基于CNN-LSTM的铁路道岔故障诊断系统研究  

Research on Fault Diagnosis System of Railway Turnout based on CNN-LSTM

作　　者：陈溥[1] Chen Pu

机构地区：[1]柳州铁道职业技术学院,广西柳州545616

出　　处：《时代汽车》2024年第21期172-174,共3页Auto Time

基　　金：2023年广西高校中青年教师科研基础能力提升项目“基于CNN-LSTM的铁路道岔故障诊断系统研究”(立项编号:2023KY1437);2022年柳州铁道职业技术学院校级项目“基于深度学习的铁路道岔故障诊断系统的开发与研究”(立项编号:2022-KJB10)。

摘　　要：铁路道岔是铁路运输系统中的关键组成部分,其工作状态直接影响着列车运行的安全与效率,铁路道岔故障的及时诊断与检修对确保铁路系统正常运行至关重要。本文提出了一种基于卷积神经网络(CNN)和长短期记忆网络(LSTM)混合而成的深度学习故障诊断模型,通过采集铁路道岔动作电流和功率曲线数据来组成训练集和测试集,并对模型进行训练和测试,结果表明,与单一的CNN和LSTM诊断模型相比,本文提出的CNN-LSTM混合模型的故障诊断效果更优。最后设计并开发了一套铁路道岔故障监测和诊断系统,实现了对铁路道岔的实时监测和故障诊断。Railway turnouts are a key component of the railway transportation system,and their working status directly affects the safety and efficiency of train operation,and the timely diagnosis and maintenance of railway turnout faults is very important to ensure the normal operation of the railway system.This paper proposes a deep learning fault diagnosis model based on the combination of Convolutional Neural Network(CNN)and Long Short-Term Memory Network(LSTM),which collects the current and power curve data of railway switches to form a training set and a test set,and trains and tests the model.The CNN-LSTM hybrid model proposed in this paper has a better fault diagnosis effect.Finally,a set of railway turnout fault monitoring and diagnosis system was designed and developed,which realized the real-time monitoring and fault diagnosis of railway turnouts.

关 键 词：铁路道岔 卷积神经网络 长短期记忆网络 

分 类 号：U21[交通运输工程—道路与铁道工程]