基于OC-SVM与DNN相结合的ZPW-2000R轨道电路故障诊断研究  

Fault Diagnosis of ZPW-2000R Track Circuits Based on OC-SVM and DNN

作　　者：谢本凯 蔡水涌 黄春雷 禹建丽 陈广智 王国保 XIE Benkai;CAI Shuiyong;HUANG Chunlei;YU Jianli;CHEN Guangzhi;WANG Guobao(School of Management Engineering,Zhengzhou University of Aeronautics,Zhengzhou 450046,China;Customer Technical Service Center,Heilongjiang Ruixing Technology Co.,Ltd.,Harbin 150030,China;School of Intelligent Engineering,Zhengzhou University of Aeronautics,Zhengzhou 450046,China)

机构地区：[1]郑州航空工业管理学院管理工程学院,河南郑州450046 [2]黑龙江瑞兴科技股份有限公司客户技术服务中心,黑龙江哈尔滨150030 [3]郑州航空工业管理学院智能工程学院,河南郑州450046

出　　处：《工业工程》2023年第4期154-163,共10页Industrial Engineering Journal

基　　金：河南省软科学研究计划资助项目(212400410099);河南省高等教育教学改革研究与实践项目(2021SJGLX470);河南省自然科学基金资助项目(222300410367);河南省高等学校重点科研资助项目(22B520041)。

摘　　要：针对轨道电路故障诊断准确率低且高质量故障数据难以收集等问题,提出一种基于单分类支持向量机(OC-SVM)与深度神经网络(DNN)相结合的故障诊断方法.该方法使用OC-SVM模型对数据进行单分类识别,将正样本数据输入到DNN模型进行训练和预测,为负样本数据添加标签并收集.利用ZPW-2000R轨道电路信号数据进行大量实验,结果表明OC-SVM模型能精确地识别出正负样本数据,DNN模型能准确高效地诊断出15种数据类型,且准确率高达99%.与粒子群算法优化支持向量机、卷积神经网络、堆叠自编码器3种故障诊断方法相比,该组合方法的准确率更高,诊断效果更稳定.To address the problems of low accuracy for fault diagnosis for track circuits and difficulty in collecting high-quality fault data,a fault diagnosis method based on the combination of one-class support vector machine(OC-SVM)and deep neural network(DNN)is proposed.This method uses OC-SVM model to perform single-class recognition of data.The positive sample data are input into DNN model for training and prediction to label and collect the negative sample data.A large number of experiments are conducted using ZPW-2000R track circuit signal data.Results show that the OC-SVM model can accurately identify the positive and negative sample data,and DNN model can accurately and efficiently diagnose 15 types of data with an accuracy rate of 99%.Compared with the three fault diagnosis methods of particle swarm algorithm optimized support vector machine,convolutional neural network and stacked self-encoder,this combined method has a higher accuracy and more stable diagnosis effectiveness.

关 键 词：故障诊断 深度神经网络 单分类支持向量机 ZPW-2000R轨道电路 

分 类 号：U284.92[交通运输工程—交通信息工程及控制]