LI Yang-qing1,2， LIN Hai-xiang1,2
（1. School of Automation and Electrical Engineering, Lanzhou Jiaotong University, Lanzhou 730070, China； 2. Rail Transit Electrical Automation Engineering Laboratory of Gansu Province, Lanzhou Jiaotong University, Lanzhou 730070, China）
Abstract： Radio block center (RBC) system is the core equipment of China train control system-3 (CTCS-3). Now, the fault analysis of RBC system mainly depends on manual work, and the diagnostic results are inaccurate and inefficient. Therefore, the intelligent fault diagnosis method of RBC system based on one-hot model, kernel principal component analysis (KPCA) and self-organizing map (SOM) network was proposed. Firstly, the fault document matrix based on one-hot model was constructed by the fault feature lexicon selected manually and fault tracking record table. Secondly, the KPCA method was used to reduce the dimension and noise of the fault document matrix to avoid information redundancy. Finally, the processed data were input into the SOM network to train the KPCA-SOM fault classification model. Compared with back propagation (BP) neural network algorithm and SOM network algorithm, common fault patterns of train control RBC system can be effectively distinguished by KPCA-SOM intelligent diagnosis model, and the accuracy and processing efficiency are further improved.
Key words： radio block center (RBC) system; fault diagnosis; self-organizing map (SOM); kernel principal component (KPCA)
CLD number： U284.92 doi： 10.3969/j.issn.1674-8042.2020.02.008
References
［1］Zhang J W, Lu Z X, Zhou Z F, et al. RBC log analysis of abnormal train stopping. Railway Communication Signals, 2013, 49(7): 32-34.
［2］Guo Y Z, Yan L B. Analysis of equipment problems in radio blocking center (RBC) of Beijing-Shanghai high-speed railway. Railway Communication Signal, 2012, 48(8): 17-20.
［3］Guo J, Yang Y, Wang X M, et al. Fault diagnosis method for RBC system of high speed railway train control equipment rireless blocking center. CN Patent: 105629962A, 2016-06-01.
［4］Lin H X. Signal monitoring system principle and engineering application. Beijing: Chinese Railway Press, 2015: 198-218.
［5］Liang X, Wang H F, Guo J, et al. Fault diagnosis method for train control equipment based on Bayesian network. Journal of Railways, 2017, 39(8): 93-100.
［6］Zhao Y, Xu T H, Zhou Y P, et al. Research on fault diagnosis methods for vehicle-borne equipment of high speed railway signal system based on bayesian network. Journal of Railways, 2014, 36(11): 48-53.
［7］Zhang X, Du X S, Liu C Y. Research and implementation of fault diagnosis expert system for station signal control equipment. Journal of Railways, 2009, 31(3): 43-49.
［8］Huang Z W, Wei X X, Liu Z. Research on track circuit fault diagnosis based on fuzzy neural network. Journal of Railways, 2012, 34(11): 54-59.
［9］Lin H X, Li Y Q. Hidden-security-risk analysis and fault location improvement for high-speed railway switch. Journal of Railway Science and Engineering, 2018, 15(9): 2217-2223.
［10］Zhang H Y. Case based reasoning method for fault diagnosis of train control RBC system. Beijing: Beijing Jiaotong University, 2016: 12-36.
［11］Yang Z, Yun X, Wang X Q. Fault reasoning and diagnosis technology based on ACO&CBR. Advanced Materials Research, 2013, 655: 1722-1729.
［12］Liu Y, Chen L. Mechanical fault diagnosis of vacuum circuit breaker based on SOM. Journal of Electrical Technology, 2017, 32(5): 49-54.
［13］Chen X Y, Yam X F. Fault diagnosis in chemical process based on self-organizing map integrated with fisher discriminant analysis. Chinese Journal of Chemical Engineering (English Version), 2013, 21(4): 382-387.
［14］Yang T G, Gui W H. Fault diagnosis of induction motor based on KPCA and RVM. Journal of Motor and Control, 2016, 20(9): 89-95.
［15］Zou Y F, Wu W L, Li Z Y. Clustering analysis of low voltage fault arc based on self-organizing mapping neural network. Chinese Journal of Scientific Instrument, 2010, 31(3): 571-576.
［16］Zhang X N, Lei W, Tang C H, et al. A cluster analysis method based on molecular structure design theory. Vibration and Impact, 2018, 37(15): 78-83.
［17］Guo Q J, Yu H B, Nie Y Y, et al. Joint time-frequency and kernel principal component based SOM for machine maintenance. Advances in Neural Networks, 2006, 39(73): 1144-1154.
基于KPCA-SOM网络的列控RBC系统故障诊断方法
李阳庆1,2， 林海香1,2
（1. 兰州交通大学 自动化与电气工程学院， 甘肃 兰州 730070；2. 甘肃省轨道交通电气自动化工程实验室（兰州交通大学）， 甘肃 兰州 730070）
摘 要： 无线闭塞中心(RBC)系统是CTCS-3级列控系统的核心设备， 在现场其故障分析主要依靠人工完成， 诊断结果不精确、 效率低。 因此， 提出了基于one-hot模型、 核主元分析（KPCA）和自组织映射（SOM）网络的RBC系统智能故障诊断方法。 首先， 通过人工选取的故障特征词库和故障追踪记录表构建基于“one-hot”模型的故障文档矩阵； 其次， 利用核主元分析方法对故障文档矩阵进行降维降噪处理， 避免信息冗余； 最后将处理后的数据输入至SOM网络， 训练生成KPCA-SOM故障分类模型。 通过与BP神经网络算法、 SOM网络算法比对分析， KPCA-SOM智能诊断方法可有效地对列控RBC系统常见故障类型进行区分， 并且在准确率和处理效率上进一步优化提升。
关键词: 无线闭塞中心（RBC）系统； 故障诊断； 自组织映射网络（SOM）； 核主元分析（KPCA）
引用格式： LI Yang-qing， LIN Hai-xiang. Fault diagnosis method of train control RBC system based on KPCA-SOM network. Journal of Measurement Science and Instrumentation, 2020, 11（2）： 161-168. ［doi： 10.3969／j.issn.1674-8042.2020.02.008］
[full text view]
