A Combination of WKNN to Fault Diagnosis of Rolling Element Bearings

This paper presents a new method for fault diagnosis of rolling element bearings, which is developed based on a combination of weighted K nearest neighbor WKNN classifiers. This method uses wavelet packet transform based on the lifting scheme to preprocess the vibration signals before feature extraction. Time- and frequency-domain features are all extracted to represent the operation conditions of the bearings totally. Sensitive features are selected after feature extraction. And then, multiple classifiers based on WKNN are combined to overcome the two disadvantages of KNN and therefore it may enhance the classification accuracy. The experimental results of the proposed method to fault diagnosis of the rolling element bearings show that this method enables the detection of abnormalities in bearings and at the same time identification of fault categories and levels. DOI: 10.1115/1.4000478

[1]  Jiang Hongkai,et al.  A sliding window feature extraction method for rotating machinery based on the lifting scheme , 2007 .

[2]  Xavier Chiementin,et al.  Early Detection of Fatigue Damage on Rolling Element Bearings Using Adapted Wavelet , 2007 .

[3]  Zheng Hu,et al.  Detecting and Predicting Early Faults of Complex Rotating Machinery Based on Cyclostationary Time Series Model , 2006 .

[4]  Yaguo Lei,et al.  Application of the EEMD method to rotor fault diagnosis of rotating machinery , 2009 .

[5]  K. Loparo,et al.  Bearing fault diagnosis based on wavelet transform and fuzzy inference , 2004 .

[6]  C. A. Murthy,et al.  On visualization and aggregation of nearest neighbor classifiers , 2005, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[7]  Yaguo Lei,et al.  Application of a Novel Hybrid Intelligent Method to Compound Fault Diagnosis of Locomotive Roller Bearings , 2008 .

[8]  Leon N. Cooper,et al.  Neighborhood size selection in the k-nearest-neighbor rule using statistical confidence , 2006, Pattern Recognit..

[9]  S. J. Loutridis,et al.  Self-Similarity in Vibration Time Series: Application to Gear Fault Diagnostics , 2008 .

[10]  Yan Qiu Chen,et al.  Improving nearest neighbor classification with cam weighted distance , 2006, Pattern Recognit..

[11]  Yaguo Lei,et al.  New clustering algorithm-based fault diagnosis using compensation distance evaluation technique , 2008 .

[12]  Wim Sweldens,et al.  The lifting scheme: a construction of second generation wavelets , 1998 .

[13]  Leon N. Cooper,et al.  Improving nearest neighbor rule with a simple adaptive distance measure , 2007, Pattern Recognit. Lett..

[14]  W. Sweldens.  The Lifting Scheme: A Custom - Design Construction of Biorthogonal Wavelets "Industrial Mathematics , 1996 .

[15]  Patrick S. K. Chua,et al.  Vibration analysis with lifting scheme and generalized cross validation in fault diagnosis of water hydraulic system , 2007 .

[16]  Sanghamitra Bandyopadhyay,et al.  Genetic algorithms for generation of class boundaries , 1998, IEEE Trans. Syst. Man Cybern. Part B.

[17]  Qiao Hu,et al.  Fault diagnosis of rotating machinery based on multiple ANFIS combination with GAs , 2007 .

[18]  I. Daubechies,et al.  Factoring wavelet transforms into lifting steps , 1998 .