基于混合深度学习的高铁道岔故障诊断研究  

Research on fault diagnosis of High Speed Railway Turnout Based on hybrid deep learning

作　　者：张贺宁 李欣 魏静 ZHANG Hening;LI Xin;WEI Jing(Xinjiang Railway Vocational and Technical College,Urumqi 830011,China)

机构地区：[1]新疆铁道职业技术学院,乌鲁木齐830011

出　　处：《自动化与仪器仪表》2022年第1期109-112,共4页Automation & Instrumentation

基　　金：重庆市省部级课题名称:“交通强国战略”背景下动车组检修专业课程思政探究与实践(203760)。

摘　　要：针对现行高铁道岔故障诊断过度依赖人工经验,导致故障诊断效率低的问题,提出一种混合深度降噪自编码器与支持向量机的高铁道岔故障诊断方案。通过采用深度降噪自编码器自动提取高铁道岔动作电流曲线特征,并将其输入支持向量机模型进行故障,实现了高铁道岔的故障诊断。最后,通过采用提出方法对实际高铁道岔数据进行故障诊断仿真,验证了提出方法的有效性。结果表明,本研究提出的基于混合深度学习的高铁道岔故障诊断方法可有效检测出高铁道岔故障,具有较高的准确性,可用于实际高铁道岔故障诊断。Aiming at the problem that the current high-speed railway turnout fault diagnosis relies too much on manual experience,resulting in low efficiency of fault diagnosis,a high-speed railway turnout fault diagnosis scheme based on hybrid deep noise reduction self encoder and support vector machine is proposed.The fault diagnosis of high-speed railway turnout is realized by automatically extracting the characteristics of action current curve of high-speed railway turnout with deep noise reduction self encoder and inputting it into support vector machine model for fault diagnosis.Finally,the effectiveness of the proposed method is verified by the fault diagnosis simulation of the actual high-speed railway turnout data.The results show that the fault diagnosis method of High-speed Railway Turnout Based on hybrid deep learning proposed in this study can effectively detect the fault of high-speed railway turnout,has high accuracy,and can be used in the fault diagnosis of actual high-speed railway turnout.

关 键 词：深度降噪自编码器 支持向量机 混合深度学习 故障诊断 

分 类 号：TP277[自动化与计算机技术—检测技术与自动化装置]