融合BiLSTM-CBA组合模型的高铁车载设备故障诊断

doi:10.16265/j.cnki.issn1003-3033.2022.06.2747

中国安全科学学报 ›› 2022, Vol. 32 ›› Issue (6): 79-86.doi: 10.16265/j.cnki.issn1003-3033.2022.06.2747

融合BiLSTM-CBA组合模型的高铁车载设备故障诊断

林海香¹(), 卢冉¹, 陆人杰², 李新琴³, 赵正祥¹, 白万胜¹

1 兰州交通大学自动化与电气工程学院,甘肃兰州 730070
2 卡斯柯信号有限公司,上海 200071
3 中国铁道科学研究院集团有限公司电子计算技术研究所,北京 100081

收稿日期:2022-01-11 修回日期:2022-04-14 出版日期:2022-06-28 发布日期:2022-12-28
作者简介:
林海香 (1977—),女,甘肃天水人,博士,副教授,主要从事轨道交通安全防护与控制、交通信息数据挖掘等方面的研究。E-mail: linhaixiang@mail.lzjtu.cn。
基金资助:
中国铁道科学研究院集团有限公司科研项目(2021YJ184)

Fault diagnosis of high-speed railway on-board equipment based on BiLSTM-CBA hybrid model

LIN Haixiang¹(), LU Ran¹, LU Renjie², LI Xinqin³, ZHAO Zhengxiang¹, BAI Wansheng¹

1 School of Automation and Electrical Engineering, Lanzhou Jiaotong University, Lanzhou Gansu 730070, China
2 CASCO Signal Ltd., Shanghai 200071, China
3 Institute of Computing Technology, China Academy of Railway Sciences Corporation Limited, Beijing 100081, China

Received:2022-01-11 Revised:2022-04-14 Online:2022-06-28 Published:2022-12-28

摘要/Abstract

摘要：

为提高高铁车载设备在运营维护过程中数据利用率,以CRH2型与CRH3型动车组列车中最具代表性的CTCS3-300T型车载设备的故障文本数据为例,提出一种将双向长短时记忆网络(BiLSTM)与关联规则分类器(CBA)技术相结合的车载设备故障诊断模型。首先,该模型通过Word2vec工具对车载设备故障文本进行词向量训练;其次,针对故障数据分布不平衡的问题,通过合成少数类过采样技术(SMOTE)算法,自动生成小类别文本向量数据;然后,利用BiLSTM获取故障文本特征;最后,采用CBA算法实现车载设备故障诊断,通过试验分析某铁路局近5年的车载故障文本数据。结果表明:该模型使故障诊断的精确率和召回率分别达到95.66%和96.29%,相较于未采用SMOTE算法的模型,其召回率提升11.77%;该模型能够保证整体分类准确率,同时,也具备较好的小类别分类性能。

关键词: 双向长短时记忆网络(BiLSTM), 关联规则分类器(CBA), 车载设备, 故障诊断, 合成少数类过采样技术(SMOTE)

Abstract:

In order to improve data utilization rate of on-board equipment on high speed trains during operation and maintenance, with fault text data of the most representative CTCS3-300T equipment in CRH2 and CRH3 EMUs as an example, a fault diagnosis model based on BiLSTM and CBA was proposed Firstly, used Word2vec tool to train word vector for fault text. Secondly, for the problem of unbalanced distribution of fault data, small category text vector data were automatically generated by SMOTE algorithm. Then, BiLSTM was utilized to obtain fault text features. Finally, fault diagnosis was accomplished by CBA algorithm., and text data of on-board equipment of a railway bureau in the past 5 years were experimentally analyzed. The results show that the proposed model can make precision and recall rate of fault diagnosis reach 95.66% and 96.29% respectively. And compared with the model without SMOTE algorithm, its recall rate has increased by 11.77%, which not only guarantees accuracy of general classification, but also gets better classification performance of minority classes.

Key words: Bi-directional long short-term memory (BiLSTM), classification based on associations (CBA), on-board equipment, fault diagnosis, synthetic minority over-sampling technique (SMOTE)

林海香, 卢冉, 陆人杰, 李新琴, 赵正祥, 白万胜. 融合BiLSTM-CBA组合模型的高铁车载设备故障诊断[J]. 中国安全科学学报, 2022, 32(6): 79-86.

LIN Haixiang, LU Ran, LU Renjie, LI Xinqin, ZHAO Zhengxiang, BAI Wansheng. Fault diagnosis of high-speed railway on-board equipment based on BiLSTM-CBA hybrid model[J]. China Safety Science Journal, 2022, 32(6): 79-86.

图/表 12

表1

图1

图2

图3

图4

图5

图6

图7

图8

图9

图10

表2

参考文献 16

[1]	刘浩. 基于关联规则的高铁列控车载设备故障诊断方法研究[D]. 北京: 北京交通大学, 2018.
	LIU Hao. Research on fault diagnosis method for CTCS on-board equipment of high-speed railway based on association rules[D]. Beijing: Beijing Jiaotong University, 2018.
[2]	周璐婕, 董昱. 基于GA-BP神经网络的列控车载设备故障诊断方法研究[J]. 铁道科学与工程学报, 2018, 15(12): 3257-3265.
	ZHOU Lujie, DONG Yu. Research on fault diagnosis method for on-board equipment of train control system based on GA-BP neural network[J]. Journal of Railway Science and Engineering, 2018, 15(12): 3257-3265.
[3]	钟志旺, 唐涛, 王峰. 基于PLSA和SVM的道岔故障特征提取与诊断方法研究[J]. 铁道学报, 2018, 40(7): 80-87.
	ZHONG Zhiwang, TANG Tao, WANG Feng. Research on fault extraction and diagnosis of railway based on PLSA and SVM[J]. Journal of the China Railway Society, 2018, 40(7): 80-87.
[4]	黄贤英, 刘广峰, 刘小洋, 等. 基于word2vec和双向LSTM的情感分类深度模型[J]. 计算机应用研究, 2019, 36(12): 3583-3587,3596.
	HUANG Xianying, LIU Guangfeng, LIU Xiaoyang, et al. Sentiment classification depth model based on word2vec and bi-directional LSTM[J]. Application Research of Computers, 2019, 36(12): 3583-3587,3596.
[5]	丁茜, 赵晓东, 吴鑫俊, 等. 基于RBF核的多分类SVM滑塌易发性评价模型[J]. 中国安全科学学报, 2022, 32(3): 194-200. doi: 10.16265/j.cnki.issn1003-3033.2022.03.026
	DING Xi, ZHAO Xiaodong, WU Xinjun, et al. Landslide susceptibility assessment model based on multi-class SVM with RBF kernel[J]. China Safety Science Journal, 2022, 32(3): 194-200. doi: 10.16265/j.cnki.issn1003-3033.2022.03.026
[6]	GAO Hongyi, ZENG Xi, YAO Chunhua. Application of improved distributed naive bayesian algorithms in text classification[J]. The Journal of Supercomputing, 2019, 75(9): 5831-5847. doi: 10.1007/s11227-019-02862-1
[7]	GE Shengxin, ZHUANG Yufeng, HU Yanzhu, et al. Research on enterprise hidden danger association rules based on text analysis[J]. IOP Conference Series: Earth and Environmental Science, 2019, 252(3): DOI:10.1088/1755-1315/252/3/032170.
[8]	李新琴, 张鹏翔, 史天运, 等. 基于深度学习集成的高速铁路信号设备故障诊断方法[J]. 铁道学报, 2020, 42(12): 97-105.
	LI Xinqin, ZHANG Pengxiang, SHI Tianyun, et al. Research on fault diagnosis method for high-speed railway signal equipment based on deep learning integration[J]. Journal of the China Railway Society, 2020, 42(12): 97-105.
[9]	谢明军, 何剑峰, 胡小溪, 等. 基于故障日志的城轨地面信号故障诊断[J]. 北京交通大学学报, 2020, 44(5): 27-35.
	XIE Mingjun, HE Jianfeng, HU Xiaoxi, et al. Fault diagnosis for urban rail transit track side signaling equipment based on fault logs[J]. Journal of Beijing Jiaotong University, 2020, 44(5): 27-35.
[10]	杨连报, 沈翔, 李新琴, 等. 基于文本分析的高速铁路道岔故障分类模型研究[J]. 中国铁路, 2020(8): 13-18.
	YANG Lianbao, SHEN Xiang, LI Xinqin, et al. Classification model of high speed railway turnout failures based on text analysis[J]. China Railway, 2020(8): 13-18.
[11]	林海香, 陆人杰, 卢冉, 等. 基于文本挖掘的铁路信号设备故障自动分类方法[J]. 云南大学学报:自然科学版, 2022, 44(2): 281-289.
	LIN Haixiang, LU Renjie, LU Ran, et al. Automatic classification method of railway signal fault based on text mining[J]. Journal of Yunnan University:Natural Sciences Edition, 2022, 44(2): 281-289.
[12]	夏容, 江官星. 基于LSTM的软件时间序列延迟预测仿真[J]. 计算机仿真, 2021, 38(12): 435-439.
	XIA Rong, JIANG Guanxing. Software time series delay prediction simulation based on LSTM[J]. Computer Simulation, 2021, 38(12): 435-439.
[13]	LIU Bing, HSU Wynne, MA Yiming. Integrating classification and association rule mining[C]. KDD' 98 Proceedings of the Rourth International Conference on Knowledge Discovery and Data Mining, 1998: 80-86.
[14]	陈述, 习俊博, 王建平, 等. 水电工程施工安全隐患关联规则挖掘[J]. 中国安全科学学报, 2021, 31(8): 75-82. doi: 10.16265/j.cnki.issn1003-3033.2021.08.011
	CHEN Shu, XI Junbo, WANG Jianping, et al. Mining association rules of near-misses of hydropower projects construction[J]. China Safety Science Journal, 2021, 31(8): 75-82. doi: 10.16265/j.cnki.issn1003-3033.2021.08.011
[15]	CHEN Zhuo, ZHOU Lanjiang, LI Xuanda, et al. The lao text classification method based on KNN[J]. Procedia Computer Science, 2020, 166: 523-528. doi: 10.1016/j.procs.2020.02.053
[16]	ANGKASA A, FITRIANAH D. The implementation of classification algorithm C4.5 in determining the illness risk level for health insurance company in indonesia[J]. International Journal of Computer Applications, 2020, 177(37): 44-50.

故障标号	故障类别	故障案例频数/条
C1	车载安全计算机单元	115
C2	应答器传输模块	455
C3	轨道电路传输模块	151
C4	测速测距单元	116
C5	无线通信故障	978
C6	列车接口单元	271
C7	人机界面故障	54
C8	司法记录单元	27

模型	精确率	召回率	F₁值
SMOTE-BiLSTM-NB	0.926 3	0.924 5	0.925 4
SMOTE-BiLSTM-KNN	0.903 8	0.913 4	0.908 6
SMOTE-BiLSTM-C4.5	0.894 1	0.907 9	0.900 9
BiLSTM-CBA组合模型	0.956 6	0.962 9	0.959 7

融合BiLSTM-CBA组合模型的高铁车载设备故障诊断

Fault diagnosis of high-speed railway on-board equipment based on BiLSTM-CBA hybrid model

RichHTML

PDF

可视化

摘要/Abstract

引用本文

使用本文

图/表 12

参考文献 16

相关文章 15

编辑推荐

Metrics

本文评价

[1]	李刚, 卢佩玲, 杨勇. ZPW-2000轨道电路故障诊断算法应用研究[J]. 中国安全科学学报, 2022, 32(6): 53-59.
[2]	余伟, 王志鹏, 刘硕, 何刚. 多级精细模型下的电机匝间短路故障诊断[J]. 中国安全科学学报, 2022, 32(6): 95-102.
[3]	邢玉龙, 王剑, 上官伟, 彭聪, 朱林富. 面向海量不平衡数据的轨道电路故障诊断方法[J]. 中国安全科学学报, 2022, 32(5): 112-118.
[4]	古莹奎, 刘平, 林忠海, 邱光琦. 基于Kurtogram与DSCN的滚动轴承故障诊断方法[J]. 中国安全科学学报, 2021, 31(6): 99-105.
[5]	陈志煌, 刘国恒, 王莹莹, 朱春丽, 单荐, 翟小东. 基于动态贝叶斯网络的水下连接器故障诊断[J]. 中国安全科学学报, 2020, 30(5): 81-87.
[6]	余敬芝, 燕飞, 牛儒. 基于Petri网的形式化安全分析方法^*[J]. 中国安全科学学报, 2019, 29(S2): 138-143.
[7]	温廷新, 李洋子. 基于预处理的AFOA-ELM冲击地压危险预测模型[J]. 中国安全科学学报, 2019, 29(8): 29-34.
[8]	窦磊, 李耀, 郭进, 童音, 兰浩. 列控车载设备安全功能测试序列优化方法研究[J]. 中国安全科学学报, 2019, 29(5): 73-78.
[9]	王斌，施祖建，匡蕾. 基于改进KFDA和RW v-SVM的化工生产系统故障快速诊断[J]. 中国安全科学学报, 2013, 23(8): 84-.
[10]	宋志雄，朱红岗，李星星. 基于案例推理的大型养路机械故障诊断系统[J]. 中国安全科学学报, 2012, 22(12): 41-.
[11]	曹惠玲，赵明，曲春刚，薛鹏. 可靠性数据在民机故障诊断中的应用研究[J]. 中国安全科学学报, 2011, 21(10): 95-.
[12]	马成正，王洪德. 基于FMEA与RBF神经网络的LPG汽车罐车储罐系统故障诊断[J]. 中国安全科学学报, 2011, 21(1): 99-.
[13]	梁文，陶振文，黄超，马勇，刘显明，付萍萍，杨济海. 光纤电力通信系统故障诊断方法及应用实践[J]. 中国安全科学学报, 2008, 18(4): 104-.
[14]	岳文辉，肖兴明，唐果宁. 图像识别技术及其在机械零件无损检测中的应用[J]. 中国安全科学学报, 2007, 17(3): 156-.
[15]	邵辉，赵庆贤，李燕. 关联维数在机械设备故障诊断中的应用研究[J]. 中国安全科学学报, 2006, 16(3): 129-.