基于一维卷积神经网络的实时道岔故障诊断

doi:10.3778/j.issn.1002-8331.2103-0348

摘要/Abstract

摘要： 针对道岔故障诊断系统实时性要求高、特征提取严重依赖于先验知识的问题，提出了一种基于一维卷积神经网络（1D-CNN）的道岔实时故障诊断方法。以S700k转辙机的功率曲线为例，建立一维卷积神经网络的结构模型，该模型将特征提取与故障分类融合为一体，优化了网络参数，同时使用正则化Dropout提高模型的泛化能力，采用t-SNE可视化方法，来反映模型提取特征的有效性。仿真实验表明：卷积层和池化层对原始时域信号的自适应特征提取，能较好地捕捉信号空间维度信息，降低模型的计算量，提高模型的抗噪性能，实现了端到端的实时故障诊断，并有效地提高道岔故障实时诊断的准确率。

关键词: 一维卷积神经网络, S700k转辙机, 时间序列, 故障诊断

Abstract: In view of the high real-time requirements of turnout fault diagnosis system and the serious dependence of feature extraction on prior knowledge, a real-time fault diagnosis method for turnouts based on one-dimensional convolutional neural network（1D-CNN） is proposed. Taking the power curve of S700k switch machine as an example, a one-dimensional convolutional neural network structure model is established. The model integrates feature extraction and fault classification, optimizes network parameters, and improves the generalization ability of the model by using regularized dropout, uses t-SNE visualization method to reflect the effectiveness of model extraction features. Simulation results show that the adaptive feature extraction of the original time domain signals by the convolutional layer and the pooling layer can better capture the spatial dimension information of signal, reduce the calculation amount of the model, and improve the anti-noise performance of the model, achieving the end-to-end real-time fault diagnosis, and effectively improve the accuracy of the real-time fault diagnosis of the turnout.

Key words: one-dimensional convolution neural network, S700k switch machine, time series, fault diagnosis

池毅, 陈光武. 基于一维卷积神经网络的实时道岔故障诊断[J]. 计算机工程与应用, 2022, 58(20): 293-299.

CHI Yi, CHEN Guangwu. Real-Time Turnout Fault Diagnosis Based on One-Dimensional Convolutional Neural Network[J]. Computer Engineering and Applications, 2022, 58(20): 293-299.

参考文献

[1] 张旭，魏文军.基于PCA-WT的道岔故障电流特征识别[J].兰州交通大学学报，2018，37（2）：43-48.
ZHANG Xu，WEI Wenjun.Research on current feature indentification of turnout faults based on a PCA-WT approach[J].Journal of Lanzhou Jiaotong University，2018，37（2）：43-48.
[2] 魏文军，刘新发.基于EEMD多尺度样本熵的S700K转辙机故障诊断[J].中南大学学报（自然科学版），2019，50（11）：2763-2772.
WEI Wenjun，LIU Xinfa.Fault diagnosis of S700K switch machine based on EEMD multiscale sample entropy[J].Journal of Central South University（Science and Technology），2019，50（11）：2763-2772.
[3] 许庆阳，刘中田，赵会兵.基于隐马尔科夫模型的道岔故障诊断方法[J].铁道学报，2018，40（8）：98-106.
XU Qingyang，LIU Zhongtian，ZHAO Huibing.Method of turnout fault diagnosis based on hidden Markov model[J].Journal of the China Railway Society，2018，40（8）：98-106.
[4] 王瑞峰，陈旺斌.基于灰色神经网络的S700K转辙机故障诊断方法研究[J].铁道学报，2016，38（6）：68-72.
WANG Ruifeng，CHEN Wangbin.Research on fault diagnosis method of S700K switch machine based on grey neural network[J].Journal of the China Railway Society，2016，38（6）：68-72.
[5] 董炜，刘明明，王良顺，等.基于群决策的道岔控制电路故障诊断方法[J].自动化学报，2018，44（6）：1005-1014.
DONG Wei，LIU Mingming，WANG Liangshun，et al.Fault diagnosis for railway turnout control circuit based on group decision making[J].Acta Automatica Sinica，2018，44（6）：1005-1014.
[6] 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 feature extraction and diagnosis of railway switch based on PLSA and SVM[J].Journal of the China Railway Society，2018，40（7）：80-87.
[7] ZHAO R，YAN R，CHEN Z，et al.Deep learning and its applications to machine health monitoring[J].Mechanical Systems and Signal Processing，2019，115：213-237.
[8] HANNUN A Y，RAJPURKAR P，HAGHPANAHI M，et al.Cardiologist-level arrhythmia detection and classification in ambulatory electrocardiograms using a deep neural network[J].Nature Medicine，2019，25（1）：65.
[9] INCE T，KIRANYAZ S，EREN L，et al.Real-time motor fault detection by 1-D convolutional neural networks[J].IEEE Transactions on Industrial Electronics，2016，63（11）：7067-7075.
[10] HUANG S，TANG J，DAI J，et al.Signal status recognition based on 1DCNN and its feature extraction mechanism analysis[J].Sensors，2019，19（9）：2018.
[11] IGNATOV A.Real-time human activity recognition from accelerometer data using convolutional neural networks[J].Applied Soft Computing，2018，62：915-922.
[12] 高昆仑，杨帅，刘思言，等.基于一维卷积神经网络的电力系统暂态稳定评估[J].电力系统自动化，2019，43（12）：18-26.
GAO Kunlun，YANG Shuai，LIU Siyan，et al.Transient stability assessment of power system based on one-dimensional convolutional neural network[J].Automation of Electric Power Systems，2019，43（12）：18-26.
[13] DE BRUIN T，VERBERT K，BABU?KA R.Railway track circuit fault diagnosis using recurrent neural networks[J].IEEE Transactions on Neural Networks and Learning Systems，2016，28（3）：523-533.
[14] KERBOUA A，METATLA A，KELAIAIA R，et al.Real-time safety monitoring in the induction motor using deep hierarchic long short-term memory[J].The International Journal of Advanced Manufacturing Technology，2018，99：2245-2255.
[15] MAATEN L V D，HINTON G.Visualizing data using t-SNE[J].Journal of Machine Learning Research，2008，9：2579-2605.