An effective health indicator for bearing using corrected conditional entropy through diversity-driven multi-parent evolutionary algorithm

Abstract

The bearing vibration signal possesses nonlinear and non-stationary characteristics; hence; it is difficult to diagnosis the faults in the bearing under different working conditions. In this article, a new scheme has been proposed based on complete ensemble empirical mode decomposition with adaptive noise and corrected conditional entropy to recognize the different class of faults in bearing. The mode with minimum corrected conditional entropy is treated as a prominent mode from which sensitive features are extracted. A filter-based feature selection scheme is used for the same and for ranking the features based on variance to reduce the redundancy of data set. This data set is made input to support vector machine. The performance of the support vector machine classifier is improved by optimizing its parameters to obtain maximum classification accuracy. To address this issue, an evolutionary algorithm (diversity-driven multi-parent evolutionary algorithm) is used. With optimized support vector machine parameters, the support vector machine is trained to build a classification model with 10-fold cross-validation. After training, the built model is tested against test data set for fitness evaluation. The support vector machine classifier gives 100% accuracy at regularization and kernel parameter’s value of 1.3343 and of 782.6329, respectively, with 27.93 s of training time for a single iteration.