Fault Diagnosis of Rolling Bearing Based on Kernel Independent Component Analysis by Using Mixed Kernel Function

Abstract

Studies have shown that the type of kernel function and parameters have a very important impact on the performance of the kernel method. Aiming at the requirement of rolling bearing fault diagnosis, this paper presents a mixed kernel function of kernel independent component and studies on the optimization of its kernel parameters. The mixed kernel function is constructed based on the weighted fusion method, and the kernel parameters are optimized by using the genetic algorithm. The improved kernel independent component method is used for fault diagnosis of rolling bearing, and the testing results demonstrate that it is an effective method.