Strategy for Fault Diagnosis on Train Plug Doors Using Audio Sensors

Abstract

As the only entry/exit for passengers getting on and off a train, the train plug door is of great importance to keep train operation safe and reliable. As signal processing technologies develop rapidly, taking the easy acquisition advantages of sound signals, a novel fault diagnosis method for train plug doors using multi-scale normalized permutation entropy (MNPE) and an improved particle swarm optimization based multi-class support vector machine (IPSO-MSVM) is proposed. Firstly, sound samples are collected using high-precision audio sensor. In the features extraction process, a hybrid method blending empirical mode decomposition (EMD), multi-scale permutation entropy (MNPE) with Fisher discrimination criterion is utilized. First, EMD is used to decompose each sound signal into several intrinsic mode functions (IMFs) and a residue for stationary processing. Then, MNPE features are extracted from the IMFs. To obtain the most significant features, the Fisher discrimination criterion is further applied. To address the time-consuming defects of traditional grid based method for selecting the optimal parameters of multi-class SVM, an improved PSO (IPSO) is proposed. The superiority of the IPSO-MSVM model and the hybrid feature extraction method was tested on the collected sound samples by comparing to commonly applied methods. Results indicate the identification accuracy of the proposed method is highest, which reaches 90.54%, demonstrating its feasibility.

A Comparative Study of Fault Diagnosis for Train Door System: Traditional versus Deep Learning Approaches

“…However, in the train door application, very little study is found in the literature. For the train plug door, the audio sensor signals are used to classify faults by using the empirical mode decomposition (EMD) and support vector machine (SVM) [6]. The health monitoring method is proposed by the resistance analysis of the motor current signals during the door movement for the two cases: internal fault by the bent screw and insufficient lubrication, and external fault by pushing of passengers and obstruction.…”

A Hybrid Method for Life Prediction of Railway Relays Based on Multi-Layer Decomposition and RBFNN

“…In order to predict the release time series, the RBFNN model is trained using the first 800 values, while the rest 186 values are used as test set. Here, the idea of phase space reconstruction (PSR) [24] is adopted by selecting embedding dimension and time lag as 5 and 1, respectively. That means we use the former 5 series points (training point) to predict the next value (output point).…”

“…Finally, the original signal can be decomposed into several IMFs and a residue. Every IMF should satisfy the following two conditions: (1) the numbers of extreme points and zero-crossing points are equal or differ only by one; (2) the mean of upper and lower envelopes is zero at any point [24]. Aiming to deal with mode mixing of EMD, Wu and Huang proposed a noise-assisted method named EEMD [16].…”

Condition Monitoring for Railway Point Machines Based on Sound Analysis and Support Vector Machine

“…The description of OAO SVM can be seen in Ref. [42]. Besides, SVM provides kernel function to solve linear indivisible problems by mapping low dimensional data to higher even infinite dimensional space.…”