Intelligent bearing fault monitoring system using support vector machine and wavelet packet decomposition for induction motors

In this paper an intelligent condition monitoring of induction motor based on the wavelet packet decomposition and time domain features have been presented. The classification has been done using the support vector machine (SVM) on the basis of statistical learning theory. The data has been collected on a 10 HP induction motor in the lab having different bearing defects using piezoelectric type accelerometer. The signal is then processed to extract the time domain and wavelet features. Wavelet packet decomposition is used to extract the features from time-frequency domain. In this work, 3rd level wavelet packet decomposition has been considered. The experimental results shows that the classification of the bearing faults of the induction motor based on wavelet packet decomposition and time domain features and pattern recognition using support vector machine provides a new approach for intelligent bearing fault diagnosis of induction motor. GUI using MATLAB is developed for the work to make it more users friendly.