Efficient fault diagnosis of ball bearing using ReliefF and Random Forest classifier

The present study focuses on identifying various faults present in ball bearing from the measured vibration signal. Features such as kurtosis, skewness, mean, and root mean square, and complexity measure such as Shannon Entropy are calculated from time domain and Discrete Wavelet Transform. To select the best wavelet function, Maximum Energy to Shannon Entropy ratio criterion is used. Information Gain and ReliefF ranking methods are used to assess the quality of features and features are ranked based on the weight gain obtained from the methods used. Support Vector Machine and Random Forest classifier are selected to identify bearing faults and comparison is made to diagnose faults on the ranked feature set. Experiments are conducted on Case Western Reserve University bearing data sets. Results show that ranking method is useful for identifying best feature set and to improve classification accuracy simultaneously. Cross-validation efficiency of 98.38% is obtained when ReliefF is used with Random Forest.

[1]  Igor Kononenko,et al.  Estimating Attributes: Analysis and Extensions of RELIEF , 1994, ECML.

[2]  Satish C. Sharma,et al.  Fault diagnosis of ball bearings using machine learning methods , 2011, Expert Syst. Appl..

[3]  Satish C. Sharma,et al.  Rolling element bearing fault diagnosis using wavelet transform , 2011, Neurocomputing.

[4]  N. Tandon,et al.  A comparison of some condition monitoring techniques for the detection of defect in induction motor ball bearings , 2007 .

[5]  Amir-Massoud Bidgoli,et al.  A Hybrid Feature Selection Method to Improve Performance of a Group of Classification Algorithms , 2013, ArXiv.

[6]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[7]  David G. Stork,et al.  Pattern Classification , 1973 .

[8]  Naim Baydar,et al.  A comparative study of acoustic and vibration signals in detection of gear failures using Wigner-Ville distribution. , 2001 .

[9]  A. Mohanty,et al.  APPLICATION OF DISCRETE WAVELET TRANSFORM FOR DETECTION OF BALL BEARING RACE FAULTS , 2002 .

[10]  Sukhjeet Singh,et al.  Combined rotor fault diagnosis in rotating machinery using empirical mode decomposition , 2014 .

[11]  Chun-Chieh Wang,et al.  Multi-Scale Analysis Based Ball Bearing Defect Diagnostics Using Mahalanobis Distance and Support Vector Machine , 2013, Entropy.

[12]  Pavan Kumar Kankar,et al.  Ball Bearing Fault Diagnosis Using Supervised and Unsupervised Machine Learning Methods , 2015 .

[13]  Weihua Li,et al.  Bearing Condition Recognition and Degradation Assessment under Varying Running Conditions Using NPE and SOM , 2014 .

[14]  P. K. Kankar,et al.  A multiscale permutation entropy based approach to select wavelet for fault diagnosis of ball bearings , 2015 .

[15]  Junsheng Cheng,et al.  Multiscale Permutation Entropy Based Rolling Bearing Fault Diagnosis , 2014 .

[16]  Ioannis Antoniadis,et al.  Rolling element bearing fault diagnosis using wavelet packets , 2002 .

[17]  Pavan Kumar Kankar,et al.  Fault Classification of Ball Bearing by Rotation Forest Technique , 2016 .

[18]  Satish C. Sharma,et al.  Fault diagnosis of ball bearings using continuous wavelet transform , 2011, Appl. Soft Comput..

[19]  Jun Ni,et al.  A comparative study on damage detection in speed-up and coast-down process of grinding spindle-typed rotor-bearing system , 2007 .

[20]  Vladimir Vapnik,et al.  Statistical learning theory , 1998 .

[21]  Karthik Kappaganthu,et al.  Feature Selection for Fault Detection in Rolling Element Bearings Using Mutual Information , 2011 .

[22]  Kostas Karatzas,et al.  Computational intelligence methods for rolling bearing fault detection , 2016 .

[23]  Robert X. Gao,et al.  Base Wavelet Selection for Bearing Vibration Signal Analysis , 2009, Int. J. Wavelets Multiresolution Inf. Process..

[24]  Bo-Suk Yang,et al.  Random forests classifier for machine fault diagnosis , 2008 .

[25]  Ian H. Witten,et al.  The WEKA data mining software: an update , 2009, SKDD.

[26]  E. P. de Moura,et al.  Evaluation of principal component analysis and neural network performance for bearing fault diagnosis from vibration signal processed by RS and DF analyses , 2011 .

[27]  Pavan Kumar Kankar,et al.  Nonlinear Vibration Signature Analysis of a High Speed Rotor Bearing System Due to Race Imperfection , 2012 .

[28]  Yongbo Li,et al.  A new rolling bearing fault diagnosis method based on multiscale permutation entropy and improved support vector machine based binary tree , 2016 .

[29]  Kurt Hornik,et al.  The support vector machine under test , 2003, Neurocomputing.

[30]  Shaojiang Dong,et al.  Application of fuzzy C-means method and classification model of optimized K-nearest neighbor for fault diagnosis of bearing , 2016 .

[31]  Xiang Wang,et al.  Bearing Fault Diagnosis Based on Statistical Locally Linear Embedding , 2015, Sensors.

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