Feature Selection for Enhancement of Bearing Fault Detection and Diagnosis Based on Self-Organizing Map

Mechanical faults account for a large majority of the faults in the electrical rotating machinery, it can result in partial or total breakdown of a motor. Therefore, their diagnosis is an intensively investigated field of research. This paper investigates the application of the Self-Organizing Maps (SOM) for the detection of rolling element bearing damages in three phase induction motor. It discusses the integration of features selection methods in the fault classification system based on SOM. The bearings vibration signal is obtained from experiment in different conditions: normal bearing, bearing with inner race fault, bearing with outer race fault and bearings with balls fault. Then multiple features extraction techniques from time, frequency and time-frequency domains are used. ReliefF and min redundancy max Relevance (mRMR) features selection techniques are used to select the optimal features and reduce the dimension of calculated data. Finally, the SOM is used for classification of the different conditions. The obtained results show that the association of feature selection techniques to SOM classifier conduct to the improvement the classification performances of the fault detection process.

[1]  V. Sugumaran,et al.  Effect of number of features on classification of roller bearing faults using SVM and PSVM , 2011, Expert Syst. Appl..

[2]  Marko Robnik-Sikonja,et al.  Theoretical and Empirical Analysis of ReliefF and RReliefF , 2003, Machine Learning.

[3]  Ibrahim Senol,et al.  Detection of bearing defects in three-phase induction motors using Park’s transform and radial basis function neural networks , 2006 .

[4]  Nader Sawalhi,et al.  Fault Severity Estimation in Rotating Mechanical Systems Using Feature Based Fusion and Self-Organizing Maps , 2010, ICANN.

[5]  Esa Alhoniemi,et al.  Self-organizing map in Matlab: the SOM Toolbox , 1999 .

[6]  T. A. Harris,et al.  Rolling Bearing Analysis , 1967 .

[7]  Ngoc-Tu Nguyen,et al.  Optimal feature selection using genetic algorithm for mechanical fault detection of induction motor , 2008 .

[8]  Robert X. Gao,et al.  Wavelets for fault diagnosis of rotary machines: A review with applications , 2014, Signal Process..

[9]  Teuvo Kohonen,et al.  Self-Organizing Maps , 2010 .

[10]  Norden E. Huang,et al.  New method for nonlinear and nonstationary time series analysis: empirical mode decomposition and Hilbert spectral analysis , 2000, SPIE Defense + Commercial Sensing.

[11]  Yubao Chen,et al.  Fuzzy decision system for fault classification under high levels of uncertainty , 1995 .

[12]  Fuhui Long,et al.  Feature selection based on mutual information criteria of max-dependency, max-relevance, and min-redundancy , 2003, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[13]  Bo Ma,et al.  Incipient fault diagnosis of rolling element bearing based on wavelet packet transform and energy operator , 2011 .

[14]  Yaguo Lei,et al.  A review on empirical mode decomposition in fault diagnosis of rotating machinery , 2013 .

[15]  Guillermo R. Bossio,et al.  Self-organizing map approach for classification of mechanical and rotor faults on induction motors , 2012, Neural Computing and Applications.

[16]  Laibin Zhang,et al.  Degradation assessment of bearing fault using SOM network , 2011, 2011 Seventh International Conference on Natural Computation.

[17]  Sulochana Wadhwani,et al.  Automatic Fault Classification of Rolling Element Bearing using Wavelet Packet Decomposition and Artificial Neural Network , 2011 .

[18]  Said Touati,et al.  Stator Faults Detection and Diagnosis in Reactor Coolant Pump Using Kohonen Self-organizing Map , 2013, Modeling Approaches and Algorithms for Advanced Computer Applications.

[19]  Chris K. Mechefske,et al.  Fault detection and diagnosis in low speed rolling element bearings Part I: The use of parametric spectra , 1992 .

[20]  Bing Li,et al.  A Two Stage Feature Selection Method for Gear Fault Diagnosis Using ReliefF and GA-Wrapper , 2009, 2009 International Conference on Measuring Technology and Mechatronics Automation.

[21]  Yaguo Lei,et al.  A new approach to intelligent fault diagnosis of rotating machinery , 2008, Expert Syst. Appl..

[22]  Robert X. Gao,et al.  PCA-based feature selection scheme for machine defect classification , 2004, IEEE Transactions on Instrumentation and Measurement.

[23]  Kimmo Kiviluoto,et al.  Topology preservation in self-organizing maps , 1996, Proceedings of International Conference on Neural Networks (ICNN'96).

[24]  A. Al-Ghandoor,et al.  An Intelligent Machine Condition Monitoring System Using Time-Based Analysis: Neuro-Fuzzy Versus Neural Network , 2009 .

[25]  Jafar Zarei,et al.  Induction motors bearing fault detection using pattern recognition techniques , 2012, Expert Syst. Appl..