Article(id=1278415771466437326, tenantId=1146029695717560320, journalId=1146031787341344770, issueId=1277328335906669390, articleNumber=1003-3033(2026)05-0089-09, orderNo=null, doi=10.16265/j.cnki.issn1003-3033.2026.05.1124, pmid=null, cstr=null, oa=null, hot=null, price=null, onlineType=0, articleFormat=0, articleType=null, articleTypeStr=research-article, receivedDate=1768147200000, receivedDateStr=2026-01-12, revisedDate=1773504000000, revisedDateStr=2026-03-15, acceptedDate=null, acceptedDateStr=null, onlineDate=1782727671733, onlineDateStr=2026-06-29, pubDate=1779897600000, pubDateStr=2026-05-28, doiRegisterDate=null, doiRegisterDateStr=null, onlineIssueDate=1782727671733, onlineIssueDateStr=2026-06-29, onlineJustAcceptDate=null, onlineJustAcceptDateStr=null, onlineFirstDate=null, onlineFirstDateStr=null, sourceXml=null, magXml=null, createTime=1782727671733, creator=13701087609, updateTime=1782727671733, updator=13701087609, issue=Issue{id=1277328335906669390, tenantId=1146029695717560320, journalId=1146031787341344770, year='2026', volume='36', issue='5', pageStart='1', pageEnd='318', issueExtLink='null', onlineDate='null', pubDate='1779897600000', pubDateStr='2026-05-28', beforeIssueId=null, nextIssueId=null, price=null, status=1, issueComplete=1, articleOrder=1, issueType=1, specialIssue=null, createTime=1782468406892, creator='13701087609', updateTime=1782867658151, updator='13701087609', preIssue=null, nextIssue=null, articleTotal=null, ext={EN=IssueExt(id=1279002917143286724, tenantId=1146029695717560320, journalId=1146031787341344770, issueId=1277328335906669390, language=EN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=), CN=IssueExt(id=1279002917143286725, tenantId=1146029695717560320, journalId=1146031787341344770, issueId=1277328335906669390, language=CN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=)}, issueFiles=null, downloadFileDto=null}, startPage=89, endPage=97, ext={EN=ArticleExt(id=1278415771751649999, articleId=1278415771466437326, tenantId=1146029695717560320, journalId=1146031787341344770, language=EN, title=Fault diagnosis model for mine main hoists based on BO-XGBoost-SHAP architecture, columnId=1277328337617941059, journalTitle=China Safety Science Journal, columnName=Safety Technology and Engineering, runingTitle=null, highlight=null, articleAbstract=

To address the problems of lagging fault response and insufficient accuracy in the traditional operation and maintenance mode of mine main hoists, a fault diagnosis model for mine main hoists based on BO-XGBoost was constructed, and the SHAP method was integrated to improve the model interpretability. The Bayesian Optimization (BO) algorithm was used to optimize the hyperparameters of the eXtreme Gradient Boosting (XGBoost) model. Based on the monitoring data from an experimental mine main hoist, the XGBoost model combined with the SHAP attribution analysis method was adopted to identify the key influencing factors and their action mechanisms. The results show that compared with the baseline XGBoost model, the BO-XGBoost model increases accuracy by 4.1%, reduces log loss by 41.9%, and shortens model training time by 80.1%. Compared with traditional decision tree, random forest and LightGBM algorithms, the BO-XGBoost model improves precision by 26.5%, 11.9% and 13.6%, respectively, demonstrating excellent test accuracy.Wire rope tension, lower sheave temperature and motor voltage are the three key causal factors of faults. Different fault types are affected by different factors; for instance, excessively high main shaft vibration, motor temperature and excessively low hoisting speed provide greater positive gain for main shaft fault prediction. Three-factor interaction analysis reveals the dominant role and influence patterns of various factors during wire rope faults. The probability of wire rope faults is mainly dominated by tension, motor current and hoisting speed. Excessively low tension or current significantly increases the risk, and rising hoisting speed further aggravates the fault probability, whereas lower sheave temperature has a weak influence.

, authors=Wu Sheng1, 2, Xiaoyu Chu1, **, Minwei Wu1, authorsList=Wu Sheng, Xiaoyu Chu, Minwei Wu, authorCompany=null, correspAuthors=Xiaoyu Chu, 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, fund=null), CN=ArticleExt(id=1278415775513940708, articleId=1278415771466437326, tenantId=1146029695717560320, journalId=1146031787341344770, language=CN, title=基于BO-XGBoost-SHAP架构的矿井主提升机故障诊断模型, columnId=1277328337940902469, journalTitle=中国安全科学学报, columnName=安全技术与工程, runingTitle=null, highlight=null, articleAbstract=

为解决矿用主提升机传统运维模式中故障响应滞后、精准度不足的问题,构建基于贝叶斯优化-极限梯度提升算法(BO-XGBoost)的矿井主提升机故障诊断模型,并结合沙普利加和解释法(SHAP)增强模型的可解释性;使用贝叶斯优化(BO)算法优化XGBoost超参数;基于试验煤矿主提升机监测数据,结合XGBoost模型与SHAP归因分析方法识别关键影响因素与作用机制。研究结果表明:与基线XGBoost模型相比,BO-XGBoost模型准确率提高4.1%,对数损失降低41.9%,模型训练时间缩短80.1%;相较于传统决策树、随机森林和LightGBM算法,BO-XGBoost模型的精确率分别提升26.5%、11.9%和13.6%,展现出优异的测试准确性;钢丝绳张力、下天轮温度以及电机电压是故障发生的3个关键致因因素;不同故障类型受不同因素影响,如过高的主轴振动、电机温度以及过低的提升速度对主轴故障预测的正增益更大;三因素交互分析揭示了钢丝绳故障时各因素的主导作用及影响规律,钢丝绳故障概率主要由张力、电机电流及提升速度主导,张力或电流过低会显著增加风险,提升速度升高也会加剧故障概率,而下天轮温度影响较弱。

, authors=盛武1, 2, 储小渝1, **, 吴敏玮1, authorsList=盛武, 储小渝, 吴敏玮, authorCompany=null, correspAuthors=储小渝, authorNote=

盛 武 (1969—),男,安徽淮南人,博士,副教授,主要从事矿业安全与数据挖掘等方面的研究。E-mail:

, correspAuthorsNote=
** 储小渝(2001—),女,安徽安庆人,硕士研究生,主要研究方向为矿井设备状态监测与故障诊断。E-mail:
, copyrightStatement=null, copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=6IC3Yu46bbaL+4D20YbHUg==, magXml=CMsMx7kQi5uUM9/UlTNr+Q==, pdfUrl=null, pdf=KHkUPij7LX1mUvF8l9cV5w==, pdfFileSize=10327574, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=Ns8DGgry8uYaId0fhrrNNA==, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=P8RxB4DjBnUnHDA/rAxB4w==, mapNumber=null, fund=null)}, authors=[Author(id=1278415776180835052, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415771466437326, orderNo=0, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=wsheng116@163.com, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1278415776302469871, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415771466437326, authorId=1278415776180835052, language=EN, stringName=Wu Sheng, firstName=Wu, middleName=null, lastName=Sheng, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 2, address=1 College of Economic and Management, Anhui University of Science and Technology, Huainan Anhui 232001, China
2 State Key Laboratory of Digital Intelligent Technology for Unmanned Coal Mining, Anhui University of Science and Technology, Huainan Anhui 232001, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1278415776377967344, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415771466437326, authorId=1278415776180835052, language=CN, stringName=盛武, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 2, address=1 安徽理工大学 经济与管理学院, 安徽 淮南 232001
2 安徽理工大学 煤炭无人化开采数智技术全国重点实验室, 安徽 淮南 232001, bio={"img":"Wb0xhWeb/M4Q42TeqdCblQ==","content":"

盛 武 (1969—),男,安徽淮南人,博士,副教授,主要从事矿业安全与数据挖掘等方面的研究。E-mail:

"}, bioImg=Wb0xhWeb/M4Q42TeqdCblQ==, bioContent=

盛 武 (1969—),男,安徽淮南人,博士,副教授,主要从事矿业安全与数据挖掘等方面的研究。E-mail:

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1278415775874650853, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415771466437326, xref=1, ext=[AuthorCompanyExt(id=1278415776000479974, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415771466437326, companyId=1278415775874650853, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 College of Economic and Management, Anhui University of Science and Technology, Huainan Anhui 232001, China), AuthorCompanyExt(id=1278415776008868583, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415771466437326, companyId=1278415775874650853, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 安徽理工大学 经济与管理学院, 安徽 淮南 232001)]), AuthorCompany(id=1278415776088560360, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415771466437326, xref=2, ext=[AuthorCompanyExt(id=1278415776096948969, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415771466437326, companyId=1278415776088560360, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 State Key Laboratory of Digital Intelligent Technology for Unmanned Coal Mining, Anhui University of Science and Technology, Huainan Anhui 232001, China), AuthorCompanyExt(id=1278415776105337578, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415771466437326, companyId=1278415776088560360, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 安徽理工大学 煤炭无人化开采数智技术全国重点实验室, 安徽 淮南 232001)])]), Author(id=1278415776453464818, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415771466437326, orderNo=1, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=2209892789@qq.com, emailSecond=null, emailThird=null, correspondingAuthor=1, authorType=1, ext={EN=AuthorExt(id=1278415776533156596, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415771466437326, authorId=1278415776453464818, language=EN, stringName=Xiaoyu Chu, firstName=Xiaoyu, middleName=null, lastName=Chu, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, **, address=1 College of Economic and Management, Anhui University of Science and Technology, Huainan Anhui 232001, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1278415776617042677, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415771466437326, authorId=1278415776453464818, language=CN, stringName=储小渝, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, **, address=1 安徽理工大学 经济与管理学院, 安徽 淮南 232001, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1278415775874650853, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415771466437326, xref=1, ext=[AuthorCompanyExt(id=1278415776000479974, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415771466437326, companyId=1278415775874650853, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 College of Economic and Management, Anhui University of Science and Technology, Huainan Anhui 232001, China), AuthorCompanyExt(id=1278415776008868583, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415771466437326, companyId=1278415775874650853, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 安徽理工大学 经济与管理学院, 安徽 淮南 232001)])]), Author(id=1278415776705123063, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415771466437326, 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=1278415776826757881, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415771466437326, authorId=1278415776705123063, language=EN, stringName=Minwei Wu, firstName=Minwei, middleName=null, lastName=Wu, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 College of Economic and Management, Anhui University of Science and Technology, Huainan Anhui 232001, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1278415776914838266, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415771466437326, authorId=1278415776705123063, language=CN, stringName=吴敏玮, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 安徽理工大学 经济与管理学院, 安徽 淮南 232001, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1278415775874650853, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415771466437326, xref=1, ext=[AuthorCompanyExt(id=1278415776000479974, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415771466437326, companyId=1278415775874650853, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 College of Economic and Management, Anhui University of Science and Technology, Huainan Anhui 232001, China), AuthorCompanyExt(id=1278415776008868583, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415771466437326, companyId=1278415775874650853, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 安徽理工大学 经济与管理学院, 安徽 淮南 232001)])])], keywords=[Keyword(id=1278415777032278779, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415771466437326, language=EN, orderNo=1, keyword=Bayesian Optimization-eXtreme Gradient Boosting (BO-XGBoost)), Keyword(id=1278415777120359164, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415771466437326, language=EN, orderNo=2, keyword=SHapley Additive exPlanations (SHAP)), Keyword(id=1278415777200050941, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415771466437326, language=EN, orderNo=3, keyword=mine main hoist), Keyword(id=1278415777279742718, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415771466437326, language=EN, orderNo=4, keyword=fault diagnosis), Keyword(id=1278415777376211711, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415771466437326, language=EN, orderNo=5, keyword=cause location), Keyword(id=1278415777468486400, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415771466437326, language=CN, orderNo=1, keyword=贝叶斯优化-极限梯度提升算法(BO-XGBoost)), Keyword(id=1278415777564955393, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415771466437326, language=CN, orderNo=2, keyword=沙普利加和解释法(SHAP)), Keyword(id=1278415777648841474, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415771466437326, language=CN, orderNo=3, keyword=矿井主提升机), Keyword(id=1278415777732727555, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415771466437326, language=CN, orderNo=4, keyword=故障诊断), Keyword(id=1278415777812419332, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415771466437326, language=CN, orderNo=5, keyword=致因定位)], refs=[Reference(id=1278415784267453219, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415771466437326, doi=null, pmid=null, pmcid=null, year=2023, volume=49, issue=10, pageStart=75, pageEnd=86, url=null, language=null, rfNumber=[1], rfOrder=0, authorNames=王琛, 杨岸, journalName=工矿自动化, refType=null, unstructuredReference=王琛, 杨岸. 矿井提升机健康状态评估与预测系统研究[J]. 工矿自动化, 2023, 49(10):75-86., articleTitle=矿井提升机健康状态评估与预测系统研究, refAbstract=null), Reference(id=1278415784359727908, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415771466437326, doi=null, pmid=null, pmcid=null, year=2023, volume=49, issue=10, pageStart=75, pageEnd=86, url=null, language=null, rfNumber=[1], rfOrder=1, authorNames=Wang Chen, Yang An, journalName=Journal of Mine Automation, refType=null, unstructuredReference=Wang Chen, Yang An. Research on the health evaluation and prediction system for mine hoists[J]. Journal of Mine Automation, 2023, 49(10):75-86., articleTitle=Research on the health evaluation and prediction system for mine hoists, refAbstract=null), Reference(id=1278415784435225381, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415771466437326, doi=null, pmid=null, pmcid=null, year=2025, volume=61, issue=17, pageStart=114, pageEnd=123, url=null, language=null, rfNumber=[2], rfOrder=2, authorNames=邵海东, 肖一鸣, 钟翔, journalName=机械工程学报, refType=null, unstructuredReference=邵海东, 肖一鸣, 钟翔, . 面向可信机械故障诊断的模型校准方法[J]. 机械工程学报, 2025, 61(17):114-123., articleTitle=面向可信机械故障诊断的模型校准方法, refAbstract=null), Reference(id=1278415784519111462, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415771466437326, doi=null, pmid=null, pmcid=null, year=2025, volume=61, issue=17, pageStart=114, pageEnd=123, url=null, language=null, rfNumber=[2], rfOrder=3, authorNames=Shao Haidong, Xiao Yiming, Zhong Xiang, journalName=Journal of Mechanical Engineering, refType=null, unstructuredReference=Shao Haidong, Xiao Yiming, Zhong Xiang, et al. Model calibration method for trustworthy mechanical fault diagnosis[J]. Journal of Mechanical Engineering, 2025, 61(17):114-123., articleTitle=Model calibration method for trustworthy mechanical fault diagnosis, refAbstract=null), Reference(id=1278415784590414631, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415771466437326, doi=null, pmid=null, pmcid=null, year=2020, volume=39, issue=2, pageStart=282, pageEnd=287, url=null, language=null, rfNumber=[3], rfOrder=4, authorNames=黄帅, 吴娟, 李琳琳, journalName=机械科学与技术, refType=null, unstructuredReference=黄帅, 吴娟, 李琳琳, . 粒子群优化的SVM提升钢丝绳故障诊断[J]. 机械科学与技术, 2020, 39 (2): 282-287., articleTitle=粒子群优化的SVM提升钢丝绳故障诊断, refAbstract=null), Reference(id=1278415784653329192, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415771466437326, doi=null, pmid=null, pmcid=null, year=2020, volume=39, issue=2, pageStart=282, pageEnd=287, url=null, language=null, rfNumber=[3], rfOrder=5, authorNames=Huang Shuai, Wu Juan, Li Linlin, journalName=Mechanical Science and Technology for Aerospace Engineering, refType=null, unstructuredReference=Huang Shuai, Wu Juan, Li Linlin, et al. Fault detection of hoisting wireope with SVM optimized by PSO[J]. Mechanical Science and Technology for Aerospace Engineering, 2020, 39 (2): 282-287., articleTitle=Fault detection of hoisting wireope with SVM optimized by PSO, refAbstract=null), Reference(id=1278415784720438057, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415771466437326, doi=null, pmid=null, pmcid=null, year=2020, volume=40, issue=4, pageStart=1310, pageEnd=1319, url=null, language=null, rfNumber=[4], rfOrder=6, authorNames=李兵, 韩睿, 何怡刚, journalName=中国电机工程学报, refType=null, unstructuredReference=李兵, 韩睿, 何怡刚, . 改进随机森林算法在电机轴承故障诊断中的应用[J]. 中国电机工程学报, 2020, 40(4): 1310-1319,1 422., articleTitle=改进随机森林算法在电机轴承故障诊断中的应用, refAbstract=null), Reference(id=1278415784791741226, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415771466437326, doi=null, pmid=null, pmcid=null, year=2020, volume=40, issue=4, pageStart=1310, pageEnd=1319, url=null, language=null, rfNumber=[4], rfOrder=7, authorNames=Li Bing, Han Rui, He Yigang, journalName=Proceedings of the CSEE, refType=null, unstructuredReference=Li Bing, Han Rui, He Yigang, et al. Applications of the improved random forest algorithm in fault diagnosis of motor bearings[J]. Proceedings of the CSEE, 2020, 40(4): 1310-1319,1 422., articleTitle=Applications of the improved random forest algorithm in fault diagnosis of motor bearings, refAbstract=null), Reference(id=1278415784867238699, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415771466437326, doi=null, pmid=null, pmcid=null, year=2024, volume=34, issue=7, pageStart=83, pageEnd=90, url=null, language=null, rfNumber=[5], rfOrder=8, authorNames=徐菁, 闫尊昊, 杨松森, journalName=中国安全科学学报, refType=null, unstructuredReference=徐菁, 闫尊昊, 杨松森, . 基于EMI-CNN的建筑施工模板支撑体系节点健康监测[J]. 中国安全科学学报, 2024, 34 (7): 83-90., articleTitle=基于EMI-CNN的建筑施工模板支撑体系节点健康监测, refAbstract=null), Reference(id=1278415784976290604, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415771466437326, doi=null, pmid=null, pmcid=null, year=2024, volume=34, issue=7, pageStart=83, pageEnd=90, url=null, language=null, rfNumber=[5], rfOrder=9, authorNames=Xu Jing, Yan Zunhao, Yang Songsen, journalName=China Safety Science Journal, refType=null, unstructuredReference=Xu Jing, Yan Zunhao, Yang Songsen, et al. Health monitoring of joints in construction formwork support systems based on EMI-CNN[J]. China Safety Science Journal, 2024, 34 (7): 83-90., articleTitle=Health monitoring of joints in construction formwork support systems based on EMI-CNN, refAbstract=null), Reference(id=1278415785043399469, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415771466437326, doi=null, pmid=null, pmcid=null, year=2023, volume=55, issue=3, pageStart=814, pageEnd=826, url=null, language=null, rfNumber=[6], rfOrder=10, authorNames=Choi J, Lee S J, journalName=Nuclear Engineering and Technology, refType=null, unstructuredReference=Choi J, Lee S J. RNN-based integrated system for real-time sensor fault detection and fault-informed accident diagnosis in nuclear power plant accidents[J]. Nuclear Engineering and Technology, 2023, 55 (3): 814-826., articleTitle=RNN-based integrated system for real-time sensor fault detection and fault-informed accident diagnosis in nuclear power plant accidents, refAbstract=null), Reference(id=1278415785118896942, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415771466437326, doi=null, pmid=null, pmcid=null, year=2021, volume=19, issue=3, pageStart=254, pageEnd=259, url=null, language=null, rfNumber=[7], rfOrder=11, authorNames=马怀祥, 冯旭威, 李东升, journalName=中国工程机械学报, refType=null, unstructuredReference=马怀祥, 冯旭威, 李东升, . 基于CNN和XGBoost的滚动轴承故障诊断方法[J]. 中国工程机械学报, 2021, 19(3): 254-259., articleTitle=基于CNN和XGBoost的滚动轴承故障诊断方法, refAbstract=null), Reference(id=1278415785186005807, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415771466437326, doi=null, pmid=null, pmcid=null, year=2021, volume=19, issue=3, pageStart=254, pageEnd=259, url=null, language=null, rfNumber=[7], rfOrder=12, authorNames=Ma Huaixiang, Feng Xuwei, Li Dongsheng, journalName=Chinese Journal of Construction Machinery, refType=null, unstructuredReference=Ma Huaixiang, Feng Xuwei, Li Dongsheng, et al. Fault diagnosis method of rolling bearing based on CNN and XGBoost[J]. Chinese Journal of Construction Machinery, 2021, 19(3): 254-259., articleTitle=Fault diagnosis method of rolling bearing based on CNN and XGBoost, refAbstract=null), Reference(id=1278415785257308976, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415771466437326, doi=null, pmid=null, pmcid=null, year=2025, volume=38, issue=5, pageStart=209, pageEnd=223, url=null, language=null, rfNumber=[8], rfOrder=13, authorNames=陈英, 朱加勋, 田毅, journalName=中国公路学报, refType=null, unstructuredReference=陈英, 朱加勋, 田毅, . 基于K-Means-XGBoost-SHAP集成化框架的交通事故严重程度致因分析[J]. 中国公路学报, 2025, 38 (5): 209-223., articleTitle=基于K-Means-XGBoost-SHAP集成化框架的交通事故严重程度致因分析, refAbstract=null), Reference(id=1278415785349583665, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415771466437326, doi=null, pmid=null, pmcid=null, year=2025, volume=38, issue=5, pageStart=209, pageEnd=223, url=null, language=null, rfNumber=[8], rfOrder=14, authorNames=Chen Ying, Zhu Jiaxun, Tian Yi, journalName=China Journal of Highway and Transport, refType=null, unstructuredReference=Chen Ying, Zhu Jiaxun, Tian Yi, et al. Analysis of factors contributing to traffic accident severity based on an integrated framework of K-Means-XGBoost-SHAP[J]. China Journal of Highway and Transport 2025, 38 (5): 209-223., articleTitle=Analysis of factors contributing to traffic accident severity based on an integrated framework of K-Means-XGBoost-SHAP, refAbstract=null), Reference(id=1278415785441858354, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415771466437326, doi=null, pmid=null, pmcid=null, year=2025, volume=57, issue=5, pageStart=1, pageEnd=13, url=null, language=null, rfNumber=[9], rfOrder=15, authorNames=熊峰, 陈腾盛, 邓楚兵, journalName=工程科学与技术, refType=null, unstructuredReference=熊峰, 陈腾盛, 邓楚兵, . 基于BO-XGBoost算法的气凝胶混凝土力学和保温性能预测方法[J]. 工程科学与技术, 2025, 57 (5): 1-13., articleTitle=基于BO-XGBoost算法的气凝胶混凝土力学和保温性能预测方法, refAbstract=null), Reference(id=1278415785500578611, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415771466437326, doi=null, pmid=null, pmcid=null, year=2025, volume=57, issue=5, pageStart=1, pageEnd=13, url=null, language=null, rfNumber=[9], rfOrder=16, authorNames=Xiong Feng, Chen Tengsheng, Deng Chubing, journalName=Advanced Engineering Sciences, refType=null, unstructuredReference=Xiong Feng, Chen Tengsheng, Deng Chubing, et al. Prediction method for the mechanical and thermal insulation properties of aerogel concrete based on the BO-XGBoost algorithm[J]. Advanced Engineering Sciences, 2025, 57(5):1-13., articleTitle=Prediction method for the mechanical and thermal insulation properties of aerogel concrete based on the BO-XGBoost algorithm, refAbstract=null), Reference(id=1278415785576076084, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415771466437326, doi=null, pmid=null, pmcid=null, year=2017, volume=null, issue=null, pageStart=4768, pageEnd=4777, url=null, language=null, rfNumber=[10], rfOrder=17, authorNames=Lundberg S M, Lee S I, journalName=Proceedings of the 31st International Conference on Neural Information Processing Systems, refType=null, unstructuredReference=Lundberg S M, Lee S I. A unified approach to interpreting model predictions[C]. Proceedings of the 31st International Conference on Neural Information Processing Systems. December 4-9, 2017,Long Beach,California,USA. ACM,2017:4768-4777., articleTitle=A unified approach to interpreting model predictions, refAbstract=null), Reference(id=1278415785634796341, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415771466437326, doi=null, pmid=null, pmcid=null, year=2025, volume=35, issue=4, pageStart=110, pageEnd=119, url=null, language=null, rfNumber=[11], rfOrder=18, authorNames=刘亚栋, 刘贤, 胡贺松, journalName=中国安全科学学报, refType=null, unstructuredReference=刘亚栋, 刘贤, 胡贺松, . 基于可解释机器学习模型的基坑围护墙变形影响因素分析[J]. 中国安全科学学报, 2025, 35 (4): 110-119., articleTitle=基于可解释机器学习模型的基坑围护墙变形影响因素分析, refAbstract=null), Reference(id=1278415785718682422, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415771466437326, doi=null, pmid=null, pmcid=null, year=2025, volume=35, issue=4, pageStart=110, pageEnd=119, url=null, language=null, rfNumber=[11], rfOrder=19, authorNames=Liu Yadong, Liu Xian, Hu Hesong, journalName=China Safety Science Journal, refType=null, unstructuredReference=Liu Yadong, Liu Xian, Hu Hesong, et al. Analysis of feature importance to retaining wall deformation of excavation using interpretable machine learning model[J]. China Safety Science Journal, 2025, 35 (4): 110-119., articleTitle=Analysis of feature importance to retaining wall deformation of excavation using interpretable machine learning model, refAbstract=null), Reference(id=1278415785794179895, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415771466437326, doi=null, pmid=null, pmcid=null, year=2025, volume=42, issue=8, pageStart=1615, pageEnd=1624, url=null, language=null, rfNumber=[12], rfOrder=20, authorNames=陈竞, 张宏伟, 王凯旋, journalName=机电工程, refType=null, unstructuredReference=陈竞, 张宏伟, 王凯旋. 基于 SSA-CNN-BiLSTM 的提升机制动系统故障诊断模型[J]. 机电工程, 2025, 42 (8): 1615-1624., articleTitle=基于 SSA-CNN-BiLSTM 的提升机制动系统故障诊断模型, refAbstract=null), Reference(id=1278415785865483064, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415771466437326, doi=null, pmid=null, pmcid=null, year=2025, volume=42, issue=8, pageStart=1615, pageEnd=1624, url=null, language=null, rfNumber=[12], rfOrder=21, authorNames=Chen Jing, Zhang Hongwei, Wang Kaixuan, journalName=Journal of Mechanical & Electrical Engineering, refType=null, unstructuredReference=Chen Jing, Zhang Hongwei, Wang Kaixuan. Fault diagnosis model of hoist braking system based on SSA-CNN-BiLSTM[J]. Journal of Mechanical & Electrical Engineering, 2025, 42 (8): 1615-1624., articleTitle=Fault diagnosis model of hoist braking system based on SSA-CNN-BiLSTM, refAbstract=null)], funds=[Fund(id=1278415784045155105, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415771466437326, awardId=71971003, language=CN, fundingSource=国家自然科学基金资助(71971003), fundOrder=null, country=null), Fund(id=1278415784116458274, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415771466437326, awardId=2024cxcysj081, language=CN, fundingSource=2024年度安徽省新时代育人质量工程项目(2024cxcysj081), fundOrder=null, country=null)], companyList=[AuthorCompany(id=1278415775874650853, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415771466437326, xref=1, ext=[AuthorCompanyExt(id=1278415776000479974, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415771466437326, companyId=1278415775874650853, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 College of Economic and Management, Anhui University of Science and Technology, Huainan Anhui 232001, China), AuthorCompanyExt(id=1278415776008868583, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415771466437326, companyId=1278415775874650853, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 安徽理工大学 经济与管理学院, 安徽 淮南 232001)]), AuthorCompany(id=1278415776088560360, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415771466437326, xref=2, ext=[AuthorCompanyExt(id=1278415776096948969, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415771466437326, companyId=1278415776088560360, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 State Key Laboratory of Digital Intelligent Technology for Unmanned Coal Mining, Anhui University of Science and Technology, Huainan Anhui 232001, China), AuthorCompanyExt(id=1278415776105337578, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415771466437326, companyId=1278415776088560360, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 安徽理工大学 煤炭无人化开采数智技术全国重点实验室, 安徽 淮南 232001)])], figs=[ArticleFig(id=1278415777946637061, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415771466437326, language=EN, label=Fig.1, caption=Architecture diagram of BO-XGBoost-SHAP, figureFileSmall=Ikl07Q1QVKL8pQuiXwYStQ==, figureFileBig=Ns8DGgry8uYaId0fhrrNNA==, tableContent=null), ArticleFig(id=1278415779628552966, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415771466437326, language=CN, label=图1, caption=BO-XGBoost-SHAP架构, figureFileSmall=Ikl07Q1QVKL8pQuiXwYStQ==, figureFileBig=Ns8DGgry8uYaId0fhrrNNA==, tableContent=null), ArticleFig(id=1278415779884405511, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415771466437326, language=EN, label=Fig.2, caption=On-site physical object, figureFileSmall=nmUq8/EJkQgS1sYSgtmMhg==, figureFileBig=sB04cpxSqnPf3XgPiHwWBQ==, tableContent=null), ArticleFig(id=1278415779989263112, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415771466437326, language=CN, label=图2, caption=现场实物, figureFileSmall=nmUq8/EJkQgS1sYSgtmMhg==, figureFileBig=sB04cpxSqnPf3XgPiHwWBQ==, tableContent=null), ArticleFig(id=1278415780068954889, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415771466437326, language=EN, label=Fig.3, caption=Logarithmic loss graph of model training, figureFileSmall=gpK/1GvutrQ7N7x/cWvsNw==, figureFileBig=HEZmMZoeFPR+xC+eRspQyQ==, tableContent=null), ArticleFig(id=1278415780198978314, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415771466437326, language=CN, label=图3, caption=模型训练对数损失图, figureFileSmall=gpK/1GvutrQ7N7x/cWvsNw==, figureFileBig=HEZmMZoeFPR+xC+eRspQyQ==, tableContent=null), ArticleFig(id=1278415780362556171, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415771466437326, language=EN, label=Fig.4, caption=Model classification prediction results, figureFileSmall=Xqj9qqnPhpJPjr7evYxiUA==, figureFileBig=PDLoYC80H8GjnpLa8aLxIA==, tableContent=null), ArticleFig(id=1278415780425470732, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415771466437326, language=CN, label=图4, caption=模型分类预测结果, figureFileSmall=Xqj9qqnPhpJPjr7evYxiUA==, figureFileBig=PDLoYC80H8GjnpLa8aLxIA==, tableContent=null), ArticleFig(id=1278415780517745421, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415771466437326, language=EN, label=Fig.5, caption=Ranking of feature importance, figureFileSmall=SBBj6HIJBY0gf8oIV7wDRA==, figureFileBig=vojQxcQhJKKe5hFb8hi4Rg==, tableContent=null), ArticleFig(id=1278415780593242894, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415771466437326, language=CN, label=图5, caption=特征重要度排序, figureFileSmall=SBBj6HIJBY0gf8oIV7wDRA==, figureFileBig=vojQxcQhJKKe5hFb8hi4Rg==, tableContent=null), ArticleFig(id=1278415780660351759, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415771466437326, language=EN, label=Fig.6, caption=SHAP value heat map of sample features, figureFileSmall=zDpDr1yW58nvqULlz2SLIw==, figureFileBig=8TmM2LswFQYH/oh07VOArA==, tableContent=null), ArticleFig(id=1278415780740043536, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415771466437326, language=CN, label=图6, caption=样本特征的SHAP值热图, figureFileSmall=zDpDr1yW58nvqULlz2SLIw==, figureFileBig=8TmM2LswFQYH/oh07VOArA==, tableContent=null), ArticleFig(id=1278415780819735313, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415771466437326, language=EN, label=Fig.7, caption=Summary chart of SHAP under fault classification, figureFileSmall=qmnvjoC5UwwT/eQ9Uql4hQ==, figureFileBig=TdlJ4mRG793b2f3YmPoCqA==, tableContent=null), ArticleFig(id=1278415780891038482, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415771466437326, language=CN, label=图7, caption=故障分类下SHAP摘要图, figureFileSmall=qmnvjoC5UwwT/eQ9Uql4hQ==, figureFileBig=TdlJ4mRG793b2f3YmPoCqA==, tableContent=null), ArticleFig(id=1278415780953953043, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415771466437326, language=EN, label=Fig.8, caption=SHAP feature contribution waterfall chart, figureFileSmall=oYnaJDMQtsMCrFsRQQ7I7w==, figureFileBig=SC9ZArUA0v+ShVpKYo0qtg==, tableContent=null), ArticleFig(id=1278415781029450516, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415771466437326, language=CN, label=图8, caption=SHAP特征贡献瀑布图, figureFileSmall=oYnaJDMQtsMCrFsRQQ7I7w==, figureFileBig=SC9ZArUA0v+ShVpKYo0qtg==, tableContent=null), ArticleFig(id=1278415781117530901, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415771466437326, language=EN, label=Fig.9, caption=Interaction analysis of key factors, figureFileSmall=2d9A+8QoV5N8r+m7/a8cew==, figureFileBig=IUWjHkO/ebjf40a5rhvXtA==, tableContent=null), ArticleFig(id=1278415781188834070, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415771466437326, language=CN, label=图9, caption=重要因素交互分析, figureFileSmall=2d9A+8QoV5N8r+m7/a8cew==, figureFileBig=IUWjHkO/ebjf40a5rhvXtA==, tableContent=null), ArticleFig(id=1278415781297885975, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415771466437326, language=EN, label=Table 1, caption=

Distribution of categories

, figureFileSmall=null, figureFileBig=null, tableContent=
类型 类别 数量/组
正常 0 1 613
闸盘故障 1 120
主轴故障 2 104
电机故障 3 121
天轮故障 4 99
钢丝绳故障 5 103
), ArticleFig(id=1278415781406937880, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415771466437326, language=CN, label=表1, caption=

类别分布情况

, figureFileSmall=null, figureFileBig=null, tableContent=
类型 类别 数量/组
正常 0 1 613
闸盘故障 1 120
主轴故障 2 104
电机故障 3 121
天轮故障 4 99
钢丝绳故障 5 103
), ArticleFig(id=1278415781495018265, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415771466437326, language=EN, label=Table 2, caption=

Partial data

, figureFileSmall=null, figureFileBig=null, tableContent=
序号 X1/℃ X2/(mm/s) X3/℃ X4/℃ X5/℃ X6/N X7/(m/s) X8/A X9/V
1 45.00 0.98 65.00 53.00 50.00 12 095.67 8.58 158.08 377.10
2 45.50 1.09 65.42 52.98 50.37 12 072.59 8.00 136.20 377.19
3 45.98 1.11 65.83 52.91 50.74 11 777.28 8.29 132.88 376.85
2158 43.95 1.57 69.92 47.39 51.48 11 793.79 8.83 131.03 377.34
2159 43.50 1.19 69.83 47.23 51.14 11 965.58 8.60 155.43 381.39
2160 47.00 0.92 70.00 48.02 49.54 12 104.57 8.85 170.00 370.00
), ArticleFig(id=1278415781591487258, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415771466437326, language=CN, label=表2, caption=

部分数据

, figureFileSmall=null, figureFileBig=null, tableContent=
序号 X1/℃ X2/(mm/s) X3/℃ X4/℃ X5/℃ X6/N X7/(m/s) X8/A X9/V
1 45.00 0.98 65.00 53.00 50.00 12 095.67 8.58 158.08 377.10
2 45.50 1.09 65.42 52.98 50.37 12 072.59 8.00 136.20 377.19
3 45.98 1.11 65.83 52.91 50.74 11 777.28 8.29 132.88 376.85
2158 43.95 1.57 69.92 47.39 51.48 11 793.79 8.83 131.03 377.34
2159 43.50 1.19 69.83 47.23 51.14 11 965.58 8.60 155.43 381.39
2160 47.00 0.92 70.00 48.02 49.54 12 104.57 8.85 170.00 370.00
), ArticleFig(id=1278415781717316379, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415771466437326, language=EN, label=Table 3, caption=

Range of hyperparameters and optimal parameters for bayesian optimization

, figureFileSmall=null, figureFileBig=null, tableContent=
超参数 描述 取值范围 取值结果
max_depth 树的最大深度 (3,10) 4
learning_rate 学习率 (0.01,0.3) 0.3
n_estimators 树的数量 (50,500) 89
gamma 最小损失减少阈值 (0,5) 2.9
min_child_weight 子节点最小权重和 (1,10) 3
subsample 样本采样比例 (0.5,1.0) 1
colsample_bytree 特征采样比例 (0.5,1.0) 1
reg_alpha L1正则化项 (0,10) 0.0
reg_lambda L2正则化项 (0,10) 1.2
), ArticleFig(id=1278415781901865756, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415771466437326, language=CN, label=表3, caption=

贝叶斯优化的超参数的取值范围及最优参数结果

, figureFileSmall=null, figureFileBig=null, tableContent=
超参数 描述 取值范围 取值结果
max_depth 树的最大深度 (3,10) 4
learning_rate 学习率 (0.01,0.3) 0.3
n_estimators 树的数量 (50,500) 89
gamma 最小损失减少阈值 (0,5) 2.9
min_child_weight 子节点最小权重和 (1,10) 3
subsample 样本采样比例 (0.5,1.0) 1
colsample_bytree 特征采样比例 (0.5,1.0) 1
reg_alpha L1正则化项 (0,10) 0.0
reg_lambda L2正则化项 (0,10) 1.2
), ArticleFig(id=1278415781977363229, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415771466437326, language=EN, label=Table 4, caption=

Comparison of model results before and after optimization

, figureFileSmall=null, figureFileBig=null, tableContent=
模型 A R P F1
XGBoost 0.914 4 0.914 4 0.915 3 0.912 3
BO-XGBoost 0.951 4 0.951 4 0.952 6 0.948 8
), ArticleFig(id=1278415782044472094, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415771466437326, language=CN, label=表4, caption=

优化前后模型结果对比

, figureFileSmall=null, figureFileBig=null, tableContent=
模型 A R P F1
XGBoost 0.914 4 0.914 4 0.915 3 0.912 3
BO-XGBoost 0.951 4 0.951 4 0.952 6 0.948 8
), ArticleFig(id=1278415782128358175, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415771466437326, language=EN, label=Table 5, caption=

Comparison of results from various machine learning models

, figureFileSmall=null, figureFileBig=null, tableContent=
评价指标 决策树 随机森林 LightGBM XGBoost BO-XGBoost
A 0.904 3 0.935 2 0.935 2 0.914 4 0.951 4
R 0.720 0 0.812 4 0.818 2 0.914 4 0.951 4
P 0.752 9 0.851 5 0.838 5 0.915 3 0.952 6
F1 0.732 0 0.829 7 0.827 7 0.912 3 0.948 8
训练时长/s 0.019 4 0.384 1 3.742 9 0.580 0 0.110 0
), ArticleFig(id=1278415782329684768, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415771466437326, language=CN, label=表5, caption=

多种机器学习模型结果对比

, figureFileSmall=null, figureFileBig=null, tableContent=
评价指标 决策树 随机森林 LightGBM XGBoost BO-XGBoost
A 0.904 3 0.935 2 0.935 2 0.914 4 0.951 4
R 0.720 0 0.812 4 0.818 2 0.914 4 0.951 4
P 0.752 9 0.851 5 0.838 5 0.915 3 0.952 6
F1 0.732 0 0.829 7 0.827 7 0.912 3 0.948 8
训练时长/s 0.019 4 0.384 1 3.742 9 0.580 0 0.110 0
)], attaches=null, journal=Journal(id=1123942128916217864, delFlag=0, nameCn=中国安全科学学报, nameEn=China Safety Science Journal, nameHistory1=null, nameHistory2=null, issn=1003-3033, eissn=, cn=11-2865/X, coden=null, periodic=0, language=CN, oaType=0, ccby=null, superviseOffice=null, ownerOffice=null, pubOffice=null, editorOffice=null, officeType=null, aims=null, clcCode=null, officeProv=null, officeCity=null, officeAddr=null, officeZip=null, officeEmail=null, officePhone=null, editDirector=null, officeDirector=null, officeDirectorPhone=null, officeStaffNum=null, officeEmpNum=null, coverPicUrl=fkqsFM6VKlHC4gCtS5XqTw==, journalPrice=null, startedYear=null, abbrevIsoEn=Chin Saf Sci J, journalRemark=null, publicationField=null, createdTime=null, updatedTime=1784015834644, createdBy=null, updatedBy=13041195026, firstLetterCn=Z, firstLetterEn=Z, subjectCode=Engineering, subjectName=工程, subjectCodeEn=Engineering, subjectNameEn=null, picCn=fkqsFM6VKlHC4gCtS5XqTw==, picEn=SHn9HgqSxtJrOcAxqD++4Q==, jcr=null, cjcr=null, exts=[JournalExt(id=1283818719495308010, language=CN, name=中国安全科学学报, nameHistory1=null, nameHistory2=null, managedBy=中国科学技术协会, sponsoredBy=中国职业安全健康协会, publishedBy=《中国安全科学学报》编辑部, editorOffice=, officeProv=null, officeCity=null, officeAddr=, officeZip=, editDirector=, officeDirector=null, officePhone=null, coverPicUrl=null, journalRemark=, submitArticleUrl=null, websiteUrl=http://www.cssjj.com.cn/, createdTime=1784015834926, updatedTime=1784015834926, createdBy=13041195026, updatedBy=13041195026, submissionGuidelinesUrl=http://www.cssjj.com.cn/CN/column/item15.shtml, submissionAuthorUrl=https://zgaqkxxbauthor.manuscriptcloud.com/login, submissionEditorUrl=https://zgaqkxxbeditor.manuscriptcloud.com/login, submissionReviewUrl=https://zgaqkxxbauthor.manuscriptcloud.com/login, submissionCeEditorUrl=https://zgaqkxxbeditor.manuscriptcloud.com/login, submissionAeEditorUrl=https://zgaqkxxbeditor.manuscriptcloud.com/login, option={"copyright":""}), JournalExt(id=1283818719541445355, language=EN, name=China Safety Science Journal, 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=http://www.cssjj.com.cn/EN/1003-3033/home.shtml, createdTime=1784015834937, updatedTime=1784015834937, createdBy=13041195026, updatedBy=13041195026, submissionGuidelinesUrl=https://synbioj.cip.com.cn/EN/column/column3.shtml, submissionAuthorUrl=https://zgaqkxxbauthor.manuscriptcloud.com/login, submissionEditorUrl=https://zgaqkxxbeditor.manuscriptcloud.com/login, submissionReviewUrl=https://zgaqkxxbauthor.manuscriptcloud.com/login, submissionCeEditorUrl=https://zgaqkxxbeditor.manuscriptcloud.com/login, submissionAeEditorUrl=https://zgaqkxxbeditor.manuscriptcloud.com/login, option={"copyright":""})], databaseList=null, tenantJournalId=1146031787341344770, websiteList=[Website(id=1148243202345263519, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1146031787341344770, 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/zgaqkxxb/CN, language=CN, createTime=1751692112766, createBy=18614031015, updateTime=1753502583634, updateBy=18614031015, name=《中国安全科学学报》中文站点, tplId=1146099689490845704, title=中国安全科学学报, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1148618794941046792, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1148243202345263519, code=articleTextType, value=kx, createTime=1751781661020, updateTime=1751781661020, creator=18614031015, updator=18614031015), WebsiteProps(id=1148618794911686661, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1148243202345263519, code=banner, value=null, createTime=1751781661012, updateTime=1751781661012, creator=18614031015, updator=18614031015), WebsiteProps(id=1148618794894909444, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1148243202345263519, code=logo, value=https://castjournals.cast.org.cn/joweb/kjdb/CN/file/pic?fileId=tui0IVO9FMwB61HHtX5scg==, createTime=1751781661008, updateTime=1751781661008, creator=18614031015, updator=18614031015), WebsiteProps(id=1148618794932658183, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1148243202345263519, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/kjdb/CN/file/pic, createTime=1751781661017, updateTime=1751781661017, creator=18614031015, updator=18614031015), WebsiteProps(id=1148618794924269574, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1148243202345263519, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_cn_619/, createTime=1751781661015, updateTime=1751781661015, creator=18614031015, updator=18614031015)]), Website(id=1155836763751993353, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1146031787341344770, 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/zgaqkxxb/EN, language=EN, createTime=1753502558893, createBy=18614031015, updateTime=1753524450387, updateBy=18614031015, name=《中国安全科学学报》英文站点, tplId=1146101810881728533, title=China Safety Science Journal, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1155895925743669425, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1155836763751993353, code=articleTextType, value=kx, createTime=1753516664205, updateTime=1753516664205, creator=18614031015, updator=18614031015), WebsiteProps(id=1155895925722697902, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1155836763751993353, code=banner, value=null, createTime=1753516664200, updateTime=1753516664200, creator=18614031015, updator=18614031015), WebsiteProps(id=1155895925714309293, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1155836763751993353, code=logo, value=https://castjournals.cast.org.cn/joweb/kjdb/CN/file/pic?fileId=tui0IVO9FMwB61HHtX5scg==, createTime=1753516664198, updateTime=1753516664198, creator=18614031015, updator=18614031015), WebsiteProps(id=1155895925735280816, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1155836763751993353, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/kjdb/CN/file/pic, createTime=1753516664203, updateTime=1753516664203, creator=18614031015, updator=18614031015), WebsiteProps(id=1155895925731086511, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1155836763751993353, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_cn_619/, createTime=1753516664202, updateTime=1753516664202, creator=18614031015, updator=18614031015)])], journalTitle=中国安全科学学报, weixinUrl=null, journalUrl=null, iacademicId=null, status=1, seqNo=null, journalTitleEn=China Safety Science Journal, journalPhotoCn=fkqsFM6VKlHC4gCtS5XqTw==, journalPhotoEn=SHn9HgqSxtJrOcAxqD++4Q==, journalFirstLetter=Z, journalRecommend=null, journalNew=null, journalCollection=1, 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, interPubPlatform=, interPubPlatformUrl=null), detailUrlCn=https://castjournals.cast.org.cn/joweb/zgaqkxxb/CN/10.16265/j.cnki.issn1003-3033.2026.05.1124, detailUrlEn=https://castjournals.cast.org.cn/joweb/zgaqkxxb/EN/10.16265/j.cnki.issn1003-3033.2026.05.1124, pdfUrlCn=https://castjournals.cast.org.cn/joweb/zgaqkxxb/CN/PDF/10.16265/j.cnki.issn1003-3033.2026.05.1124, pdfUrlEn=https://castjournals.cast.org.cn/joweb/zgaqkxxb/EN/PDF/10.16265/j.cnki.issn1003-3033.2026.05.1124, aliStartDate=0, aliEndDate=0, collectionFlag=false, citedCount=null, citedUrl=null, previewStatus=0, delFlag=0, hasFullText=1, orderTime=1779897600000, fullTextJson=null, articleText=null, reference=null)
收藏切换
基于BO-XGBoost-SHAP架构的矿井主提升机故障诊断模型
收藏切换
PDF下载
盛武 1, 2 , 储小渝 1, ** , 吴敏玮 1
中国安全科学学报 | 安全技术与工程 2026,36(5): 89-97
收起
收藏切换
中国安全科学学报 |安全技术与工程 2026 , 36 (5) : 89 -97
基于BO-XGBoost-SHAP架构的矿井主提升机故障诊断模型
全屏
[Author(id=1278415776180835052, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415771466437326, orderNo=0, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=wsheng116@163.com, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1278415776302469871, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415771466437326, authorId=1278415776180835052, language=EN, stringName=Wu Sheng, firstName=Wu, middleName=null, lastName=Sheng, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 2, address=1 College of Economic and Management, Anhui University of Science and Technology, Huainan Anhui 232001, China
2 State Key Laboratory of Digital Intelligent Technology for Unmanned Coal Mining, Anhui University of Science and Technology, Huainan Anhui 232001, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1278415776377967344, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415771466437326, authorId=1278415776180835052, language=CN, stringName=盛武, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 2, address=1 安徽理工大学 经济与管理学院, 安徽 淮南 232001
2 安徽理工大学 煤炭无人化开采数智技术全国重点实验室, 安徽 淮南 232001, bio={"img":"Wb0xhWeb/M4Q42TeqdCblQ==","content":"

盛 武 (1969—),男,安徽淮南人,博士,副教授,主要从事矿业安全与数据挖掘等方面的研究。E-mail:

"}, bioImg=Wb0xhWeb/M4Q42TeqdCblQ==, bioContent=

盛 武 (1969—),男,安徽淮南人,博士,副教授,主要从事矿业安全与数据挖掘等方面的研究。E-mail:

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1278415775874650853, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415771466437326, xref=1, ext=[AuthorCompanyExt(id=1278415776000479974, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415771466437326, companyId=1278415775874650853, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 College of Economic and Management, Anhui University of Science and Technology, Huainan Anhui 232001, China), AuthorCompanyExt(id=1278415776008868583, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415771466437326, companyId=1278415775874650853, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 安徽理工大学 经济与管理学院, 安徽 淮南 232001)]), AuthorCompany(id=1278415776088560360, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415771466437326, xref=2, ext=[AuthorCompanyExt(id=1278415776096948969, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415771466437326, companyId=1278415776088560360, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 State Key Laboratory of Digital Intelligent Technology for Unmanned Coal Mining, Anhui University of Science and Technology, Huainan Anhui 232001, China), AuthorCompanyExt(id=1278415776105337578, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415771466437326, companyId=1278415776088560360, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 安徽理工大学 煤炭无人化开采数智技术全国重点实验室, 安徽 淮南 232001)])]), Author(id=1278415776453464818, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415771466437326, orderNo=1, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=2209892789@qq.com, emailSecond=null, emailThird=null, correspondingAuthor=1, authorType=1, ext={EN=AuthorExt(id=1278415776533156596, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415771466437326, authorId=1278415776453464818, language=EN, stringName=Xiaoyu Chu, firstName=Xiaoyu, middleName=null, lastName=Chu, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, **, address=1 College of Economic and Management, Anhui University of Science and Technology, Huainan Anhui 232001, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1278415776617042677, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415771466437326, authorId=1278415776453464818, language=CN, stringName=储小渝, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, **, address=1 安徽理工大学 经济与管理学院, 安徽 淮南 232001, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1278415775874650853, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415771466437326, xref=1, ext=[AuthorCompanyExt(id=1278415776000479974, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415771466437326, companyId=1278415775874650853, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 College of Economic and Management, Anhui University of Science and Technology, Huainan Anhui 232001, China), AuthorCompanyExt(id=1278415776008868583, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415771466437326, companyId=1278415775874650853, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 安徽理工大学 经济与管理学院, 安徽 淮南 232001)])]), Author(id=1278415776705123063, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415771466437326, 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=1278415776826757881, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415771466437326, authorId=1278415776705123063, language=EN, stringName=Minwei Wu, firstName=Minwei, middleName=null, lastName=Wu, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 College of Economic and Management, Anhui University of Science and Technology, Huainan Anhui 232001, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1278415776914838266, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415771466437326, authorId=1278415776705123063, language=CN, stringName=吴敏玮, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 安徽理工大学 经济与管理学院, 安徽 淮南 232001, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1278415775874650853, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415771466437326, xref=1, ext=[AuthorCompanyExt(id=1278415776000479974, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415771466437326, companyId=1278415775874650853, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 College of Economic and Management, Anhui University of Science and Technology, Huainan Anhui 232001, China), AuthorCompanyExt(id=1278415776008868583, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415771466437326, companyId=1278415775874650853, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 安徽理工大学 经济与管理学院, 安徽 淮南 232001)])])]
盛武1, 2 , 储小渝1, ** , 吴敏玮1
作者信息
  • 1 安徽理工大学 经济与管理学院, 安徽 淮南 232001
  • 2 安徽理工大学 煤炭无人化开采数智技术全国重点实验室, 安徽 淮南 232001
通讯作者:
** 储小渝(2001—),女,安徽安庆人,硕士研究生,主要研究方向为矿井设备状态监测与故障诊断。E-mail:
作者简介:

盛 武 (1969—),男,安徽淮南人,博士,副教授,主要从事矿业安全与数据挖掘等方面的研究。E-mail:

Fault diagnosis model for mine main hoists based on BO-XGBoost-SHAP architecture
Wu Sheng1, 2 , Xiaoyu Chu1, ** , Minwei Wu1
Affiliations
  • 1 College of Economic and Management, Anhui University of Science and Technology, Huainan Anhui 232001, China
  • 2 State Key Laboratory of Digital Intelligent Technology for Unmanned Coal Mining, Anhui University of Science and Technology, Huainan Anhui 232001, China
出版时间: 2026-05-28 doi: 10.16265/j.cnki.issn1003-3033.2026.05.1124
文章导航
收藏切换

为解决矿用主提升机传统运维模式中故障响应滞后、精准度不足的问题,构建基于贝叶斯优化-极限梯度提升算法(BO-XGBoost)的矿井主提升机故障诊断模型,并结合沙普利加和解释法(SHAP)增强模型的可解释性;使用贝叶斯优化(BO)算法优化XGBoost超参数;基于试验煤矿主提升机监测数据,结合XGBoost模型与SHAP归因分析方法识别关键影响因素与作用机制。研究结果表明:与基线XGBoost模型相比,BO-XGBoost模型准确率提高4.1%,对数损失降低41.9%,模型训练时间缩短80.1%;相较于传统决策树、随机森林和LightGBM算法,BO-XGBoost模型的精确率分别提升26.5%、11.9%和13.6%,展现出优异的测试准确性;钢丝绳张力、下天轮温度以及电机电压是故障发生的3个关键致因因素;不同故障类型受不同因素影响,如过高的主轴振动、电机温度以及过低的提升速度对主轴故障预测的正增益更大;三因素交互分析揭示了钢丝绳故障时各因素的主导作用及影响规律,钢丝绳故障概率主要由张力、电机电流及提升速度主导,张力或电流过低会显著增加风险,提升速度升高也会加剧故障概率,而下天轮温度影响较弱。

贝叶斯优化-极限梯度提升算法(BO-XGBoost)  /  沙普利加和解释法(SHAP)  /  矿井主提升机  /  故障诊断  /  致因定位

To address the problems of lagging fault response and insufficient accuracy in the traditional operation and maintenance mode of mine main hoists, a fault diagnosis model for mine main hoists based on BO-XGBoost was constructed, and the SHAP method was integrated to improve the model interpretability. The Bayesian Optimization (BO) algorithm was used to optimize the hyperparameters of the eXtreme Gradient Boosting (XGBoost) model. Based on the monitoring data from an experimental mine main hoist, the XGBoost model combined with the SHAP attribution analysis method was adopted to identify the key influencing factors and their action mechanisms. The results show that compared with the baseline XGBoost model, the BO-XGBoost model increases accuracy by 4.1%, reduces log loss by 41.9%, and shortens model training time by 80.1%. Compared with traditional decision tree, random forest and LightGBM algorithms, the BO-XGBoost model improves precision by 26.5%, 11.9% and 13.6%, respectively, demonstrating excellent test accuracy.Wire rope tension, lower sheave temperature and motor voltage are the three key causal factors of faults. Different fault types are affected by different factors; for instance, excessively high main shaft vibration, motor temperature and excessively low hoisting speed provide greater positive gain for main shaft fault prediction. Three-factor interaction analysis reveals the dominant role and influence patterns of various factors during wire rope faults. The probability of wire rope faults is mainly dominated by tension, motor current and hoisting speed. Excessively low tension or current significantly increases the risk, and rising hoisting speed further aggravates the fault probability, whereas lower sheave temperature has a weak influence.

Bayesian Optimization-eXtreme Gradient Boosting (BO-XGBoost)  /  SHapley Additive exPlanations (SHAP)  /  mine main hoist  /  fault diagnosis  /  cause location
盛武, 储小渝, 吴敏玮. 基于BO-XGBoost-SHAP架构的矿井主提升机故障诊断模型. 中国安全科学学报, 2026 , 36 (5) : 89 -97 . DOI: 10.16265/j.cnki.issn1003-3033.2026.05.1124
Wu Sheng, Xiaoyu Chu, Minwei Wu. Fault diagnosis model for mine main hoists based on BO-XGBoost-SHAP architecture[J]. China Safety Science Journal, 2026 , 36 (5) : 89 -97 . DOI: 10.16265/j.cnki.issn1003-3033.2026.05.1124
矿井主提升机是煤矿运输系统的核心设备,基于监测数据对其进行一体化精准故障诊断与致因定位,对实现煤矿智能化、保障生产系统安全高效运行至关重要[1]
近年来,随着人工智能技术的突破性发展,机器学习在工业设备故障诊断领域的应用普及率显著提升[2]。早期多采用支持向量机[3]、随机森林[4]等传统算法,通过人工提取振动、电流等信号的时域、频域特征分类。随着深度学习的兴起,卷积神经网络[5]、循环神经网络[6]等模型被用于自动特征学习,但存在训练成本高、过拟合以及风险大等问题。极端梯度提升树(eXtreme Gradient Boosting,XGBoost)作为一种集成学习算法,因其处理高维数据能力强、泛化性能优异,逐渐在工业故障诊断中受到关注[7]。然而,XGBoost算法的性能对超参数(如学习率、树的深度)敏感,传统网格搜索或随机搜索调参效率低且易陷入局部最优。机器学习“黑箱式”逻辑过程,制约着应用效果,模型可解释性成为工业场景落地的关键需求。沙普利加和解释法(SHapley Additive exPlanations,SHAP)方法基于博弈论中的Shapley值,能够量化输入特征对预测结果的贡献度,为复杂系统模型提供全局与局部解释[8],文献检索结果显示,其在矿山设备诊断中的应用尚处于探索阶段。现有研究多聚焦于算法性能对比,缺乏对模型决策逻辑与矿山设备知识融合的深入分析。
鉴于此,笔者拟以矿井主提升机为对象,提出一种融合贝叶斯优化(Bayesian Optimization,BO)与XGBoost的智能故障诊断模型,并通过SHAP方法揭示模型逻辑过程及决策依据,以期构建一个“故障类型识别与致因定位”一体化高精度与强工业可解释性的故障诊断模型,提升矿井主提升机智能运维的可靠性与实用性。
XGBoost是一种基于梯度提升框架的集成学习算法,通过迭代优化决策树模型与正则化策略,实现高精度预测。BO是一种高效的参数优化方法[9],可通过概率模型与迭代寻优搜索全局最优解,且能显著减少目标函数评估次数。
SHAP算法建立在Game Theory中的Shapley值理论基础上,该理论最初用于衡量在合作博弈中每个玩家对最终收益的贡献值,将Shapley值应用到机器学习模型解释中,形成SHAP算法,为解决机器学习模型的黑盒问题提供新思路[10]。文中采用的是适合于树模型的SHAP变种方法—TreeSHAP,利用树结构特性,通过路径遍历和加权平均快速计算Shapley值[11]
模型架构如图1所示,首先,采集现场主提升机相关运行数据以及仿真数据建立数据库,并按照8∶2比例将数据划分为训练集和测试集,训练集用于模型参数调整,测试集用于评估模型泛化能力;其次在训练集中使用BO算法优化模型的超参数,通过多次迭代获得最优参数组合;然后使用优化后的模型进行故障诊断,通过各种模型评估指标,验证模型的适应性与有效性;最后,使用SHAP可解释性分析解析结果。
为评估机器学习模型的性能,采用以下4个评价指标进行评估:准确率A、召回率R、精确率PF1分数。
数据来源于HBZZ煤矿矿井主提升机的实际运行数据,现场实物如图2所示。
受现场设备配置限制,该矿仅部署温度、振动、电流等传感器,据此采集闸盘温度、电机电流、主轴振动等特征参数,覆盖闸盘、主轴、电机等5类故障,并由维护团队依据历史维修记录完成标签标注。现场数据以正常样本为主,故障样本偏少。为此,通过仿真模拟5类故障并获取对应运行数据[12],采用合成少数类过采样技术进行样本扩增。在特征空间内对少数类故障样本进行线性插值生成新样本,而非简单复制原始信号,可有效避免过拟合,提升模型诊断鲁棒性。
数据集具体类别分布情况见表1。部分数据见表2表2中,X1-X5分别为闸盘温度、主轴振动、电机温度、上天轮温度、下天轮温度,X6-X9分别为钢丝绳张力、提升速度、电机电流、电机电压。
XGBoost模型拥有多个超参数,它们对模型的计算精度有着不同程度的影响,超参数优化的结果见表3
图3为优化前的XGBoost算法与经BO优化后的XGBoost算法的训练轨迹差异,经超参数调优的BO-XGBoost展现出更优的收敛特性,其目标函数值在15次迭代周期内即达到全局最优,较原始模型实现41.9%的损失函数降幅,且收敛过程的稳定性显著增强。
使用测试集分别测试XGBoost模型和BO-XGBoost模型。测试集中包含432组样本数据,其中正常样本323组,闸盘故障样本24组,主轴故障样本24组,电机故障样本21组,天轮故障样本20组,钢丝绳故障样本20组。2种模型的混淆矩阵如图4所示。
图4a可以看出,以正常样本为例,在323组正常样本中,317组被正确分类,3组正常样本被预测为闸盘故障,1组正常样本被预测为主轴故障,1组正常样本被预测为电机故障,1组正常样本被预测为钢丝绳故障。从图4b可以看出,同样以正常样本为例,323组正常样本全部被正确分类。对比结果表明:BO-XGBoost模型的分类效果明显优于XGBoost模型。
表4为2种算法在矿井主提升机故障诊断中的多维度性能评估结果。试验数据表明:BO-XGBoost 模型在预测准确率指标上实现95%的检测精度,较基线模型提升4.1%。此外,该优化模型的RPF1分数等核心指标均有提升,其中,F1分数较原模型提高6.3%。该结果验证了BO优化框架的有效性,其通过智能参数搜索机制,可显著提升故障诊断的综合判别能力。
为验证BO-XGBoost模型在矿井主提升机故障诊断中的有效性,选取多种典型机器学习分类器进行横向对比。基于相同数据集,各算法在相同试验条件下完成模型训练与验证,表5为不同算法的性能对比数据。
表5可知:在矿井主提升机故障诊断中,BO-XGBoost算法在ARPF1分数等核心评估指标上均表现最优;决策树虽具有最高训练效率(0.019 4s),但分类性能显著滞后;随机森林与LightGBM的A相近,但后者训练用时较长,且两者综合性能较BO-XGBoost仍存在差距。试验结果表明:通过BO-XGBoost模型,在提高原模型计算效率的同时,将A提升至95.1%,多维性能评估指标较对比算法也有提升。
图5为降序排列各特征SHAP值绝对均值的总和,从全局视角揭示不同输入特征对模型预测结果的影响程度排序。由图5可知:影响最大的分别是钢丝绳张力、下天轮温度和电机电压,而提升速度和电机温度相对影响较小;各类别故障的主导特征存在差异,可以快速实现故障致因定位。
不同故障类型中影响因素有着一定差异性,采用SHAP值热图进行可视化分析,全局样本特征的SHAP值热图如图6所示,闸盘故障中闸盘温度、主轴故障中主轴振动、电机故障中电机电压、天轮故障中钢丝绳张力以及钢丝绳故障中钢丝绳张力对模型预测具有显著贡献,表明这些特征在故障类型致因定位与可解释性分析中具有重要作用。
为进一步表征输入特征对故障类别预测的贡献度与作用效果,采用TreeSHAP方法分析各故障类别下特征对诊断结果的边际影响,从而快速实现故障的致因定位。图7为5种故障条件下,重要度排名前5的特征对预测结果的影响程度。图7中,每个点代表一个样本,横坐标为SHAP值,颜色渐变对应特征取值大小;纵轴特征按SHAP重要度由高到低自上而下排列。
闸盘故障类型如图7a所示,在闸盘故障中,对预测结果影响最大的特征分别是闸盘温度、下天轮温度和上天轮温度。以闸盘温度变量为例,红色区域主要在SHAP值为正值区域,表明温度越高,对闸盘故障预测的正增益越明显。蓝色区域主要在SHAP值为负值区域,表明温度越低,对闸盘故障预测的负增益效果越突出;主轴故障类型如图7b所示,在主轴故障中,过高的主轴振动、电机温度以及过低的提升速度对故障预测的正增益越大;由图7c可知:过高的电机电压和过低的电机电流都会让电机故障预测的正增益效果更突出;由图7d可知:过高的钢丝绳张力和过高的上下天轮温度会增加故障发生概率;钢丝绳故障类型如图7e所示,钢丝绳张力越小、电机电流越小,对故障预测的正增益效果越突出。
考虑到输入特征在不同故障类型中的SHAP值存在差异,为深入解析输入特征对特定故障类别的差异化作用机制,在5种故障类型中各随机选择一个故障样本,通过构建局部解释模型量化各特征对目标故障类型的具体影响路径,SHAP特征贡献瀑布图如图8所示。
图8中,横轴为模型输出SHAP值,纵轴按特征重要性降序排列。故障样本属性值标注于特征左侧,红色代表特征对预测结果呈正向贡献,蓝色为负向贡献,对应数值为该特征的SHAP值。其中,E[f(x)]为模型基准值,f(x)为模型输出值。如图8a所示,闸盘温度、上下天轮温度对闸盘故障预测有显著正向贡献,其中闸盘温度贡献最大;该样本预测值高于基线值,属于闸盘故障类别的倾向性更强。如图8b所示,主轴振动、提升速度对主轴故障预测呈显著负向贡献,其中主轴振动负向贡献最大;该样本预测值低于基线值,属于主轴故障类别的倾向性较弱。电机故障样本如图8c所示,电机电流、电压对电机故障预测有显著正向贡献,其中电机电流贡献最大;该样本预测值高于基线值,属于电机故障类别的倾向性更强。由图8d可知:钢丝绳张力、上下天轮温度对天轮故障预测有显著正向贡献,其中钢丝绳张力贡献最大;该样本预测值高于基线值,属于天轮故障类别的倾向性更强。由图8e可知:钢丝绳张力、电机电流对钢丝绳故障预测有显著正向贡献,其中钢丝绳张力贡献最大;该样本预测值高于基线值,属于钢丝绳故障类别的倾向性更强。
为解析多变量协同作用与故障发生概率的关联,构建三阶交互效应分析框架。结合现场运维反馈,钢丝绳故障影响最为严重,其中,钢丝绳张力与电机电流为关键主导因素。选取上述2个核心变量,分别与提升速度、下天轮温度2个次要关键变量组成交互组合,分析其协同作用对钢丝绳故障发生概率的影响机制,重要因素交互效应如图9所示。
图9a可知:当钢丝绳张力和电机电流都较小时,提升速度越快,SHAP值显著升高(黄色区域)表明发生该类故障的概率越大。这可能是因为电机电流较小时,电机无法正常为钢丝绳提供稳定的拉力,此时提升速度过快,钢丝绳可能会出现过度的弹性伸长,导致钢丝绳内部的应力分布不均匀,长期处于这种状态,钢丝绳容易产生疲劳损伤,如钢丝的断裂、局部变形等。
图9b可知:当钢丝绳张力和电机电流较小时,该类故障发生的概率更大,且与下天轮温度的关系不大。这可能是因为虽然温度变化可能会影响钢丝绳的材质性能和润滑效果,但其他因素(张力过小等)在故障发生中起主导作用,温度变化对钢丝绳性能的影响相对较小。
1) 相较于传统XGBoost模型,BO-XGBoost模型准确率提升4.1%,对数损失大幅降低41.9%,且训练效率显著优化。在横向对比中,其精准率全面优于决策树、随机森林与LightGBM等模型,表现出高水平的测试准确性。
2) 运用TreeSHAP方法分析特征集合对诊断结果的边际贡献,发现钢丝绳张力、下天轮温度以及电机电压是导致故障发生的最重要的3个因素。但不同故障类型的主要影响因素存在差异,钢丝绳张力是天轮故障和钢丝绳故障发生的关键影响因素,闸盘温度、主轴振动以及电机电压分别对闸盘故障、主轴故障和电机故障有较大影响。
3) 3因素交互分析发现:在发生钢丝绳故障时,钢丝绳张力以及电机电流起到主导作用,过小的钢丝绳张力和过低的电机电流会大幅增加故障发生的概率,同时随着提升速度的升高,故障概率也会变大。
  • 国家自然科学基金资助(71971003)
  • 2024年度安徽省新时代育人质量工程项目(2024cxcysj081)
参考文献 引证文献
排序方式:
[1]
王琛, 杨岸. 矿井提升机健康状态评估与预测系统研究[J]. 工矿自动化, 2023, 49(10):75-86.
Wang Chen, Yang An. Research on the health evaluation and prediction system for mine hoists[J]. Journal of Mine Automation, 2023, 49(10):75-86.
[2]
邵海东, 肖一鸣, 钟翔, . 面向可信机械故障诊断的模型校准方法[J]. 机械工程学报, 2025, 61(17):114-123.
Shao Haidong, Xiao Yiming, Zhong Xiang, et al. Model calibration method for trustworthy mechanical fault diagnosis[J]. Journal of Mechanical Engineering, 2025, 61(17):114-123.
[3]
黄帅, 吴娟, 李琳琳, . 粒子群优化的SVM提升钢丝绳故障诊断[J]. 机械科学与技术, 2020, 39 (2): 282-287.
Huang Shuai, Wu Juan, Li Linlin, et al. Fault detection of hoisting wireope with SVM optimized by PSO[J]. Mechanical Science and Technology for Aerospace Engineering, 2020, 39 (2): 282-287.
[4]
李兵, 韩睿, 何怡刚, . 改进随机森林算法在电机轴承故障诊断中的应用[J]. 中国电机工程学报, 2020, 40(4): 1310-1319,1 422.
Li Bing, Han Rui, He Yigang, et al. Applications of the improved random forest algorithm in fault diagnosis of motor bearings[J]. Proceedings of the CSEE, 2020, 40(4): 1310-1319,1 422.
[5]
徐菁, 闫尊昊, 杨松森, . 基于EMI-CNN的建筑施工模板支撑体系节点健康监测[J]. 中国安全科学学报, 2024, 34 (7): 83-90.
Xu Jing, Yan Zunhao, Yang Songsen, et al. Health monitoring of joints in construction formwork support systems based on EMI-CNN[J]. China Safety Science Journal, 2024, 34 (7): 83-90.
[6]
Choi J, Lee S J. RNN-based integrated system for real-time sensor fault detection and fault-informed accident diagnosis in nuclear power plant accidents[J]. Nuclear Engineering and Technology, 2023, 55 (3): 814-826.
[7]
马怀祥, 冯旭威, 李东升, . 基于CNN和XGBoost的滚动轴承故障诊断方法[J]. 中国工程机械学报, 2021, 19(3): 254-259.
Ma Huaixiang, Feng Xuwei, Li Dongsheng, et al. Fault diagnosis method of rolling bearing based on CNN and XGBoost[J]. Chinese Journal of Construction Machinery, 2021, 19(3): 254-259.
[8]
陈英, 朱加勋, 田毅, . 基于K-Means-XGBoost-SHAP集成化框架的交通事故严重程度致因分析[J]. 中国公路学报, 2025, 38 (5): 209-223.
Chen Ying, Zhu Jiaxun, Tian Yi, et al. Analysis of factors contributing to traffic accident severity based on an integrated framework of K-Means-XGBoost-SHAP[J]. China Journal of Highway and Transport 2025, 38 (5): 209-223.
[9]
熊峰, 陈腾盛, 邓楚兵, . 基于BO-XGBoost算法的气凝胶混凝土力学和保温性能预测方法[J]. 工程科学与技术, 2025, 57 (5): 1-13.
Xiong Feng, Chen Tengsheng, Deng Chubing, et al. Prediction method for the mechanical and thermal insulation properties of aerogel concrete based on the BO-XGBoost algorithm[J]. Advanced Engineering Sciences, 2025, 57(5):1-13.
[10]
Lundberg S M, Lee S I. A unified approach to interpreting model predictions[C]. Proceedings of the 31st International Conference on Neural Information Processing Systems. December 4-9, 2017,Long Beach,California,USA. ACM,2017:4768-4777.
[11]
刘亚栋, 刘贤, 胡贺松, . 基于可解释机器学习模型的基坑围护墙变形影响因素分析[J]. 中国安全科学学报, 2025, 35 (4): 110-119.
Liu Yadong, Liu Xian, Hu Hesong, et al. Analysis of feature importance to retaining wall deformation of excavation using interpretable machine learning model[J]. China Safety Science Journal, 2025, 35 (4): 110-119.
[12]
陈竞, 张宏伟, 王凯旋. 基于 SSA-CNN-BiLSTM 的提升机制动系统故障诊断模型[J]. 机电工程, 2025, 42 (8): 1615-1624.
Chen Jing, Zhang Hongwei, Wang Kaixuan. Fault diagnosis model of hoist braking system based on SSA-CNN-BiLSTM[J]. Journal of Mechanical & Electrical Engineering, 2025, 42 (8): 1615-1624.
2026年第36卷第5期
PDF下载
200
83
引用本文
BibTeX
文章信息
doi: 10.16265/j.cnki.issn1003-3033.2026.05.1124
  • 接收时间:2026-01-12
  • 首发时间:2026-06-29
  • 出版时间:2026-05-28
补充材料
相关文章
文章信息
作者
出版历史
  • 收稿日期:2026-01-12
  • 修回日期:2026-03-15
基金
国家自然科学基金资助(71971003)
2024年度安徽省新时代育人质量工程项目(2024cxcysj081)
作者信息
    1 安徽理工大学 经济与管理学院, 安徽 淮南 232001
    2 安徽理工大学 煤炭无人化开采数智技术全国重点实验室, 安徽 淮南 232001

通讯作者:

** 储小渝(2001—),女,安徽安庆人,硕士研究生,主要研究方向为矿井设备状态监测与故障诊断。E-mail:
参考文献
分享链接
https://castjournals.cast.org.cn/joweb/zgaqkxxb/CN/10.16265/j.cnki.issn1003-3033.2026.05.1124
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