Support vector machine based optimization of multi-fault classification of gears with evolutionary algorithms from time–frequency vibration data

A multi-fault classification of gears has been attempted by support vector machine (SVM) learning techniques with the help of time–frequency (wavelet) vibration data. A suitable exploitation of SVM is based on the selection of SVM parameters. The main focus of the present paper is to study the performance of the multiclass capability of SVM techniques. Different optimization methods (i.e., the grid-search method (GSM), the genetic algorithm (GA) and the artificial bee colony algorithm (ABCA)) have been performed for optimizing SVM parameters. Four fault conditions of gears have been considered. The continuous wavelet transform (CWT) and wavelet packet transform (WPT) are estimated from time domain signals, and a set of statistical features are extracted from the wavelet transform. The prediction of fault classification has been attempted at the same angular speed as the measured data as well as innovatively at the intermediate and extrapolated angular speed conditions, since it is not feasible to have measurement of vibration data at continuous speeds of interest. The classification ability is noted and compared with predictions when purely time domain data is used, and it shows an excellent prediction performance.