Bearing fault diagnosis analysis based on improved adaptive search algorithms and SVMs

Abstract

Bearings as an important component in the mechanical industry, its fault diagnosis is significant. The support vector machine (SVM) has a good effect in solving small sample, nonlinear and other problems. This paper optimizes the penalty function and sum function of the support vector machine based on the improved harmonic search algorithm, which effectively improves the accuracy of classification. The experimental shows that the algorithm in this paper has obvious classification effect and practicality.