A Convolutional Autoencoder Based Fault Detection Method for Metro Railway Turnout
作者机构：School of Electronic and Information EngineeringTongji UniversityShanghai201804China School of EngineeringCity University of Hong KongHong Kong200433China School of Civil AviationNorthwestern Polytechnical UniversityXi’an710072China School of Computer EngineeringJimei UniversityXiamen361021China
出 版 物：《Computer Modeling in Engineering & Sciences》 (工程与科学中的计算机建模（英文）)
年 卷 期：2023年第136卷第7期
页 面：471-485页
核心收录：
学科分类：08[工学] 080203[工学-机械设计及理论] 0802[工学-机械工程]
基 金：supported in part by the National Natural Science Foundation of China under Grant U1734211
主 题：Convolutional autoencoder fault detection metro railway turnout
摘 要：Railway turnout is one of the critical equipment of Switch&Crossing(S&C)Systems in railway,related to the train’s safety and operation *** the advancement of intelligent sensors,data-driven fault detection technology for railway turnout has become an important research ***,little research in the literature has investigated the capability of data-driven fault detection technology for metro railway *** paper presents a convolutional autoencoder-based fault detection method for the metro railway turnout considering human field inspection ***,the one-dimensional original time-series signal is converted into a twodimensional image by data pre-processing and 2D ***,a binary classification model based on the convolutional autoencoder is developed to implement fault *** profile and structure information can be captured by processing data as *** performance of our method is evaluated and tested on real-world operational current data in themetro *** results show that the proposedmethod achieves better performance,especially in terms of error rate and specificity,and is robust in practical engineering applications.
维普期刊数据库