Fault Diagnosis of Train Plug Door Based on a Hybrid Criterion for IMFs Selection and Fractional Wavelet Package Energy Entropy

The train plug door is the only way for passengers getting on and off. Its failures will make train operation ineffective. Taking the developed digital signal processing technologies into consideration, a data-driven diagnosis method for train plug doors is proposed based on sound recognition. First, a novel preprocessing method based on empirical mode decomposition and hybrid intrinsic mode functions (IMFs) selection criterion is proposed. The selected significant IMFs are used to reconstruct the signals. Inspired by the idea of fractional calculus, novel entropy named fractional wavelet package decomposition energy entropy (FWPDE) is proposed. Finally, multi-class support vector machine is used for classification and validation. Experimental results indicate that the proposed preprocessing method is of great significance to extract effective FWPDE features. In addition, FWPDE is more powerful in comparison with the classical wavelet package decomposition energy entropy. The identification accuracy using the proposed method reaches 96.28%, which demonstrates its effectiveness and superiority.

[1]  Yuan Cao,et al.  Local Fractional Functional Method for Solving Diffusion Equations on Cantor Sets , 2014 .

[2]  Pengcheng Jiang,et al.  Optimal Resonant Band Demodulation Based on an Improved Correlated Kurtosis and Its Application in Bearing Fault Diagnosis , 2017, Sensors.

[3]  Yuan Cao,et al.  Multiobjective Sizing Optimization for Island Microgrids Using a Triangular Aggregation Model and the Levy-Harmony Algorithm , 2018, IEEE Transactions on Industrial Informatics.

[4]  Paul Honeine,et al.  Multi-class SVM classification combined with kernel PCA feature extraction of ECG signals , 2012, 2012 19th International Conference on Telecommunications (ICT).

[5]  Ji-Huan He.  A Tutorial Review on Fractal Spacetime and Fractional Calculus , 2014 .

[6]  Peng Li,et al.  Parallel processing algorithm for railway signal fault diagnosis data based on cloud computing , 2018, Future Gener. Comput. Syst..

[7]  Xia Ju.  Fault Diagnosis Research for Metro Door Based on FTA , 2014 .

[8]  Feng Liu,et al.  Bio-Inspired Speed Curve Optimization and Sliding Mode Tracking Control for Subway Trains , 2019, IEEE Transactions on Vehicular Technology.

[9]  Yuanyuan Liu,et al.  EMD interval thresholding denoising based on similarity measure to select relevant modes , 2015, Signal Process..

[10]  Zhigang Liu,et al.  Traction Inverter Open Switch Fault Diagnosis Based on Choi-Williams Distribution Spectral Kurtosis and Wavelet-Packet Energy Shannon Entropy , 2017, Entropy.

[11]  A. Vincent Antony Kumar,et al.  Improving medical diagnosis performance using hybrid feature selection via relieff and entropy based genetic search (RF-EGA) approach: application to breast cancer prediction , 2019, Clust. Comput..

[12]  Hongguang Li,et al.  Chatter detection in milling process based on the energy entropy of VMD and WPD , 2016 .

[13]  Yong Zhang,et al.  Classification of EEG Signals Based on Autoregressive Model and Wavelet Packet Decomposition , 2016, Neural Processing Letters.

[14]  Sébastien Grondel,et al.  Bond Graph modeling for fault detection and isolation of a train door mechatronic system , 2016 .

[15]  Guo Xie,et al.  Strategy for Fault Diagnosis on Train Plug Doors Using Audio Sensors † , 2018, Sensors.

[16]  Zhenpo Wang,et al.  Voltage fault diagnosis and prognosis of battery systems based on entropy and Z-score for electric vehicles , 2017 .

[17]  Yong Qin,et al.  Rail Train Door System Hidden Danger Identification Based on Extended Time and Probability Petri Net , 2016 .

[18]  Tao Wen,et al.  A Safety Computer System Based on Multi-Sensor Data Processing † , 2019, Sensors.

[19]  Yuan Cao,et al.  A Fault Diagnosis Method for Train Plug Doors via Sound Signals , 2021, IEEE Intelligent Transportation Systems Magazine.

[20]  Min Li,et al.  Fault feature extraction of rolling bearing based on an improved cyclical spectrum density method , 2015 .

[21]  Clive Roberts,et al.  Use of parameter estimation for the detection and diagnosis of faults on electric train door systems , 2009 .

[22]  Zhou Ha.  Analysis of rolling bearing fault diagnosis based on EMD and kurtosis Hilbert envelope demodulation , 2014 .

[23]  Min Zhou,et al.  ECG Classification Using Wavelet Packet Entropy and Random Forests , 2016, Entropy.

[24]  Juan F. Ramirez-Villegas,et al.  Wavelet packet energy, Tsallis entropy and statistical parameterization for support vector-based and neural-based classification of mammographic regions , 2012, Neurocomputing.

[25]  Jie Wang,et al.  Device-Free Identification Using Intrinsic CSI Features , 2018, IEEE Transactions on Vehicular Technology.

[26]  Yuan Cao,et al.  Research on dynamic nonlinear input prediction of fault diagnosis based on fractional differential operator equation in high-speed train control system. , 2019, Chaos.

[27]  José António Tenreiro Machado,et al.  Fractional Order Generalized Information , 2014, Entropy.

[28]  N. Huang,et al.  The empirical mode decomposition and the Hilbert spectrum for nonlinear and non-stationary time series analysis , 1998, Proceedings of the Royal Society of London. Series A: Mathematical, Physical and Engineering Sciences.

[29]  Klaus C. J. Dietmayer,et al.  Stationary Detection of the Pedestrian?s Intention at Intersections , 2013, IEEE Intelligent Transportation Systems Magazine.