[1]王亭岭,赵君,查园园,等.高速铁路列控车载设备故障诊断的研究及应用[J].高速铁路技术,2024,15(03):55-61.[doi:10.12098/j.issn.1674-8247.2024.03.011]
 WANG Tingling,ZHAO Jun,ZHA Yuanyuan,et al.Study on Fault Diagnosis for Onboard Equipment in High-speed Railway Train Control Systems and Application[J].HIGH SPEED RAILWAY TECHNOLOGY,2024,15(03):55-61.[doi:10.12098/j.issn.1674-8247.2024.03.011]
点击复制

高速铁路列控车载设备故障诊断的研究及应用()
分享到:

《高速铁路技术》[ISSN:1674-8247/CN:51-1730/U]

卷:
15卷
期数:
2024年03期
页码:
55-61
栏目:
研究创新
出版日期:
2024-06-20

文章信息/Info

Title:
Study on Fault Diagnosis for Onboard Equipment in High-speed Railway Train Control Systems and Application
文章编号:
1674-8247(2024)03-0055-07
作者:
王亭岭1赵君1查园园2郑炳校1
1.华北水利水电大学, 郑州 450045;2.北京交通大学, 北京 100044
Author(s):
WANG Tingling1ZHAO Jun1ZHA Yuanyuan2ZHENG Bingxiao1
1.North China University of Water Resources and Electric Power ,Zhengzhou 450045 ,China;2.Beijing Jiaotong University , Beijing 100044 ,China
关键词:
车载设备专家知识贝叶斯网络K2算法
Keywords:
onboard equipmentexpert knowledgeBayesian networkK2 algorithm
分类号:
U284
DOI:
10.12098/j.issn.1674-8247.2024.03.011
文献标志码:
A
摘要:
列控系统中车载设备故障具有复杂性和不确定性,且数据记录非文本化,传统的基于专家知识的诊断方法效率低下且精确度不佳。贝叶斯网络(BN)在处理不确定性和相关复杂性问题方面具有显著优势,本文以CTCS3-300T型车载设备为研究对象,建立贝叶斯网络模型进行故障诊断。通过分析典型车载设备故障处理现状,提出一种结合专家知识、故障数据集和K2算法的贝叶斯网络模型研究方法;利用K2算法和最大似然估计法分别进行结构学习、参数学习,从局部到整体优化贝叶斯网络诊断模型,实现故障的快速定位;建立最优贝叶斯网络模型,并进行推理计算,其故障诊断准确率为87.1%。与传统的专家知识模型相比,最优贝叶斯网络模型的故障诊断准确率提高了37.4%。经实例分析和模型验证,该模型能够保证故障诊断结果的准确性且提高故障诊断的效率。
Abstract:
Faults in onboard equipment within railway train control systems exhibit complexity and uncertainty,compounded by the non-textual nature of recorded data. Traditional diagnosis methods based on expert knowledge often prove inefficient and inaccurate. Bayesian network(BN)excel in handling uncertainties and related complexities. This paper focuses on CTCS3-300T onboard equipment,employing a BN model for fault diagnosis. By examining current practices in addressing typical onboard equipment malfunctions,a methodology combining expert knowledge,fault datasets,and the K2 algorithm was proposed for BN model development. Utilizing K2 algorithm and maximum likelihood estimation,structure learning and parameter learning were carried out,incrementally refining the BN diagnostic model for rapid fault localization. An optimized BN model was established,achieving a fault diagnosis accuracy of 87. 1%. Compared to conventional expert-knowledge-based models,this optimal BN model enhances fault diagnosis accuracy by 37. 4%. According to the results of case analysis and model validation,the model is able to ensure fault diagnosis accuracy while significantly improving diagnostic efficiency.

参考文献/References:

[1] 孟德友,范况生. 高铁建设对区域发展影响的国内研究进展与展望[J]. 商丘师范学院学报,2021,37(12):44-49. MENG Deyou,FAN Kuangsheng. Domestic Research Progress and Prospect of the Impact of High-speed Rail Construction on Regional Development[J]. Journal of Shangqiu Normal University,2021, 37(12):44-49.
[2] 马保仁. 我国高速铁路列车运行图现状分析及展望[J]. 高速铁路技术,2021,12(5):8-11,30. MA Baoren. Analysis on Current Situation and Prospect of Train Diagram of High-speed Railway in China[J]. High Speed Railway Technology,2021,12(5):8-11,30.
[3] 赵阳,徐田华,周玉平,等. 基于贝叶斯网络的高铁信号系统车载设备故障诊断方法的研究[J]. 铁道学报,2014,36(11):48-53. ZHAO Yang,XU Tianhua,ZHOU Yuping,et al. Bayesian Network Based Fault Diagnosis System for Vehicle On-board Equipment of High-speed Railway[J]. Journal of the China Railway Society, 2014,36(11):48-53.
[4] 刘恩东,林俊亭. 车载控制器设备故障处理浅析及维护建议[J].中国新通信,2021,23(6):140-142. LIU Endong,LIN Junting. Analysis on Fault Treatment and Maintenance Suggestions of Vehicle Controller Equipment[J]. China New Telecommunications,2021,23(6):140-142.
[5] 孟寒松. 基于通信的列车运行控制系统测试研究[J]. 铁路计算机应用,2021,30(10):63-68. MENG Hansong. Test Method of Communication Based Train Control System[J]. Railway Computer Application,2021,30(10):63-68.
[6] 卢长利. 铁路电务车载设备故障应急处置存在的问题及对策研究[J]. 科技与创新,2019(7):130-131. LU Changli. Research on Problems and Countermeasures in Emergency Disposal of Railway Electric Vehicle Equipment Faults[J]. Science and Technology & Innovation,2019(7):130-131.
[7] 翁顺,吴俐滢,朱宏平,等. 基于模糊聚类的高速列车车速识别[J]. 高速铁路技术,2022,13(4):13-23,29.WENG Shun,WU Liying,ZHU Hongping,et al. Speed Recognition of High-speed Train Based on Fuzzy Clustering[J]. High Speed Railway Technology,2022,13(4):13-23,29.
[8] 张德平,张国强. 基于故障树的轨道交通车载设备可靠性分析[J]. 电子产品可靠性与环境试验,2021,39(S1):37-39. ZHANG Deping,ZHANG Guoqiang. Reliability Analysis of Rail Transit Vehicle Equipment Based on Fault Tree[J]. Electronic Product Reliability and Environmental Testing,2021,39(S1):37-39.
[9] 赵阳,徐田华. 基于文本挖掘的高铁信号系统车载设备故障诊断[J]. 铁道学报,2015,37(8):53-59. ZHAO Yang,XU Tianhua. Text Mining Based Fault Diagnosis for Vehicle On-board Equipment of High Speed Railway Signal System [J]. Journal of the China Railway Society,2015,37(8):53-59.
[10]周璐婕,党建武,王瑜鑫,等. 基于卷积神经网络的列控车载设备故障分类研究[J]. 铁道学报,2021,43(6):70-77. ZHOU Lujie,DANG Jianwu,WANG Yuxin,et al. Research on Fault Classification Method for Onboard Equipment of Train Control System Based on Convolutional Neural Network[J]. Journal of the China Railway Society,2021,43(6):70-77.
[11]刘孜学,王富斌,虞凯. 基于改进YOLOv3的铁路落石检测方法研究与实现[J]. 高速铁路技术,2022,13(3):52-56,80. LIU Zixue,WANG Fubin,YU Kai. Research and Implementation of the Railway Rockfall Detection Based on Modified YOLOv3[J]. High Speed Railway Technology,2022,13(3):52-56,80.
[12]BEHJATI S,BEIGY H. Improved K2 Algorithm for Bayesian Network Structure Learning[J]. Engineering Applications of Artificial Intelligence,2020,91 :103617.
[13]SCRUCCA L. A Fast and Efficient Modal EM Algorithm for Gaussian Mixtures[J]. Statistical Analysis and Data Mining:the ASA Data Science Journal,2021,14(4):305-314.
[14]郝建,张浩,张军政,等. 列车运行控制系统仿真测试自动化方法研究[J]. 铁道标准设计,2022,66(6):152-158. HAO Jian,ZHANG Hao,ZHANG Junzheng,et al. Research on Automatic Simulation Test Method of Train Control System[J]. Railway Standard Design,2022,66(6):152-158.
[15]江磊,王小敏,刘一骝,等. 基于动态贝叶斯网络的CTCS3-300T列控车载系统运行可靠性及可用性评估[J]. 铁道学报,2020, 42(3):85-92. JIANG Lei,WANG Xiaomin,LIU Yiliu,et al. DBN-based Operational Reliability and Availability Evaluation of CTCS3-300T Onboard System[J]. Journal of the China Railway Society,2020, 42(3):85-92.
[16]TANZINA A,NITA Y. A Probabilistic Estimation of Traffic Congestion Using Bayesian Network[J]. Measurement,2021,174.
[17]WEI Wei,ZHAO Xiaoqiang. Bi-TLLDA and CSSVM Based Fault Diagnosis of Vehicle On-board Equipment for High Speed Railway[J]. Measurement Science and Technology,2021,32(8):085005.[18]BEHJATI S,BEIGY H. Improved K2 Algorithm for Bayesian Network Structure Learning[J]. Engineering Applications of Artificial Intelligence,2020,91 :103617.
[19]MNICH K,RUDNICKI W R. All-relevant Feature Selection Using Multidimensional Filters with Exhaustive Search[J]. Information Sciences,2020,524 :277-297.
[20]徐苗,王慧玲,梁义,等. 基于K2算法的因果结构学习研究综述[J]. 伊犁师范学院学报(自然科学版),2021,15(1):51-57. XU Miao,WANG Huiling,LIANG Yi,et al. A Survey of Causal Structure Learning Based on K2 Algorithm[J]. Journal of Yili Normal University (Natural Science Edition),2021,15(1):51-57.

备注/Memo

备注/Memo:
收稿日期:2022-09-13
作者简介:王亭岭(1975-),男,副教授。
更新日期/Last Update: 2024-06-30