该方法在一定程度上能够加快以轮心载荷为基础的零部件以及整车的可靠性、耐久性开发与评价,有助于快速提升汽车产品品质。
  • 国家自然科学基金项目(51705322)
  • 产学研合作项目(H-2022-304-042)
参考文献 引证文献
排序方式:
[1]
赵礼辉,李佳欣,井清,等. 关联用户的汽车试验场耐久性评价路况循环确定方法研究[J]. 汽车工程202042(1):127-133.
ZHAO LihuiLI JiaxinJING Qing,et al. Research on the method of determining road condition cycles of durability test of correlated user automobile test field[J]. Automotive Engineering202042(1):127-133.(In Chinese)
[2]
邹喜红,凌龙,陈静,等. 用户关联的驱动桥试验场耐久性试验规范研究[J]. 中国机械工程202233(14):1670-1679.
ZOU XihongLING LongCHEN Jing,et al. Research on durability test specifications of user-association drive axle test fields[J].China Mechanical Engineering202233(14):1670-1679.(In Chinese)
[3]
冯金芝,付道琪,郑松林,等. 悬架动态K&C试验典型激励谱的编制研究[J]. 机械强度202244(4):965-971.
FENG JinzhiFU DaoqiZHENG Songlin,et al. Study on the compilation of typical excitation spectrum of suspension dynamic K&C test[J]. Journal of Mechanical Strength202244(4):965-971.(In Chinese)
[4]
熊飞. 基于实车道路谱的车身疲劳寿命预测[D]. 广州:华南理工大学,2017:56.
XIONG Fei. The fatigue life prediction of car body structure based on real road spectrum[D]. Guangzhou:South China University of Technology,2017:56.(In Chinese)
[5]
徐春. 汽车变速器道路载荷谱的采集和应用研究[D]. 北京:北京理工大学,2018:28.
XU Chun. Research for acquisition and application of vehicle transmission road load spectrum[D]. Beijing:Beijing Institute of Technology,2018:28.(In Chinese)
[6]
王超. 基于虚拟试验场的车轮六分力提取方法研究[D]. 重庆:重庆理工大学,2022:55.
WANG Chao. Research on wheel six-component force extraction method based on virtual proving ground[D]. Chongqing:Chongqing University of Technology,2022:55.(In Chinese)
[7]
李荣强,连小锋,朱睿,等. 基于机器学习的飞机起落架着陆载荷预测模型[J]. 科学技术与工程202323(18):8011-8017.
LI RongqiangLIAN XiaofengZHU Rui,et al. Prediction model of landing load of aircraft landing gear based on machine learning[J]. Science Technology and Engineering202323(18):8011-8017.(In Chinese)
[8]
牟哲岳,孙勇,王瑞良,等. 基于实测数据和机器学习的风电机组载荷预测模型[J]. 太阳能学报202344(10):414-419.
MOU ZheyueSUN YongWANG Ruiliang,et al. Prediction model for wind turbine loads based on experimental data and machine learning[J]. Acta Energiae Solaris Sinica202344(10):414-419.(In Chinese)
[9]
杨博文,霍军周,张伟,等. 服役结构超前载荷实时预测方法的研究[J]. 东北大学学报(自然科学版)202243(4):541-550.
YANG BowenHUO JunzhouZHANG Wei,et al. Research on real-time overload prediction method of in-service structures[J].Journal of Northeastern University (Natural Science)202243(4):541-550.(In Chinese)
[10]
罗欢,胡浩炬,余家皓. 基于深度卷积-长短期记忆神经网络的整车道路载荷预测[J]. 汽车技术2021(7):46-51.
LUO HuanHU HaojuYU Jiahao,et al. Prediction of vehicle road load based on deep convolution neutral network-long-short term memory[J]. Automobile Technology2021(7):46-51.(In Chinese)
[11]
WANG YZHENG X KWANG L,et al. Edge-computing based soft sensors with local Finite Impulse Response models for vehicle wheel center loads estimation under multiple working conditions[J]. Control Engineering Practice2023133:105447.
[12]
韩雪飞,施展,华云松. 基于参数优化MOMEDA与CEEMDAN的滚动轴承微弱故障特征提取研究[J]. 机械强度202143(5):1041-1049.
HAN XuefeiSHI ZhanHUA Yunsong,et al. Weak fault feature extraction of rolling bearing based on parameter optimized MOMEDA and CEEMDAN[J]. Journal of Mechanical Strength202143(5):1041-1049.(In Chinese)
[13]
ZHAO J WNIE G ZYAN M,et al. A novel approach to precipitation prediction using a coupled CEEMDAN-GRU-Transformer model with permutation entropy algorithm[J]. Water Science & Technology202388(4):1015-1038.
[14]
BANDT CPOMPE B.Permutation entropy:a natural complexity measure for time series[J].Physical Review Letters200288(17):174102.
[15]
李志军,张鸿鹏,王亚楠,等. 排列熵—CEEMD分解下的新型小波阈值去噪谐波检测方法[J]. 电机与控制学报202024(12):120-129.
LI ZhijunZHANG HongpengWANG Yanan,et al. Wavelet threshold denoising harmonic detection method based on permutation entropy-CEEMD decomposition[J]. Electric Machines and Control202024(12):120-129.(In Chinese)
[16]
陈祥龙,张兵志,冯辅周,等. 基于改进排列熵的滚动轴承故障特征提取[J]. 振动工程学报201831(5):902-908.
CHEN XianglongZHANG BingzhiFENG Fuzhou,et al. Fault feature extraction of rolling bearings based on an improved permutation entropy[J]. Journal of Vibration Engineering201831(5):902-908.(In Chinese)
[17]
ZHANG X LCAO L YCHEN Y,et al. Microseismic signal denoising by combining variational mode decomposition with permutation entropy[J]. Applied Geophysics202219(1):65-80.
[18]
徐隆,杨军,周龙,等. PE-VMD与小波阈值的干涉型光纤联合去噪方法[J]. 国外电子测量技术202241(10):39-46.
XU LongYANG JunZHOU Long,et al. Joint denoising method for interferic fibers with PE-VMD and wavelet thresholds[J].Foreign Electronic Measurement Technology202241(10):39-46.(In Chinese)
[19]
于淼,张耀鲁,何禹潼,等. 变分模态分解-排列熵方法用于分布式光纤振动传感系统去噪[J]. 光学学报202242(7):62-73.
YU MiaoZHANG YaoluHE Yutong,et al. Variational mode decomposition and permutation entropy method for denoising of distributed optical fiber vibration sensing system[J]. Acta Optica Sinica202242(7):62-73.(In Chinese)
[20]
李冬毅,覃方君,李安,等.强噪声条件下原子重力仪小波降噪适应性研究[J]. 海军工程大学学报202335(2):52-58.
LI DongyiQIN FangjunLI An,et al. Research on adaptability of wavelet denoising algorithm of atom gravimeter under strong noise conditions[J]. Journal of Naval University of Engineering202335(2):52-58.(In Chinese)
[21]
宋秀兰,董兆航,单杭冠,等. 基于时空融合的多头注意力车辆轨迹预测[J]. 浙江大学学报(工学版)202357(8):1636-1643.
SONG XiulanDONG ZhaohangSHAN Hangguan,et al. Vehicle trajectory prediction based on temporal-spatial multi-head attention mechanism[J]. Journal of Zhejiang University(Engineering Science)202357(8):1636-1643.(In Chinese)
[22]
梁冠群,赵通,王岩,等. 基于LSTM网络的路面不平度辨识方法[J]. 汽车工程202143(4):509-517.
LIANG GuanqunZHAO TongWANG Yan,et al. Road unevenness identification based on LSTM network[J].Automotive Engineering202143(4):509-517.(In Chinese)
[23]
魏孟,王桥,叶敏,等. 基于NARX动态神经网络的锂离子电池剩余寿命间接预测[J]. 工程科学学报202244(3):380-388.
WEI MengWANG QiaoYE Min,et al. An indirect remaining useful life prediction of lithiumion batteries based on a NARX dynamic neural network[J].Chinese Journal of Engineering202244(3):380-388.(In Chinese)
[24]
文昌俊,陈哲,邵明颖,等. 基于改进PSO_BP神经网络的干燥机可靠性预测[J]. 机械强度202345(2):504-508.
WEN ChangjunCHEN ZheSHAO Mingying,et al. Reliability prediction of dryer based on improved PSO_BP neural network[J]. Journal of Mechanical Strength202345(2):504-508.(In Chinese)
[25]
LI D HTIAN J WSHI S W,et al. Lightweight design of commercial vehicle cab based on fatigue durability[J]. Computer Modeling in Engineering & Sciences2023136(1):421-445.
2025年第47卷第10期
PDF下载
132
66
引用本文
BibTeX
文章信息
doi: 10.16579/j.issn.1001.9669.2025.10.001
  • 接收时间:2023-11-28
  • 首发时间:2026-02-11
  • 出版时间:2025-10-15
补充材料
相关文章
文章信息
作者
出版历史
  • 收稿日期:2023-11-28
  • 修回日期:2024-01-14
基金
National Natural Science Foundation of China(51705322)
国家自然科学基金项目(51705322)
Industry-Academia-Research Collaboration Project(H-2022-304-042)
产学研合作项目(H-2022-304-042)
作者信息
    1.上海理工大学 机械工程学院,上海 200093
    2.机械工业汽车机械零部件强度与可靠性评价重点实验室,上海 200093
    3.上海市新能源汽车可靠性评价专业技术服务平台,上海 200093
    4.中汽研汽车试验场股份有限公司,盐城 224100

通讯作者:

赵礼辉,男,1985年生,山东青岛人,博士,副教授,硕士研究生导师;主要研究方向为车辆强度可靠性设计与评价、车辆载荷特征建模与快速试验;E-mail:
参考文献
分享链接
https://castjournals.cast.org.cn/joweb/jxqd/CN/10.16579/j.issn.1001.9669.2025.10.001
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