LU Renjie， LIN Haixiang， XU Li， LU Ran， ZHAO Zhengxiang， BAI Wansheng
（School of Automation and Electrical Engineering, Lanzhou Jiaotong University, Lanzhou 730070, China）
Abstract： Rapid and precise location of the faults of on-board equipment of train control system is a significant factor to ensure reliable train operation. Text data of the fault tracking table of on-board equipment are taken as samples, and an on-board equipment fault diagnosis model is designed based on the combination of convolutional neural network (CNN) and particle swarm optimization-support vector machines (PSO-SVM). Due to the characteristics of high dimensionality and sparseness of fault text data, CNN is used to achieve feature extraction. In order to decrease the influence of the imbalance of the fault sample data category on the classification accuracy, the PSO-SVM algorithm is introduced. The fully connected classification part of CNN is replaced by PSO-SVM, the extracted features are classified precisely, and the intelligent diagnosis of on-board equipment fault is implemented. According to the test analysis of the fault text data of on-board equipment recorded by a railway bureau and comparison with other models, the experimental results indicate that this model can obviously upgrade the evaluation indexes and can be used as an effective model for fault diagnosis for on-board equipment.
Key words： on-board equipment; fault diagnosis; convolutional neural network (CNN); unbalanced text data; particle swarm optimization-support vector machines (PSO-SVM)
References
［1］ZHOU L J, DONG Y. Research on fault diagnosis method for on-board equipment of train control system based on GA-BP neural network. Journal of Railway Science and Engineering, 2018, 15(12): 3257-3265.
［2］LIU H. Research on fault diagnosis method for CTCS on-board equipment of high-speed railway based on association rules. Beijing: Beijing Jiaotong University, 2018.
［3］LIANG X, WAN H F, GUO J, et al. Bayesian network based fault diagnosis method for on-board equipment of train control system. Journal of the China Railway Society, 2017, 39(8): 93-100.
［4］FENG B. Research on fault analysis method for CTCS on-board equipment of high-speed railway based on hidden markov model. Beijing: Beijing Jiaotong University, 2020.
［5］ZHOU L J, DANG J W, WANG Y X, et al. Fault diagnosis for on-board equipment of train control system based on CNN-CSRF hybrid mode. Journal of the China Railway Society, 2020, 42(11): 94-101.
［6］ZHOU Q H, LI X L. Research on short text classification method of railway signal equipment fault based on MCNN. Journal of Railway Science and Engineering, 2019, 16(11): 2859-2865.
［7］ZHANG Y S, ZHENG J, JIANG Y R, et al. A text sentiment classification modeling method based on coordinated CNN-LSTM-Attention model. Chinese Journal of Electronics, 2019, 28(1): 120-126.
［8］KIM Y. Convolutional neural networks for sentence classification//2014 Conference on Empirical Methods in Natural Language Processing. Oct. 25-29, 2014, Doha, Qatar, Stroudsburg: ACL, 2014: 1746-1751.
［9］MATEUSZ B, ATSUTO M, MACIEJ A. A systematic study of the class imbalance problem in convolutional neural networks. Neural Networks, 2018, 10(6): 249-259.
［10］LI J W. Research on fault diagnosis of on-board equipment for train control system based on BN optimized by CS-PSO. Lanzhou: Lanzhou Jiaotong University, 2019.
［11］FAN L H, WU X C, GUO R C. Based on association rules and variable weight coefficient working state evaluation method of on-board equipment of train control system. Railway Standard Design, 2021, 65(3): 171-176.
［12］BENGIO Y, DUCHARME R, VINCENT P, et al. A neural probabilistic language model. Journal of Machine Learning Research, 2003, 3(6): 1137-1155.
［13］CHEN L, LI J. Text feature selection methods based on word vector. Journal of Chinese Computer Systems, 2018, 39(5): 991-994.
［14］XIANG Q W, YUAN Y, YU Y J, et al. Rotor position self-sensing of SRM using PSO-RVM. Energies, 2018, 11(1): 66-78.
［15］KENNEDY J. Particle swarm optimization. Aiaa Journal, 2003, 41(8): 129-132.
［16］XU L L, CHI D X. Machine learning classification strategy for imbalanced data sets. Computer Engineering and Applications, 2020, 56(24): 12-27.
基于CNN和PSO-SVM组合模型的列控车载设备故障诊断
陆人杰， 林海香， 许丽， 卢冉， 赵正祥， 白万胜
（兰州交通大学 自动化与电气工程学院， 甘肃 兰州 730070）
摘要:快速准确地定位列控车载设备故障是保证列车可靠运行的重要因素。 本文以车载设备故障追踪表中的文本数据为样本， 设计基于卷积神经网络（CNN）与粒子群优化-支持向量机（PSO-SVM）相结合的车载设备故障诊断模型。 基于故障文本数据具有高维度、 高稀疏的特点， 利用卷积神经网络对其实现特征提取。 为了降低故障样本数据类别不平衡对分类精度的影响， 采用粒子群优化的支持向量机算法对不均衡文本数据进行处理。 用PSO-SVM替代CNN全连接分类部分， 并对所提取特征进行精确分类， 实现车载设备故障智能诊断。 依据某铁路局所记录的车载设备故障文本数据进行实验分析并与其它方法对比， 实验结果表明， 该模型可使各评价指标得到明显提升， 可以作为车载设备故障诊断的有效模型。
关键词:车载设备； 故障诊断； 卷积神经网络（CNN）； 不平衡文本数据； 粒子群优化-支持向量机（PSO-SVM）
引用格式：LU Renjie, LIN Haixiang, XU Li, et al. Fault diagnosis for on-board equipment of train control system based on CNN and PSO-SVM hybrid model. Journal of Measurement Science and Instrumentation， 2022， 13（4）： 430-438. DOI： 10.3969／j.issn.1674-8042.2022.04.006
[full text view]
