Article(id=1207658078737113876, tenantId=1146029695717560320, journalId=1205116883411038211, issueId=1207658076900008717, articleNumber=null, orderNo=null, doi=null, pmid=null, cstr=null, oa=null, hot=null, price=null, onlineType=0, articleFormat=0, articleType=null, articleTypeStr=null, receivedDate=null, receivedDateStr=null, revisedDate=null, revisedDateStr=null, acceptedDate=null, acceptedDateStr=null, onlineDate=1765857723172, onlineDateStr=2025-12-16, pubDate=null, pubDateStr=null, doiRegisterDate=null, doiRegisterDateStr=null, onlineIssueDate=1765857723172, onlineIssueDateStr=2025-12-16, onlineJustAcceptDate=null, onlineJustAcceptDateStr=null, onlineFirstDate=null, onlineFirstDateStr=null, sourceXml=null, magXml=null, createTime=1765857723172, creator=13701087609, updateTime=1765857723172, updator=13701087609, issue=Issue{id=1207658076900008717, tenantId=1146029695717560320, journalId=1205116883411038211, year='2025', volume='23', issue='2', pageStart='189', pageEnd='376', issueExtLink='null', onlineDate='null', pubDate='null', beforeIssueId=null, nextIssueId=null, price=null, status=1, issueComplete=1, articleOrder=1, issueType=-1, specialIssue=null, createTime=1765857722735, creator=13701087609, updateTime=1765862348176, updator=13701087609, preIssue=null, nextIssue=null, ext={EN=IssueExt(id=1207677477451833566, tenantId=1146029695717560320, journalId=1205116883411038211, issueId=1207658076900008717, language=EN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=), CN=IssueExt(id=1207677477451833567, tenantId=1146029695717560320, journalId=1205116883411038211, issueId=1207658076900008717, language=CN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=)}, issueFiles=null}, startPage=361, endPage=365, ext={EN=ArticleExt(id=1207658079018132250, articleId=1207658078737113876, tenantId=1146029695717560320, journalId=1205116883411038211, language=EN, title=A fast anti-lifting detection method for trains based on improved BP neural network, columnId=1207658078934246168, journalTitle=Chinese Journal of Construction Machinery, columnName=Performance Mensuration, Experimentation and Fault Diagnosis, runingTitle=null, highlight=null, articleAbstract=

In the railway container yard, there are few mature intelligent anti-lifting solutions available for train flatbed loading and unloading operations due to the poor detection accuracy or speed of traditional detection methods. This paper proposes a fast anti-lifting detection method for trains based on an improved back propagation (BP) neural network. By acquiring weight data from the four locks of the hoist, a flatbed lifting detection model is established using a BP neural network. During weight adjustment, a momentum factor and an adaptive learning rate are incorporated to optimize the model's performance. Through practical tests, this method demonstrates that this model achieves a high detection rate and fast detection speed, making it suitable for providing intelligent safety protection for automated rail mounted gantry in the railway container yard.

, correspAuthors=null, authorNote=null, correspAuthorsNote=null, copyrightStatement=null, copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=null, magXml=null, pdfUrl=null, pdf=null, pdfFileSize=null, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=null, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=null, mapNumber=null, authorCompany=null, fund=null, authors=null, authorsList=Jun JIANG, Weijian MI), CN=ArticleExt(id=1207658083501842462, articleId=1207658078737113876, tenantId=1146029695717560320, journalId=1205116883411038211, language=CN, title=基于改进BP神经网络的火车防吊起快速检测方法, columnId=1207658079093629725, journalTitle=中国工程机械学报, columnName=性能检测、试验及故障诊断, runingTitle=null, highlight=null, articleAbstract=

铁路集装箱堆场对于火车平板装卸作业,由于传统检测方法检测精度或检测速度不能满足要求,鲜有成熟的智能防吊起解决方案。本文提出一种基于改进反向传播(BP)神经网络的火车防吊起快速检测方法,通过获取吊具4个锁头的称重数据,建立基于BP神经网络的平板吊起检测模型,在权值调整时加入动量因子和自适应调节学习率以优化模型性能。在实际作业中测试,本方法具有较高的检出率和快速的检测速度,可为轨道吊自动化火车作业提供智能安全防护。

, correspAuthors=null, authorNote=null, correspAuthorsNote=null, copyrightStatement=null, copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=h5x4Wal5wkpic5hyWnkpEA==, magXml=G+asRxsqbTcbM0jV3KmdwA==, pdfUrl=null, pdf=OYJ0NMEX4qiu53JtHhb0Sg==, pdfFileSize=2251677, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=KIkBPMAzk+fhxNVxaW8PBQ==, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=bYvPN89ROCFTNDA//YbNZA==, mapNumber=null, authorCompany=null, fund=null, authors=

姜军(1989—),男,博士。E-mail:

, authorsList=姜军, 宓为建)}, authors=[Author(id=1207748665993699547, tenantId=1146029695717560320, journalId=1205116883411038211, articleId=1207658078737113876, orderNo=0, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=jiangjun1989austin@163.com, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1207748666106945764, tenantId=1146029695717560320, journalId=1205116883411038211, articleId=1207658078737113876, authorId=1207748665993699547, language=EN, stringName=Jun JIANG, firstName=Jun, middleName=null, lastName=JIANG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1. Shanghai Investigation, Design & Research Institute Co., Ltd., Shanghai 200335, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1207748666220191980, tenantId=1146029695717560320, journalId=1205116883411038211, articleId=1207658078737113876, authorId=1207748665993699547, language=CN, stringName=姜军, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1.上海勘测设计研究院有限公司,上海 200335, bio={"content":"

姜军(1989—),男,博士。E-mail:

"}, bioImg=null, bioContent=

姜军(1989—),男,博士。E-mail:

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1207748665792372937, tenantId=1146029695717560320, journalId=1205116883411038211, articleId=1207658078737113876, xref=null, ext=[AuthorCompanyExt(id=1207748665800761545, tenantId=1146029695717560320, journalId=1205116883411038211, articleId=1207658078737113876, companyId=1207748665792372937, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1. Shanghai Investigation, Design & Research Institute Co., Ltd., Shanghai 200335, China), AuthorCompanyExt(id=1207748665804955850, tenantId=1146029695717560320, journalId=1205116883411038211, articleId=1207658078737113876, companyId=1207748665792372937, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.上海勘测设计研究院有限公司,上海 200335)])]), Author(id=1207748666341826805, tenantId=1146029695717560320, journalId=1205116883411038211, articleId=1207658078737113876, 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=1207748666513793277, tenantId=1146029695717560320, journalId=1205116883411038211, articleId=1207658078737113876, authorId=1207748666341826805, language=EN, stringName=Weijian MI, firstName=Weijian, middleName=null, lastName=MI, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2. Institute of Logistics Science and Engineering, Shanghai Maritime University, Shanghai 201306, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1207748666681565446, tenantId=1146029695717560320, journalId=1205116883411038211, articleId=1207658078737113876, authorId=1207748666341826805, language=CN, stringName=宓为建, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2.上海海事大学 物流科学与工程研究院,上海 201306, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1207748665897230545, tenantId=1146029695717560320, journalId=1205116883411038211, articleId=1207658078737113876, xref=null, ext=[AuthorCompanyExt(id=1207748665905619155, tenantId=1146029695717560320, journalId=1205116883411038211, articleId=1207658078737113876, companyId=1207748665897230545, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2. Institute of Logistics Science and Engineering, Shanghai Maritime University, Shanghai 201306, China), AuthorCompanyExt(id=1207748665909813460, tenantId=1146029695717560320, journalId=1205116883411038211, articleId=1207658078737113876, companyId=1207748665897230545, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.上海海事大学 物流科学与工程研究院,上海 201306)])])], keywords=[Keyword(id=1207748666916446487, tenantId=1146029695717560320, journalId=1205116883411038211, articleId=1207658078737113876, language=EN, orderNo=1, keyword=container train), Keyword(id=1207748667180687654, tenantId=1146029695717560320, journalId=1205116883411038211, articleId=1207658078737113876, language=EN, orderNo=2, keyword=F-TR lock anti-lifting), Keyword(id=1207748668279595312, tenantId=1146029695717560320, journalId=1205116883411038211, articleId=1207658078737113876, language=EN, orderNo=3, keyword=back propagation (BP) neural network), Keyword(id=1207748668380258618, tenantId=1146029695717560320, journalId=1205116883411038211, articleId=1207658078737113876, language=EN, orderNo=4, keyword=momentum factor), Keyword(id=1207748668476727617, tenantId=1146029695717560320, journalId=1205116883411038211, articleId=1207658078737113876, language=EN, orderNo=5, keyword=adaptive learning), Keyword(id=1207748668648694094, tenantId=1146029695717560320, journalId=1205116883411038211, articleId=1207658078737113876, language=CN, orderNo=1, keyword=集装箱火车), Keyword(id=1207748668740968788, tenantId=1146029695717560320, journalId=1205116883411038211, articleId=1207658078737113876, language=CN, orderNo=2, keyword=平板鹰钩(F-TR)锁防吊起), Keyword(id=1207748668866797921, tenantId=1146029695717560320, journalId=1205116883411038211, articleId=1207658078737113876, language=CN, orderNo=3, keyword=反向传播(BP)神经网络), Keyword(id=1207748669005209962, tenantId=1146029695717560320, journalId=1205116883411038211, articleId=1207658078737113876, language=CN, orderNo=4, keyword=动量因子), Keyword(id=1207748669101678963, tenantId=1146029695717560320, journalId=1205116883411038211, articleId=1207658078737113876, language=CN, orderNo=5, keyword=自适应学习)], refs=[Reference(id=1207748671031058955, tenantId=1146029695717560320, journalId=1205116883411038211, articleId=1207658078737113876, doi=null, pmid=null, pmcid=null, year=2022, volume=22, issue=1, pageStart=133, pageEnd=141, url=null, language=null, rfNumber=[1], rfOrder=0, authorNames=周勇, 张杰, 钟祾充, journalName=交通运输系统工程与信息, refType=null, unstructuredReference=周勇,张杰,钟祾充,等. 铁路集装箱中心站多轨道吊柔性协同调度优化[J]. 交通运输系统工程与信息202222(1):133-141., articleTitle=铁路集装箱中心站多轨道吊柔性协同调度优化, refAbstract=null), Reference(id=1207748671127527956, tenantId=1146029695717560320, journalId=1205116883411038211, articleId=1207658078737113876, doi=null, pmid=null, pmcid=null, year=2021, volume=36, issue=12, pageStart=3063, pageEnd=3073, url=null, language=null, rfNumber=[2], rfOrder=1, authorNames=王小寒, 贾玉林, 蔡佳芯, journalName=控制与决策, refType=null, unstructuredReference=王小寒,贾玉林,蔡佳芯. 铁路集装箱中心站资源分配与作业调度联合优化[J]. 控制与决策202136(12):3063-3073., articleTitle=铁路集装箱中心站资源分配与作业调度联合优化, refAbstract=null), Reference(id=1207748671240774174, tenantId=1146029695717560320, journalId=1205116883411038211, articleId=1207658078737113876, doi=null, pmid=null, pmcid=null, year=2011, volume=null, issue=null, pageStart=25, pageEnd=39, url=null, language=null, rfNumber=[3], rfOrder=2, authorNames=BRINKMANN B, journalName=null, refType=null, unstructuredReference=BRINKMANN B. Operations systems of container terminals:a compendious overview handbook of terminal planning[C]// Handbook of Terminal Planning. New York,NY,USA:Springer,2011:25-39., articleTitle=Operations systems of container terminals:a compendious overview handbook of terminal planning, refAbstract=null), Reference(id=1207748671362409000, tenantId=1146029695717560320, journalId=1205116883411038211, articleId=1207658078737113876, doi=null, pmid=null, pmcid=null, year=2021, volume=24, issue=4, pageStart=65, pageEnd=76, url=null, language=null, rfNumber=[4], rfOrder=3, authorNames=MI C, HUANG Y G, FU C H, journalName=IEEE Instrumentation and Measurement Magazine, refType=null, unstructuredReference=MI CHUANG Y GFU C H,et al. Vision-based measurement:actualities and developing trends in automated container terminals[J]. IEEE Instrumentation and Measurement Magazine202124(4):65-76., articleTitle=Vision-based measurement:actualities and developing trends in automated container terminals, refAbstract=null), Reference(id=1207748671463072300, tenantId=1146029695717560320, journalId=1205116883411038211, articleId=1207658078737113876, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[5], rfOrder=4, authorNames=HUANG Q F, HUANG Y G, ZHANG Z W, journalName=null, refType=null, unstructuredReference=HUANG Q FHUANG Y GZHANG Z W,et al. Truck-lifting prevention system based on vision tracking for container-lifting operation[EB/OL].(2021-12-01)[2023-08-11]. https://onlinelibrary.wiley.com/doi/10.1155/2021/9612480., articleTitle=Truck-lifting prevention system based on vision tracking for container-lifting operation, refAbstract=null), Reference(id=1207748672692003383, tenantId=1146029695717560320, journalId=1205116883411038211, articleId=1207658078737113876, doi=null, pmid=null, pmcid=null, year=2011, volume=36, issue=2, pageStart=153, pageEnd=162, url=null, language=null, rfNumber=[6], rfOrder=5, authorNames=DING S F, SU C Y, YU J Z, journalName=Artificial Intelligence Review, refType=null, unstructuredReference=DING S FSU C YYU J Z. An optimizing BP neural network algorithm based on genetic algorithm[J]. Artificial Intelligence Review201136(2):153-162., articleTitle=An optimizing BP neural network algorithm based on genetic algorithm, refAbstract=null), Reference(id=1207748672788472385, tenantId=1146029695717560320, journalId=1205116883411038211, articleId=1207658078737113876, doi=null, pmid=null, pmcid=null, year=2019, volume=31, issue=12, pageStart=8205, pageEnd=8215, url=null, language=null, rfNumber=[7], rfOrder=6, authorNames=CUI K, JING X, journalName=Neural Computing & Applications, refType=null, unstructuredReference=CUI KJING X. Research on prediction model of geotechnical parameters based on BP neural network[J]. Neural Computing & Applications201931(12):8205-8215., articleTitle=Research on prediction model of geotechnical parameters based on BP neural network, refAbstract=null), Reference(id=1207748672893329996, tenantId=1146029695717560320, journalId=1205116883411038211, articleId=1207658078737113876, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[8], rfOrder=7, authorNames=KINGMA D P, BA J, journalName=null, refType=null, unstructuredReference=KINGMA D PBA J. Adam:a method for stochastic optimization[EB/OL].(2014-12-22)[2023-08-11]. https://arxiv.org/abs/1412.6980., articleTitle=Adam:a method for stochastic optimization, refAbstract=null), Reference(id=1207748673006576214, tenantId=1146029695717560320, journalId=1205116883411038211, articleId=1207658078737113876, doi=null, pmid=null, pmcid=null, year=2015, volume=null, issue=null, pageStart=693, pageEnd=698, url=null, language=null, rfNumber=[9], rfOrder=8, authorNames=LI J J, SHENG V S, SHU Z Y, journalName=null, refType=null, unstructuredReference=LI J JSHENG V SSHU Z Y,et al. Learning from the crowd with neural net-work[C]// 2015 IEEE 14th International Conference on Machine Learning and Applications(ICMLA). Miami,FL,USA:IEEE,2015:693-698., articleTitle=Learning from the crowd with neural net-work, refAbstract=null), Reference(id=1207748673107239523, tenantId=1146029695717560320, journalId=1205116883411038211, articleId=1207658078737113876, doi=null, pmid=null, pmcid=null, year=2001, volume=null, issue=2, pageStart=101, pageEnd=104, url=null, language=null, rfNumber=[10], rfOrder=9, authorNames=左志强, 陈永进, 慈春令, journalName=燕山大学学报, refType=null, unstructuredReference=左志强,陈永进,慈春令. 基于MATLAB下的改进BP算法[J]. 燕山大学学报2001(2):101-104., articleTitle=基于MATLAB下的改进BP算法, refAbstract=null)], funds=null, companyList=[AuthorCompany(id=1207748665792372937, tenantId=1146029695717560320, journalId=1205116883411038211, articleId=1207658078737113876, xref=null, ext=[AuthorCompanyExt(id=1207748665800761545, tenantId=1146029695717560320, journalId=1205116883411038211, articleId=1207658078737113876, companyId=1207748665792372937, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1. Shanghai Investigation, Design & Research Institute Co., Ltd., Shanghai 200335, China), AuthorCompanyExt(id=1207748665804955850, tenantId=1146029695717560320, journalId=1205116883411038211, articleId=1207658078737113876, companyId=1207748665792372937, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.上海勘测设计研究院有限公司,上海 200335)]), AuthorCompany(id=1207748665897230545, tenantId=1146029695717560320, journalId=1205116883411038211, articleId=1207658078737113876, xref=null, ext=[AuthorCompanyExt(id=1207748665905619155, tenantId=1146029695717560320, journalId=1205116883411038211, articleId=1207658078737113876, companyId=1207748665897230545, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2. Institute of Logistics Science and Engineering, Shanghai Maritime University, Shanghai 201306, China), AuthorCompanyExt(id=1207748665909813460, tenantId=1146029695717560320, journalId=1205116883411038211, articleId=1207658078737113876, companyId=1207748665897230545, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.上海海事大学 物流科学与工程研究院,上海 201306)])], figs=[ArticleFig(id=1207748669311394181, tenantId=1146029695717560320, journalId=1205116883411038211, articleId=1207658078737113876, language=EN, label=Fig.1, caption=Schematic diagram of BP neural network, figureFileSmall=tp4AX76OTjQF8jZfGsrc1Q==, figureFileBig=B7VqZg0qBagoMmE2ogPvjA==, tableContent=null), ArticleFig(id=1207748669399474568, tenantId=1146029695717560320, journalId=1205116883411038211, articleId=1207658078737113876, language=CN, label=图1, caption=BP神经网络模型, figureFileSmall=tp4AX76OTjQF8jZfGsrc1Q==, figureFileBig=B7VqZg0qBagoMmE2ogPvjA==, tableContent=null), ArticleFig(id=1207748669537886613, tenantId=1146029695717560320, journalId=1205116883411038211, articleId=1207658078737113876, language=EN, label=Fig.2, caption=Weight data waveforms from the four corner points of the hoist during jogging operation, figureFileSmall=1VD5v2GgSFI6w4FaSQtMQA==, figureFileBig=+VbH24rFzBYBBQrTnXRQCA==, tableContent=null), ArticleFig(id=1207748669667910051, tenantId=1146029695717560320, journalId=1205116883411038211, articleId=1207658078737113876, language=CN, label=图2, caption=点动运行时吊具4个角点的称重数据波形, figureFileSmall=1VD5v2GgSFI6w4FaSQtMQA==, figureFileBig=+VbH24rFzBYBBQrTnXRQCA==, tableContent=null), ArticleFig(id=1207748669760184745, tenantId=1146029695717560320, journalId=1205116883411038211, articleId=1207658078737113876, language=EN, label=Fig.3, caption=Curve about the number of hidden layer neurons and network output error, figureFileSmall=2utMdK6GQ1XJQW1PJkPp6g==, figureFileBig=XRr23tdcugNIRQqv0P4aMQ==, tableContent=null), ArticleFig(id=1207748669873430965, tenantId=1146029695717560320, journalId=1205116883411038211, articleId=1207658078737113876, language=CN, label=图3, caption=隐含层神经元个数与网络输出误差的关系曲线, figureFileSmall=2utMdK6GQ1XJQW1PJkPp6g==, figureFileBig=XRr23tdcugNIRQqv0P4aMQ==, tableContent=null), ArticleFig(id=1207748670011843005, tenantId=1146029695717560320, journalId=1205116883411038211, articleId=1207658078737113876, language=EN, label=Fig.4, caption=Training process of BP neural network, figureFileSmall=hFa10m0LOFCUE7+wZ+8NJA==, figureFileBig=OpZqm3ddQ75dGHBbY42kjg==, tableContent=null), ArticleFig(id=1207748670116700609, tenantId=1146029695717560320, journalId=1205116883411038211, articleId=1207658078737113876, language=CN, label=图4, caption=BP神经网络训练流程, figureFileSmall=hFa10m0LOFCUE7+wZ+8NJA==, figureFileBig=OpZqm3ddQ75dGHBbY42kjg==, tableContent=null), ArticleFig(id=1207748670238335437, tenantId=1146029695717560320, journalId=1205116883411038211, articleId=1207658078737113876, language=EN, label=Fig.5, caption=Schematic diagram of the system equipment, figureFileSmall=vdWL1T0Kk/Ro2OAg5bajNw==, figureFileBig=9FgZnSVt7fD9xbQBUurZ/A==, tableContent=null), ArticleFig(id=1207748670326415826, tenantId=1146029695717560320, journalId=1205116883411038211, articleId=1207658078737113876, language=CN, label=图5, caption=实验设备安装, figureFileSmall=vdWL1T0Kk/Ro2OAg5bajNw==, figureFileBig=9FgZnSVt7fD9xbQBUurZ/A==, tableContent=null), ArticleFig(id=1207748670422884826, tenantId=1146029695717560320, journalId=1205116883411038211, articleId=1207658078737113876, language=EN, label=Fig.6, caption=Schematic diagram of experimental results and weight data waveform, figureFileSmall=ZXtgP1bb36FiGB0gZI0y3w==, figureFileBig=vQBwaSlGeywbOAxB8GCa/Q==, tableContent=null), ArticleFig(id=1207748670502576607, tenantId=1146029695717560320, journalId=1205116883411038211, articleId=1207658078737113876, language=CN, label=图6, caption=实验效果示意图及称重数据波形, figureFileSmall=ZXtgP1bb36FiGB0gZI0y3w==, figureFileBig=vQBwaSlGeywbOAxB8GCa/Q==, tableContent=null), ArticleFig(id=1207748670624211434, tenantId=1146029695717560320, journalId=1205116883411038211, articleId=1207658078737113876, language=EN, label=Tab.1, caption=

Experimental results of the train anti-lifting detection method based on improved BP neural network

, figureFileSmall=null, figureFileBig=null, tableContent=
测试样本20尺空箱20尺重箱40尺空箱40尺重箱
工况置信度检测时间/ms置信度检测时间/ms置信度检测时间/ms置信度检测时间/ms
正常起吊0.319 41610.203 11330.659 41170.156 8164
正常起吊0.316 41190.550 41270.569 41620.638 8147
正常起吊0.286 61320.609 31180.412 41450.322 5129
正常起吊0.145 11180.408 91200.544 41270.404 8141
正常起吊0.276 51530.482 31330.523 31210.388 7134
单锁勾连0.968 61140.879 31510.910 81350.911 7110
单锁勾连0.874 21160.918 81050.886 41140.936 5125
单锁勾连0.992 91500.851 31140.852 61550.881 1162
单锁勾连0.914 61430.998 31390.957 61060.937 2147
单锁勾连0.826 31130.891 21270.957 41220.948 6130
双锁勾连0.978 21080.844 41560.911 91210.882 1140
双锁勾连0.960 41450.913 51280.943 71370.887 3119
双锁勾连0.872 41240.815 71530.903 11370.908 3126
双锁勾连0.954 81260.855 11480.810 51510.883 0129
双锁勾连0.839 91030.922 61530.942 21420.835 1158
三锁勾连0.900 81560.889 81210.945 71150.861 7136
三锁勾连0.931 21360.953 31190.943 01380.624 1131
三锁勾连0.860 31550.962 71380.721 41110.874 8155
三锁勾连0.973 91180.926 41520.841 41350.942 6146
三锁勾连0.991 41130.701 71060.935 61190.505 1125
), ArticleFig(id=1207748670758429172, tenantId=1146029695717560320, journalId=1205116883411038211, articleId=1207658078737113876, language=CN, label=表1, caption=

基于改进BP神经网络的火车防吊起检测方法实验结果

, figureFileSmall=null, figureFileBig=null, tableContent=
测试样本20尺空箱20尺重箱40尺空箱40尺重箱
工况置信度检测时间/ms置信度检测时间/ms置信度检测时间/ms置信度检测时间/ms
正常起吊0.319 41610.203 11330.659 41170.156 8164
正常起吊0.316 41190.550 41270.569 41620.638 8147
正常起吊0.286 61320.609 31180.412 41450.322 5129
正常起吊0.145 11180.408 91200.544 41270.404 8141
正常起吊0.276 51530.482 31330.523 31210.388 7134
单锁勾连0.968 61140.879 31510.910 81350.911 7110
单锁勾连0.874 21160.918 81050.886 41140.936 5125
单锁勾连0.992 91500.851 31140.852 61550.881 1162
单锁勾连0.914 61430.998 31390.957 61060.937 2147
单锁勾连0.826 31130.891 21270.957 41220.948 6130
双锁勾连0.978 21080.844 41560.911 91210.882 1140
双锁勾连0.960 41450.913 51280.943 71370.887 3119
双锁勾连0.872 41240.815 71530.903 11370.908 3126
双锁勾连0.954 81260.855 11480.810 51510.883 0129
双锁勾连0.839 91030.922 61530.942 21420.835 1158
三锁勾连0.900 81560.889 81210.945 71150.861 7136
三锁勾连0.931 21360.953 31190.943 01380.624 1131
三锁勾连0.860 31550.962 71380.721 41110.874 8155
三锁勾连0.973 91180.926 41520.841 41350.942 6146
三锁勾连0.991 41130.701 71060.935 61190.505 1125
)], attaches=null, journal=Journal(id=1205114436508614657, delFlag=0, nameCn=中国工程机械学报, nameEn=Chinese Journal of Construction Machinery, nameHistory1=null, nameHistory2=null, issn=1672-5581, eissn=, cn=31-1926/TH, coden=null, periodic=双月刊, language=CN, oaType=1, 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=, officePhone=, editDirector=null, officeDirector=null, officeDirectorPhone=null, officeStaffNum=null, officeEmpNum=null, coverPicUrl=/KlTPs3yCXsXGMqW4Jw0zg==, journalPrice=null, startedYear=null, abbrevIsoEn=Chinese Journal of Construction Machinery, journalRemark=null, publicationField=null, createdTime=1765251271611, updatedTime=1765252089947, createdBy=18614031015, updatedBy=13701087609, firstLetterCn=C, firstLetterEn=C, subjectCode=Engineering, subjectName=工程科学, subjectCodeEn=Engineering, subjectNameEn=null, picCn=/KlTPs3yCXsXGMqW4Jw0zg==, picEn=61Q0qzkf783cI1Yd6RfYHA==, jcr=null, cjcr=null, exts=[JournalExt(id=1205117869005713608, language=CN, name=中国工程机械学报, 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=1765252089978, updatedTime=1765252089978, createdBy=13701087609, updatedBy=13701087609, submissionGuidelinesUrl=, submissionAuthorUrl=https://gche.cbpt.cnki.net/index.aspx?t=1, submissionEditorUrl=https://gche.cbpt.cnki.net/index.aspx?t=3, submissionReviewUrl=https://gche.cbpt.cnki.net/index.aspx?t=2, submissionCeEditorUrl=, submissionAeEditorUrl=, option={"copyright":""}), JournalExt(id=1205117869060239561, language=EN, name=Chinese Journal of Construction Machinery, 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=1765252089991, updatedTime=1765252089991, createdBy=13701087609, updatedBy=13701087609, submissionGuidelinesUrl=, submissionAuthorUrl=https://gche.cbpt.cnki.net/index.aspx?t=1, submissionEditorUrl=https://gche.cbpt.cnki.net/index.aspx?t=3, submissionReviewUrl=https://gche.cbpt.cnki.net/index.aspx?t=2, submissionCeEditorUrl=, submissionAeEditorUrl=, option={"copyright":""})], databaseList=null, tenantJournalId=1205116883411038211, websiteList=[Website(id=1205118567944532179, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1205116883411038211, 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/zggcjxxb/CN, language=CN, createTime=1765252256618, createBy=18614031015, updateTime=1765252390759, updateBy=18614031015, name=中国工程机械学报-中文, tplId=1146099689490845704, title=中国工程机械学报, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1205151279745048900, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1205118567944532179, code=articleTextType, value=kx, createTime=1765260055719, updateTime=1765260055719, creator=18614031015, updator=18614031015), WebsiteProps(id=1205151279715688769, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1205118567944532179, code=banner, value=null, createTime=1765260055712, updateTime=1765260055712, creator=18614031015, updator=18614031015), WebsiteProps(id=1205151279774409031, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1205118567944532179, code=grayFlag, value=0, createTime=1765260055726, updateTime=1765260055726, creator=18614031015, updator=18614031015), WebsiteProps(id=1205151279703105856, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1205118567944532179, code=logo, value=https://castjournals.cast.org.cn/joweb/zggcjxxb/CN/file/pic?fileId=JL02OL9fp/7Bo5RRnVxorw==, createTime=1765260055709, updateTime=1765260055709, creator=18614031015, updator=18614031015), WebsiteProps(id=1205151279791186249, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1205118567944532179, code=minRunFlag, value=0, createTime=1765260055730, updateTime=1765260055730, creator=18614031015, updator=18614031015), WebsiteProps(id=1205151279736660291, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1205118567944532179, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/zggcjxxb/CN/file/pic, createTime=1765260055717, updateTime=1765260055717, creator=18614031015, updator=18614031015), WebsiteProps(id=1205151279782797640, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1205118567944532179, code=silenceFlag, value=0, createTime=1765260055728, updateTime=1765260055728, creator=18614031015, updator=18614031015), WebsiteProps(id=1205151279728271682, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1205118567944532179, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_cn_619/, createTime=1765260055715, updateTime=1765260055715, creator=18614031015, updator=18614031015), WebsiteProps(id=1205151279753437509, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1205118567944532179, code=themeColor, value=null, createTime=1765260055721, updateTime=1765260055721, creator=18614031015, updator=18614031015), WebsiteProps(id=1205151279761826118, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1205118567944532179, code=themeStyle, value=null, createTime=1765260055723, updateTime=1765260055723, creator=18614031015, updator=18614031015)]), Website(id=1205118568116498664, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1205116883411038211, 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/zggcjxxb/EN, language=EN, createTime=1765252256659, createBy=18614031015, updateTime=1765252407273, updateBy=18614031015, name=中国工程机械学报-英文, tplId=1146101810881728533, title=Chinese Journal of Construction Machinery, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1205151309042262350, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1205118568116498664, code=articleTextType, value=kx, createTime=1765260062704, updateTime=1765260062704, creator=18614031015, updator=18614031015), WebsiteProps(id=1205151309021290827, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1205118568116498664, code=banner, value=null, createTime=1765260062699, updateTime=1765260062699, creator=18614031015, updator=18614031015), WebsiteProps(id=1205151309063233873, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1205118568116498664, code=grayFlag, value=0, createTime=1765260062709, updateTime=1765260062709, creator=18614031015, updator=18614031015), WebsiteProps(id=1205151309008707914, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1205118568116498664, code=logo, value=https://castjournals.cast.org.cn/joweb/zggcjxxb/EN/file/pic?fileId=JL02OL9fp/7Bo5RRnVxorw==, createTime=1765260062696, updateTime=1765260062696, creator=18614031015, updator=18614031015), WebsiteProps(id=1205151309075816787, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1205118568116498664, code=minRunFlag, value=0, createTime=1765260062712, updateTime=1765260062712, creator=18614031015, updator=18614031015), WebsiteProps(id=1205151309038068045, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1205118568116498664, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/zggcjxxb/EN/file/pic, createTime=1765260062703, updateTime=1765260062703, creator=18614031015, updator=18614031015), WebsiteProps(id=1205151309067428178, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1205118568116498664, code=silenceFlag, value=0, createTime=1765260062711, updateTime=1765260062711, creator=18614031015, updator=18614031015), WebsiteProps(id=1205151309029679436, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1205118568116498664, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_en_623/, createTime=1765260062701, updateTime=1765260062701, creator=18614031015, updator=18614031015), WebsiteProps(id=1205151309050650959, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1205118568116498664, code=themeColor, value=null, createTime=1765260062706, updateTime=1765260062706, creator=18614031015, updator=18614031015), WebsiteProps(id=1205151309054845264, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1205118568116498664, code=themeStyle, value=null, createTime=1765260062707, updateTime=1765260062707, creator=18614031015, updator=18614031015)])], journalTitle=中国工程机械学报, weixinUrl=null, journalUrl=null, iacademicId=null, status=1, seqNo=null, journalTitleEn=Chinese Journal of Construction Machinery, journalPhotoCn=/KlTPs3yCXsXGMqW4Jw0zg==, journalPhotoEn=61Q0qzkf783cI1Yd6RfYHA==, journalFirstLetter=C, 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/zggcjxxb/CN/Y2025/V23/I2/361, detailUrlEn=https://castjournals.cast.org.cn/joweb/zggcjxxb/EN/Y2025/V23/I2/361, pdfUrlCn=https://castjournals.cast.org.cn/joweb/zggcjxxb/CN/PDF/Y2025/V23/I2/361, pdfUrlEn=https://castjournals.cast.org.cn/joweb/zggcjxxb/EN/PDF/Y2025/V23/I2/361, aliStartDate=null, aliEndDate=null, collectionFlag=false, citedCount=null, citedUrl=null, reference=null)
收藏切换
基于改进BP神经网络的火车防吊起快速检测方法
收藏切换
PDF下载
姜军 1 , 宓为建 2
中国工程机械学报 | 性能检测、试验及故障诊断 2025,23(2): 361-365
收起
收藏切换
中国工程机械学报 | 性能检测、试验及故障诊断 2025, 23(2): 361-365
基于改进BP神经网络的火车防吊起快速检测方法
全屏
姜军1 , 宓为建2
作者信息
  • 1.上海勘测设计研究院有限公司,上海 200335
  • 2.上海海事大学 物流科学与工程研究院,上海 201306
  • 姜军(1989—),男,博士。E-mail:

A fast anti-lifting detection method for trains based on improved BP neural network
Jun JIANG1 , Weijian MI2
Affiliations
  • 1. Shanghai Investigation, Design & Research Institute Co., Ltd., Shanghai 200335, China
  • 2. Institute of Logistics Science and Engineering, Shanghai Maritime University, Shanghai 201306, China
文章导航
收藏切换

铁路集装箱堆场对于火车平板装卸作业,由于传统检测方法检测精度或检测速度不能满足要求,鲜有成熟的智能防吊起解决方案。本文提出一种基于改进反向传播(BP)神经网络的火车防吊起快速检测方法,通过获取吊具4个锁头的称重数据,建立基于BP神经网络的平板吊起检测模型,在权值调整时加入动量因子和自适应调节学习率以优化模型性能。在实际作业中测试,本方法具有较高的检出率和快速的检测速度,可为轨道吊自动化火车作业提供智能安全防护。

集装箱火车  /  平板鹰钩(F-TR)锁防吊起  /  反向传播(BP)神经网络  /  动量因子  /  自适应学习

In the railway container yard, there are few mature intelligent anti-lifting solutions available for train flatbed loading and unloading operations due to the poor detection accuracy or speed of traditional detection methods. This paper proposes a fast anti-lifting detection method for trains based on an improved back propagation (BP) neural network. By acquiring weight data from the four locks of the hoist, a flatbed lifting detection model is established using a BP neural network. During weight adjustment, a momentum factor and an adaptive learning rate are incorporated to optimize the model's performance. Through practical tests, this method demonstrates that this model achieves a high detection rate and fast detection speed, making it suitable for providing intelligent safety protection for automated rail mounted gantry in the railway container yard.

container train  /  F-TR lock anti-lifting  /  back propagation (BP) neural network  /  momentum factor  /  adaptive learning
姜军, 宓为建. 基于改进BP神经网络的火车防吊起快速检测方法. 中国工程机械学报, 2025 , 23 (2) : 361 -365 .
Jun JIANG, Weijian MI. A fast anti-lifting detection method for trains based on improved BP neural network[J]. Chinese Journal of Construction Machinery, 2025 , 23 (2) : 361 -365 .
在铁路集装箱堆场,集装箱起重机在火车车皮上卸箱的过程中,由于火车平板车皮上的锁销为鹰钩锁(F-TR锁)[1],起吊过程中若集装箱锁孔与鹰钩锁勾连,会出现起重机吊具将集装箱连同火车平板车皮一并吊起情况,通常称为吊火车事故。而在远端中控室的起重机司机很难准确迅速地发现安全隐患,一旦起重机将集装箱及火车车板一起吊起,就会发生极其严重的安全事故,轻则鹰钩锁或者集装箱锁孔损坏,重则发生火车平板被拉断,甚至发生起重机毁损情况[2]
在集装箱码头,通常通过安装于轨道吊门腿侧的激光雷达或者摄像机,采用智能识别技术来检测集卡防吊起[3-5]。而适用于集卡智能防吊起系统的技术方案因检测精度、速度不满足高要求,以及检测设备难以安装,无法移植应用于铁路集装箱堆场火车平板卸箱作业。本文提出一种使用基于反向传播(back propagation,BP)神经网络的火车F-TR锁防吊起检测方法,区别于智能集卡防吊起方案中利用激光或者视觉方案进行检测,本文提出利用吊具4个角点的重量传感器采集数据样本,建立基于人工神经网络的火车平板防吊起检测模型,并应用改进的BP学习算法对模型进行训练。作业中实时输入吊具4个锁头的称重数据至智能火车F-TR锁防吊起系统,实时检测火车平板是否被吊起。
BP神经网络是一种利用误差反向传播训练算法的多层前向网络,是迄今为止应用最为广泛的人工神经网络。网络结构包含输入层、隐含层及输出层,各层之间大部分采用全连接方式,同层神经元之间不存在相互连接,各神经元的输出值与输入值之间的关系由权值和阈值决定[6-7]。最为普遍应用的单层神经网络模型如图1所示,其包括输入层、隐含层和输出层。本文采用单层神经网络构建火车平板吊起检测模型,输入层特征参数为吊具左前、左后、右前、右后4个重量传感器采集数值,选择吊起置信度为输出层特征参数(即火车被吊起置信度为0.999 999,火车未被吊起置信度为0.000 001),即输入层为4个神经元,输出层为1个神经元。
根据调研,铁路集装箱堆场在火车平板车皮上作业,通常主要有以下4种工况:20尺空箱、20尺重箱、40尺空箱、40尺重箱;按照F-TR锁作业中的勾连情况可分为正常起吊、1个锁头勾连、2个锁头勾连、3个锁头勾连(4个锁头勾连的情况无法通过称重数据检测得出)。每种工况下分别利用安装于轨道吊吊具4个锁头的重量传感器采集的4个锁头的称重数据,共采集16轮。每轮共采集10组数据,其中选择5组加入训练样本集,5组作为测试样本集。
因轨道吊平板火车车皮作业有严格要求,在起吊过程中需要点动运行,在点动过程中,采集到的称重数据具有阶梯性的规律,轨道吊司机点动起升所产生的称重数据波动会影响检测吊起判断,如图2所示。图中,LR为轨道吊吊具左后钮锁传感器称重数据,RR为轨道吊吊具右后钮锁传感器称重数据,RF为轨道吊吊具右前钮锁传感器称重数据,LF为轨道吊吊具左前钮锁传感器称重数据。
因此,需要剔除刚起升时吊具钢丝绳未拉紧所采集到的噪声数据,对数据进行预处理,通过以下条件提取出吊具闭锁抓箱后至集装箱脱离车皮鹰钩锁期间的称重数据。
(1)单个锁头的称重数据都需>阈值。
(2)本帧4个锁头的称重数据总和>上一帧4个锁头的称重数据总和。
(3)本帧4个锁头的称重数据总和>历史4个锁头的称重数据最大值。
(4)本帧4个锁头的称重数据总和–上一帧4个锁头的称重数据总和>阈值。
对采集到的样本数据归一化处理可防止因输入绝对值过大使神经元输出饱和以致神经网络训练效果不佳。通过变换将数据换算到[–1,1]范围内,具体可表示为
式中:xi为某特征参数第i个数据;xmin为数据数组的最小值;xmax为数据数组的最大值;为归一化后的数据。
将预处理后的样本数据作为BP神经网络训练与测试的数据集。将不同轮测试数据交叉输入重构训练样本集可避免同类样本太集中而使网络训练时倾向于只建立与其匹配的隐射关系。
BP神经网络模型的性能极大取决于隐含层神经元个数,以经验确定神经元个数的取值范围[8],然后从最小神经元数逐步增加依次构建神经网络,比较各种神经网络结构的训练精度,得出最佳神经元数,具体可表示为
式中:h为隐含层神经元个数;m为输入层神经元个数,取4;n为输出层神经元数,取1;a为常数,取值范围[1,10]。代入式(2)可得隐含层神经元数范围值为[3,12]。设置训练次数为500次,分别设置隐含层神经元数为3至12,使用训练样本训练模型,可得隐含层神经元个数与网络输出误差的关系曲线,如图3所示。
可见,在隐含层神经元数的取值范围内,网络输出误差先呈现整体下降,在节点数为10时的误差达到最小,随后又出现波动。因此,本模型取隐含层节点数为10,即所构建的车板吊起检测模型的神经网络结构为4-10-1。
对BP神经网络的训练包含输入信号的正向传播和输出误差信号的反向传播两个过程。当输出误差超出精度要求时,网络沿着反向传播,调整网络中各隐含层神经元的权值,以使输出误差趋向最小,BP神经网络的训练流程如图4所示。
传统BP神经网络算法采用误差函数负梯度方向对权值系数进行修正。但由于神经网络误差曲面的复杂性,通常会出现收敛速度缓慢、陷入局部最小值等问题[9]
因此,本文通过在反向传播的权值调整时增加动量因子并引入自适应调节学习率对传统BP神经网络算法进行改进。计算过程如下:
假设神经网络在进行第t次训练,设输入变量为xt)={x1t),x2t),x3t),x4t)},神经网络的输出为zt),目标输出为zst)。则
式中:yi为隐含层第i个神经元的输出;ωij为输入层第j个神经元与隐含层第i个神经元的连接权值;θi为隐含层第i个神经元的激活阈值;ωi为隐含层第i个神经元与输出层神经元的连接权值;δ为输出层神经元的激活阈值。可通过计算实际输出与目标输出的误差et):
将所有训练样本均通过式(3)~式(5)计算误差,通过计算均方差作为神经网络训练的目标函数:
采用负梯度下降算法计算各个从隐含层到输出层的权值ωi和从输入层到隐含层的权值ωij的调整量,并跌加前一次的部分权值的调整量:
式中:α为动量系数,本文中设为0.7;ηt)为第t次学习效率,本文中取初始值为0.2;学习效率只与网络总误差有关,可基于误差均方差进行自适应调整:若第t次误差Et)>Et+1)时,则应在t+1次学习中增加其学习效率,以加快收敛;若1.04×Et)<Et+1),表明步长过大,则应在第t+1次学习中减小学习效率,以确保收敛[10]。其表达式为
在调整权值后,将训练样本数据输入式(3)~式(6)重新计算神经网络输出误差,若输出误差满足精度要求,则完成训练;若不满足,则再次反向传播调整权值。通过多次迭代运算和权值调整,直至误差精度满足精度要求为止。
模型经过训练后的最终输出即为检测防吊起置信度。设置置信度σ来判断火车平板是否被吊起。若取σ=0.8,则有:
将模型的预测结果与实际测试结果进行对比,通过计算本算法的检出率:
在国内某铁路集装箱中心站开展火车平板防吊起测试,在轨道吊吊具的4个锁头安装重量传感器,如图5所示。在作业中实时将称重数据传输至智能火车F-TR锁防吊起检测系统,实时检测火车平板是否被吊起。
实验分别采用20尺空箱、20尺重箱、40尺空箱、40尺重箱,测试正常起吊、单F-TR锁勾连、双F-TR锁勾连、三F-TR锁勾连等16种工况,实验效果及F-TR锁勾连采集到的数据波形如图6所示,实验结果数据见表1
由测试结果可知,使用改进的BP神经网络算法对于普遍的1~3个鹰钩锁勾连情况检出率可达95%(大部分误检为因三、四F-TR锁勾连时受力平均称重技术限制无法检测),平均检测时间约为133 ms。分析实验结果可得,在结果验证了基于改进BP神经网络的火车防吊起快速检测方法对普遍工况的火车平板作业F-TR锁未解锁情况的检测能力。
针对铁路集装箱堆场火车车皮作业需要智能防吊起保护系统防止集装箱及火车车板一起吊起的安全事故,传统的激光、视觉或两者融合的检测方案无法适用于火车集装箱装卸场景,本文提出了一种基于改进BP神经网络的火车防吊起快速检测方法,利用BP神经网络搭建了火车平板吊起检测模型,并针对传统学习算法的不足,对算法进行改进。得到以下结论:
(1)相比于传统学习算法,改进的BP神经网络算法具有更好的检测精度、更快的收敛速度。
(2)基于改进学习算法构建的模型检测火车平板吊起情况,误检率在5%以内,检测速度<150 ms。该方法检测精度高、速度快,表明适用于普遍工况火车集装箱装卸作业智能防吊起保护。
(3)所提出的改进BP神经网络的火车防吊起快速检测方法,可适用于普遍火车平板集装箱装卸场景,但对于集装箱4个锁孔与火车平板均未解锁的情况,通过本算法无法检测出该情况与正常起吊的差异性。可通过在轨道吊吊具4个角点安装激光测距仪检测吊具4个角点的位移数据,结合称重数据冗余计算可解决4个F-TR锁均未解锁的问题。此检测方法的火车智能防吊起保护系统已应用于国内某铁路集装箱中心站,辅助智能远程操控系统自动化火车装卸作业。
参考文献 引证文献
排序方式:
[1]
周勇,张杰,钟祾充,等. 铁路集装箱中心站多轨道吊柔性协同调度优化[J]. 交通运输系统工程与信息202222(1):133-141.
[2]
王小寒,贾玉林,蔡佳芯. 铁路集装箱中心站资源分配与作业调度联合优化[J]. 控制与决策202136(12):3063-3073.
[3]
BRINKMANN B. Operations systems of container terminals:a compendious overview handbook of terminal planning[C]// Handbook of Terminal Planning. New York,NY,USA:Springer,2011:25-39.
[4]
MI CHUANG Y GFU C H,et al. Vision-based measurement:actualities and developing trends in automated container terminals[J]. IEEE Instrumentation and Measurement Magazine202124(4):65-76.
[5]
HUANG Q FHUANG Y GZHANG Z W,et al. Truck-lifting prevention system based on vision tracking for container-lifting operation[EB/OL].(2021-12-01)[2023-08-11]. https://onlinelibrary.wiley.com/doi/10.1155/2021/9612480.
[6]
DING S FSU C YYU J Z. An optimizing BP neural network algorithm based on genetic algorithm[J]. Artificial Intelligence Review201136(2):153-162.
[7]
CUI KJING X. Research on prediction model of geotechnical parameters based on BP neural network[J]. Neural Computing & Applications201931(12):8205-8215.
[8]
KINGMA D PBA J. Adam:a method for stochastic optimization[EB/OL].(2014-12-22)[2023-08-11]. https://arxiv.org/abs/1412.6980.
[9]
LI J JSHENG V SSHU Z Y,et al. Learning from the crowd with neural net-work[C]// 2015 IEEE 14th International Conference on Machine Learning and Applications(ICMLA). Miami,FL,USA:IEEE,2015:693-698.
[10]
左志强,陈永进,慈春令. 基于MATLAB下的改进BP算法[J]. 燕山大学学报2001(2):101-104.
2025年第23卷第2期
PDF下载
80
36
引用本文
BibTeX
文章信息
  • 首发时间:2025-12-16
补充材料
相关文章
文章信息
作者
出版历史
基金
作者信息
    1.上海勘测设计研究院有限公司,上海 200335
    2.上海海事大学 物流科学与工程研究院,上海 201306
参考文献
分享链接
https://castjournals.cast.org.cn/joweb/zggcjxxb/CN/1207658078737113876
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