A Novel Fault Diagnosis Method for Train Real‐Time Ethernet Network Based on Physical Layer Electrical Signal Features

Abstract

Train real‐time ethernet network (TREN) is responsible for the transmission of train control commands and equipment status information. Due to the harsh and changeable climatic environments, complex electromagnetic environments, and long service, the TREN has a high incidence of physical layer failures, which affects train operation safety. This paper presents a novel fault diagnosis method in which waveform electrical signal features are extracted from the physical layer signal of TREN. Random forest is used for identifying typical failure modes of actual TREN, and the model parameters are optimized to improve diagnostic performance. Finally, the physical layer signals of actual TREN are collected. The results show that the performance of the proposed fault diagnosis method is better than other advanced methods. © 2023 Institute of Electrical Engineers of Japan. Published by Wiley Periodicals LLC.