Analysis of Failure Features of High-Speed Automatic Train Protection System
An automatic train protection (ATP) system is the core to ensure operation safety of high-speed railway. At present, failure rate change rules of the system are not well understood and the maintenance strategy is not refined. In order to improve the protection capability and maintenance level of hig...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2021-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9540651/ |
| _version_ | 1818576619428642816 |
|---|---|
| author | Renwei Kang Junfeng Wang Jianqiu Chen Jingjing Zhou Yanzhi Pang Jianfeng Cheng |
| author_facet | Renwei Kang Junfeng Wang Jianqiu Chen Jingjing Zhou Yanzhi Pang Jianfeng Cheng |
| author_sort | Renwei Kang |
| collection | DOAJ |
| description | An automatic train protection (ATP) system is the core to ensure operation safety of high-speed railway. At present, failure rate change rules of the system are not well understood and the maintenance strategy is not refined. In order to improve the protection capability and maintenance level of high-speed trains, this paper proposes a decision tree machine learning model for failure feature extraction of ATP systems. First, system type, mean operation mileage, mean service time, etc. are selected as ATP failure feature parameters, and cumulative failure rate is selected as a model output label. Second, support vector machine, AdaBoost, artificial neural networks and decision tree model are adopted to train and test practical failure data. Performance analysis shows that decision tree learning model has better generalization ability. The accuracy of 0.9761 is significantly greater than the other machine learning models. Therefore, it is most suitable for failure features analysis. Third, interpretability analysis reveals the quantitative relationship between system failure and features. Finally, an intelligent maintenance system for ATP systems is built, which realize the refined maintenance throughout life cycle. |
| first_indexed | 2024-12-16T06:16:54Z |
| format | Article |
| id | doaj.art-40d275b8519247c3878d09ffe313a9cc |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-12-16T06:16:54Z |
| publishDate | 2021-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-40d275b8519247c3878d09ffe313a9cc2022-12-21T22:41:14ZengIEEEIEEE Access2169-35362021-01-01912873412874610.1109/ACCESS.2021.31133819540651Analysis of Failure Features of High-Speed Automatic Train Protection SystemRenwei Kang0https://orcid.org/0000-0003-3243-237XJunfeng Wang1https://orcid.org/0000-0002-5102-0736Jianqiu Chen2Jingjing Zhou3Yanzhi Pang4Jianfeng Cheng5State Key Laboratory of Rail Traffic Control and Safety, Beijing Jiaotong University, Beijing, ChinaState Key Laboratory of Rail Traffic Control and Safety, Beijing Jiaotong University, Beijing, ChinaGuangxi Key Laboratory of China-ASEAN Integrated Transport International Join, Nanning University, Nanning, ChinaNational Equities Exchange and Quotations, Beijing, ChinaGuangxi Key Laboratory of China-ASEAN Integrated Transport International Join, Nanning University, Nanning, ChinaSignal and Communication Research Institute, China Academy of Railway Sciences, Beijing, ChinaAn automatic train protection (ATP) system is the core to ensure operation safety of high-speed railway. At present, failure rate change rules of the system are not well understood and the maintenance strategy is not refined. In order to improve the protection capability and maintenance level of high-speed trains, this paper proposes a decision tree machine learning model for failure feature extraction of ATP systems. First, system type, mean operation mileage, mean service time, etc. are selected as ATP failure feature parameters, and cumulative failure rate is selected as a model output label. Second, support vector machine, AdaBoost, artificial neural networks and decision tree model are adopted to train and test practical failure data. Performance analysis shows that decision tree learning model has better generalization ability. The accuracy of 0.9761 is significantly greater than the other machine learning models. Therefore, it is most suitable for failure features analysis. Third, interpretability analysis reveals the quantitative relationship between system failure and features. Finally, an intelligent maintenance system for ATP systems is built, which realize the refined maintenance throughout life cycle.https://ieeexplore.ieee.org/document/9540651/Automatic train protection systemintelligent maintenancefailure featuremachine learningmodel interpretabilityhigh-speed train |
| spellingShingle | Renwei Kang Junfeng Wang Jianqiu Chen Jingjing Zhou Yanzhi Pang Jianfeng Cheng Analysis of Failure Features of High-Speed Automatic Train Protection System IEEE Access Automatic train protection system intelligent maintenance failure feature machine learning model interpretability high-speed train |
| title | Analysis of Failure Features of High-Speed Automatic Train Protection System |
| title_full | Analysis of Failure Features of High-Speed Automatic Train Protection System |
| title_fullStr | Analysis of Failure Features of High-Speed Automatic Train Protection System |
| title_full_unstemmed | Analysis of Failure Features of High-Speed Automatic Train Protection System |
| title_short | Analysis of Failure Features of High-Speed Automatic Train Protection System |
| title_sort | analysis of failure features of high speed automatic train protection system |
| topic | Automatic train protection system intelligent maintenance failure feature machine learning model interpretability high-speed train |
| url | https://ieeexplore.ieee.org/document/9540651/ |
| work_keys_str_mv | AT renweikang analysisoffailurefeaturesofhighspeedautomatictrainprotectionsystem AT junfengwang analysisoffailurefeaturesofhighspeedautomatictrainprotectionsystem AT jianqiuchen analysisoffailurefeaturesofhighspeedautomatictrainprotectionsystem AT jingjingzhou analysisoffailurefeaturesofhighspeedautomatictrainprotectionsystem AT yanzhipang analysisoffailurefeaturesofhighspeedautomatictrainprotectionsystem AT jianfengcheng analysisoffailurefeaturesofhighspeedautomatictrainprotectionsystem |