A Method for Railway Gearbox Faults Detection Based on Time- Frequency Feature Parameters and Genetic Algorithm Neural Network

Yao Dechen*, 1, 2, Limin Jia1, Yong Qin1, Yang Jianwei2
1 State Key Laboratory of Rail Traffic Control and Safety, Beijing Jiaotong University Beijing, 100044, China
2 School of Mechanical-electronic and Automobile Engineering, Beijing University of Civil Engineering and Architecture, Beijing, 100044, China

© 2014 Yao et al

open-access license: This is an open access article distributed under the terms of the Creative Commons Attribution 4.0 International Public License (CC-BY 4.0), a copy of which is available at: ( This license permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.


Early identification of faults in railway gearboxes is a challenging task in gearbox fault detection. There are extensive studies, such as patents and papers have been fully developed for processing vibration signals to obtain diagnostic information about gearbox. We have proposed a new technique for detecting faults in the railway gearbox by applying the time frequency parameters and genetic algorithm neural network to deal with railway gearbox fault signals. In this method, wavelet analysis and empirical mode decomposition (EMD) are carried out on gearbox vibration signals for extracting the time-frequency feature parameters. Then genetic algorithm neural network (GNN) is used for the classifications of the time-frequency feature parameters. The analysis results show that the effectiveness and the high recognition rate in classifying different faults of railway gearboxes.

Keywords: EMD, fault detection, genetic algorithm neural network, railway gearbox, time-frequency feature parameters, wavelet analysis.