Bearing Fault Diagnosis using Wavelet Packet Transform, Hybrid PSO and Support Vector Machine☆

A new intelligent methodology in bearing condition diagnosis analysis has been proposed to predict the status of rolling bearing based on vibration signals by multi class support vector machine (MSVM), a classification algorithm. Wavelet packet transform (WPT) is used for signal processing and standard statistical feature extraction process. Feature reduction is a method used to deselect the irrelevant features acquired from the large dataset. Recent survey shows feature reduction is used widely in the field of machine learning to discover the knowledge with reduced features. Rough set is hybridized with particle swarm optimization (PSO), an population based stochastic optimization technique, to reduce the features. The efficiency of classification algorithm is compared based on their classification accuracy before and after feature reduction. Four states of bearing health conditions such as normal, defective inner race, defective outer race and defective ball conditions are simulated and used in this proposed work.

[1]  Fulei Chu,et al.  Application of the wavelet transform in machine condition monitoring and fault diagnostics: a review with bibliography , 2004 .

[2]  P. D. McFadden,et al.  Model for the vibration produced by a single point defect in a rolling element bearing , 1984 .

[3]  Ibrahim Esat,et al.  ARTIFICIAL NEURAL NETWORK BASED FAULT DIAGNOSTICS OF ROTATING MACHINERY USING WAVELET TRANSFORMS AS A PREPROCESSOR , 1997 .

[4]  B Liu.  Selection of wavelet packet basis for rotating machinery fault diagnosis , 2005 .

[5]  Chih-Jen Lin,et al.  A comparison of methods for multiclass support vector machines , 2002, IEEE Trans. Neural Networks.

[6]  Zili Liu,et al.  A Direct Selection Method of Feature Frequency , 2012, AICI 2012.

[7]  Ahmad Taher Azar,et al.  Supervised hybrid feature selection based on PSO and rough sets for medical diagnosis , 2014, Comput. Methods Programs Biomed..

[8]  B. Samanta,et al.  ARTIFICIAL NEURAL NETWORK BASED FAULT DIAGNOSTICS OF ROLLING ELEMENT BEARINGS USING TIME-DOMAIN FEATURES , 2003 .

[9]  Tsau Young Lin,et al.  Feature Subset Selection Based on Relative Dependency between Attributes , 2004, Rough Sets and Current Trends in Computing.

[10]  Mahdi Aliyari Shoorehdeli,et al.  Multi-fault diagnosis of ball bearing based on features extracted from time-domain and multi-class support vector machine(MSVM) , 2010, 2010 IEEE International Conference on Systems, Man and Cybernetics.

[11]  Ming J. Zuo,et al.  Mechanical Fault Detection Based on the Wavelet De-Noising Technique , 2004 .

[12]  B. Samanta,et al.  Gear fault detection using artificial neural networks and support vector machines with genetic algorithms , 2004 .

[13]  Ulrich H.-G. Kreßel,et al.  Pairwise classification and support vector machines , 1999 .

[14]  Yue Shi,et al.  A modified particle swarm optimizer , 1998, 1998 IEEE International Conference on Evolutionary Computation Proceedings. IEEE World Congress on Computational Intelligence (Cat. No.98TH8360).

[15]  Y. Ueno,et al.  Prediction of spalling on a ball bearing by applying the discrete wavelet transform to vibration signals , 1996 .

[16]  Xiaoran Zhu,et al.  Intelligent fault diagnosis of rolling bearing based on kernel neighborhood rough sets and statistical features , 2012 .

[17]  P. Tse,et al.  Machine fault diagnosis through an effective exact wavelet analysis , 2004 .

[18]  Junyan Yang,et al.  Intelligent fault diagnosis of rolling element bearing based on SVMs and fractal dimension , 2007 .

[19]  Zhiwen Liu,et al.  Multi-fault classification based on wavelet SVM with PSO algorithm to analyze vibration signals from rolling element bearings , 2013, Neurocomputing.

[20]  J. Halme.  Condition Monitoring of Oil Lubricated Ball Bearing Using Wear Debris and Vibration Analysis , 2002 .

[22]  Isabelle Guyon,et al.  Comparison of classifier methods: a case study in handwritten digit recognition , 1994, Proceedings of the 12th IAPR International Conference on Pattern Recognition, Vol. 3 - Conference C: Signal Processing (Cat. No.94CH3440-5).