Application of a KPCA-KICA-HSSVM hybrid strategy in bearing fault detection

In Modern industrial, bearings are common in rotating machines. The processing data of bearings are nonlinear, and they usually are complicated distribution, which contains both Gaussian and non-Gaussian distributions. If using a single data distribution detection method, it will result in detecting performance degradation. To solve the possible monitoring difficulties of complicated distribution and nonlinear characteristics in industrial systems, this paper proposes a KPCA-KICA-HSSVM hybrid strategy. The proposed method uses KPCA, KICA and HSSVM to establish detection model, these models are work collaboratively in monitoring the real time process data to detect the possible faults. The proposed approach was tested and validated via a set of experimental data collected from a bearing test rig. Experimental results demonstrate the effectiveness of this approach.