Fault diagnosis on the bearing of traction motor in high-speed trains based on deep learning

Abstract The bearing health in the traction motor is the prerequisite and guarantee for the safe operation of high-speed trains. The vibration signals of the bearing in traction motor feature high nonlinearity, non-stationarity, and background noise. Therefore, the features of the vibration signals are diverse and complex, making it hard to diagnose the faults of the bearing effectively and accurately. To overcome the difficulty, this paper puts forward a novel fault diagnosis method for the bearing of traction motor in high speed trains based on discrete wavelet transform (DWT) and improved deep belief network (DBN). Firstly, the vibration signals were extracted from various faulty bearings, and used to generate a two-dimensional (2D) time–frequency map. Then, the time–frequency map was preprocessed, and subjected to the deep learning (DL) by the improved DBN, aiming to identify the correlation between fault features and fault types. In this way, the fault state of the bearing in the traction motor was diagnosed and identified in a semi-supervised manner. To verify its effectiveness, the proposed method was applied to diagnose the bearing faults of traction motor in high-speed trains through comparative experiments. The results show that our method achieved better diagnosis accuracy than contrastive methods like backpropagation neural network (BPNN) and support vector machine (SVM).

[1]  Bo-Suk Yang,et al.  Fault diagnosis of induction motor based on decision trees and adaptive neuro-fuzzy inference , 2009, Expert Syst. Appl..

[2]  J. I. Perat,et al.  Permanent Magnet Synchronous Motor with Different Rotor Structures for Traction Motor in High Speed Trains , 2018, Energies.

[3]  Dehua Wu,et al.  A Fast Recognition Algorithm of Online Social Network Images Based on Deep Learning , 2019, Traitement du Signal.

[4]  Muhammed Yildirim,et al.  Classification of White Blood Cells by Deep Learning Methods for Diagnosing Disease , 2019, Rev. d'Intelligence Artif..

[5]  Thalakola Rao,et al.  A Frame Work for Hospital Readmission Based on Deep Learning Approach and Naive Bayes Classification Model , 2019, Rev. d'Intelligence Artif..

[6]  Neha Bansal,et al.  An Evolving Hybrid Deep Learning Framework for Legal Document Classification , 2019, Ingénierie des Systèmes d Inf..

[7]  Fulei Chu,et al.  Ensemble deep learning-based fault diagnosis of rotor bearing systems , 2019, Comput. Ind..

[8]  M. Ahmadian,et al.  Integrated sliding mode and direct torque controls for improving transient traction in high-speed trains , 2020, Journal of Vibration and Control.

[9]  Chuijiang Guo,et al.  Operation Planning for Freight Block Trains Using Released Transport Capacity of Existing Railways , 2019 .

[10]  Jong-Duk Son,et al.  Fault diagnosis of low speed bearing based on relevance vector machine and support vector machine , 2009, Expert Syst. Appl..

[11]  Constantine Tarawneh,et al.  Thermal Modeling of a Railroad Tapered-Roller Bearing Using Finite Element Analysis , 2012 .

[12]  Chandrasekhar Nataraj,et al.  Use of particle swarm optimization for machinery fault detection , 2009, Eng. Appl. Artif. Intell..

[13]  Mehmet Recep Bozkurt,et al.  GKP Signal Processing Using Deep CNN and SVM for Tongue-Machine Interface , 2019, Traitement du Signal.

[14]  Wei Chen,et al.  Intelligent fault diagnosis of rotating machinery using support vector machine with ant colony algorithm for synchronous feature selection and parameter optimization , 2015, Neurocomputing.

[15]  Yuling Tian,et al.  A deep adaptive learning method for rolling bearing fault diagnosis using immunity , 2019, Tsinghua Science and Technology.

[16]  Yuan Li,et al.  Bearing fault diagnosis with auto-encoder extreme learning machine: A comparative study , 2017 .

[17]  Xin Zhou,et al.  Deep neural networks: A promising tool for fault characteristic mining and intelligent diagnosis of rotating machinery with massive data , 2016 .

[18]  Yongduan Song,et al.  A Novel Approach for Active Adhesion Control of High-Speed Trains Under Antiskid Constraints , 2015, IEEE Transactions on Intelligent Transportation Systems.

[19]  P. Velex,et al.  Investigations on the power losses and thermal behaviour of rolling element bearings , 2009 .

[20]  Zhonghui Yin,et al.  Random Response Analysis of Axle-Box Bearing of a High-Speed Train Excited by Crosswinds and Track Irregularities , 2019, IEEE Transactions on Vehicular Technology.

[21]  Wei Zhang,et al.  A New Deep Learning Model for Fault Diagnosis with Good Anti-Noise and Domain Adaptation Ability on Raw Vibration Signals , 2017, Sensors.

[22]  Xiao Mei,et al.  Modified repetitive learning control with unidirectional control input for uncertain nonlinear systems , 2017, Neural Computing and Applications.

[23]  Seda Arslan Tuncer,et al.  Spinal Cord Based Kidney Segmentation Using Connected Component Labeling and K-Means Clustering Algorithm , 2019, Traitement du Signal.

[24]  Ning Wang,et al.  Theoretical and experimental investigation on the thermal characteristics of double-row tapered roller bearings of high speed locomotive , 2015 .

[26]  Venkata Krishna Kishore Kolli,et al.  SVM-PUK Kernel Based MRI-brain Tumor Identification Using Texture and Gabor Wavelets , 2019, Traitement du Signal.

[27]  Guobin Lin,et al.  Internet of Things-Based Online Condition Monitor and Improved Adaptive Fuzzy Control for a Medium-Low-Speed Maglev Train System , 2020, IEEE Transactions on Industrial Informatics.

[28]  Paul Allen,et al.  Analysis of vibration and temperature on the axle box bearing of a high-speed train , 2020, Vehicle System Dynamics.

[29]  Cheng-Hao Yang,et al.  Ultra-high intensity redevelopment of the core area of Japanese rail transit hub station , 2019, International Journal of Sustainable Development and Planning.

[30]  Xiangang Li,et al.  A comparative study on selecting acoustic modeling units in deep neural networks based large vocabulary Chinese speech recognition , 2013, Neurocomputing.