基于改进卷积神经网络的无绝缘轨道电路调谐区故障诊断

田粉霞; 杨世武; 崔勇; 武沛

基于改进卷积神经网络的无绝缘轨道电路调谐区故障诊断

北京交通大学电子信息工程学院, 北京 100044

基金项目:

中国铁路总公司技术标准编制项目(17CR062)

详细信息

作者简介:
田粉霞,在读硕士研究生;杨世武,教授。

中图分类号: U284.2;TP39
计量
- 文章访问数: 82
- HTML全文浏览量: 0
- PDF下载量: 15
出版历程
- 收稿日期: 2019-11-10

Fault diagnosis of tuning zone of jointless track circuit based on improved convolutional neural network

School of Electronic and Information Engineering, Beijing Jiaotong University, Beijing 100044, China

摘要

摘要: 针对现有故障诊断中忽略调谐区故障对列车安全影响的问题,建立分路状态下机车信号电压模型,获取调谐区正常状态及不同故障状态的机车信号电压;并考虑补偿电容故障、不同道砟电阻等对机车信号电压的影响,对现有数据库进行扩充,得到调谐区故障数据集。在此基础上,采用卷积神经网络(CNN,Convolutional Neural Networks)实现调谐区的故障诊断,特征提取通过CNN中卷积层实现,并对比不同卷积层参数下诊断准确率及训练时间,选择当前条件下相对最优的卷积层参数;采用dropout函数避免训练中出现过拟合现象,并通过CNN中第2全连接层实现故障分类。针对人为构建数据集时数据标签错误的问题,通过构建标签错误数据集的方式,减小错误标签数据对训练过程的影响。测试结果表明:当信噪比为40 dB时,测试集的准确率为97.92%,即在噪声环境下,该诊断方式仍然有效。
- 无绝缘轨道电路 /
- 调谐区 /
- 深度学习 /
- 卷积神经网络 /
- 故障诊断
Abstract: To solve the problem that the influence of tuning zone fault on train safety is neglected in existing fault diagnosis, a voltage model of locomotive signal in the shunting state is established to obtain the signal voltage of locomotive in normal state and different fault state of tuning zone. Then, the initial database is expanded to obtain the data set of tuning zone fault by considering the influence of compensation capacitance fault and different ballast resistance on the signal voltage of locomotive. On that basis, Convolutional Neural Network is used to realize fault diagnosis of tuning zone. Hereinto, feature extraction is realized by convolution layer in the CNN and the relatively optimal convolution layer parameters are selected by comparing different convolution layer parameters in term of the accuracy of diagnostic and training time under current condition. Furthermore, dropout function is used to avoid overfitting in training, and fault classification is realized through the second full connection layer in the CNN. To deal with human errors in data labeling when constructing the data sets artificially, wrong labeled data sets is constructed to reduce the influence of wrong labeled data on training process. The test results show that the accuracy of the test set is 97.92% when the SNR is 40 dB and this diagnosis method is still effective in a noisy environment.
- jointless track circuit /
- tuning zone /
- deep learning /
- convolutional neural networks /
- fault diagnosis

HTML全文

参考文献(14)

[1]	陈欣. 基于粒子群支撑向量机的轨道电路故障诊断[J]. 铁路计算机应用, 2016, 25(8):56-59.
[2]	徐绍俊. SA-BP神经网络在轨道电路故障诊断中的应用研究[J]. 铁路计算机应用, 2019, 28(11):55-58.
[3]	中华人民共和国铁道部. 铁路信号维护规则技术标准[S]. 北京:中国铁道出版社, 2014:88-95.
[4]	ZHAO Linhai, ZHANG Cailin, QIU Kuanmin, et al. A fault diagnosis method for the tuning area of jointless track circuits based on a neural network[J]. Proceedings of the Institution of Mechanical Engineerings, Part F:Journal of Rail and Rapid Transit, 2013, 227(4):333-343.
[5]	张才林. 基于神经网络的无绝缘轨道电路调谐区故障诊断方法的研究[D]. 北京:北京交通大学, 2013:9-49.
[6]	孙上鹏,赵会兵,全宏宇,等. 基于定性趋势分析的无绝缘轨道电路电气绝缘节设备故障诊断方法[J]. 中国铁道科学, 2014, 35(1):105-113.
[7]	张友鹏,张玉. 基于CEEMD的无绝缘轨道电路调谐区故障特征提取[J]. 铁道科学与工程学报, 2018, 15(9):2385-2393.
[8]	贾京龙,余涛,吴子杰,等. 基于卷积神经网络的变压器故障诊断方法[J]. 电测与仪表, 2017, 54(13):62-67.
[9]	LI Hua, WANG Xiaoping, ZHAO Jiaxin,et al.Motor Fault Diagnosis Based on Short-time Fourier Transform and Convolutional Neural Network[J]. Chinese Journal of Mechanical Engineering, 2017, 30(6):1357-1368.
[10]	周奇才,刘星辰,赵炯,等. 旋转机械一维深度卷积神经网络故障诊断研究[J]. 振动与冲击, 2018, 37(23):31-37.
[11]	晁甲相. 机车信号记录器在LKJ数据误差分析中的应用[J]. 铁道通信信号, 2014, 50(9):1-4.
[12]	杨世武,陈炳均,陈海康,等. 轨道电路对分相区暂态牵引电流干扰的抑制方法[J]. 西南交通大学学报, 2019, 54(6):1332-1341.
[13]	杨世武,马沧海,赵明,等. 基于车-地关联分析的轨道电路失去分路验证方法[J]. 北京交通大学学报, 2016, 40(4):75-81.
[14]	唐乾坤. 轨道电路设备牵引电流干扰防护研究[D]. 北京:北京交通大学, 2018:43-50.

施引文献(6)

期刊类型引用(2)

1.	强丽霞，王永峰，张志强，刘元铎. 我国铁路计次定期票应用场景及优化策略. 铁道经济研究. 2024(04): 8-15+64 . 百度学术
2.	吴首蓉，张志强，周自昌，苏建飞. 面向冬奥注册人员的京张高速铁路票务服务方案研究. 铁道运输与经济. 2022(09): 26-33 . 百度学术