Safety region estimation and state identification of rolling bearings based on LMD-PCA-LSSVM

The idea of safety region estimation was introduced into state monitoring of rolling bearings, the safety region boundary estimation and state identification of rolling bearings were conducted using a new method of combination of local mean decomposition (LMD), principal component analysis (PCA) and least square support vector machine (LSSVM). Based on the collected vibration data of rolling bearings under four different states (normal, ball defect, inner race defect and outer race defect), the data were divided into a number of data pieces, and product functions (PFs) of each piece were gained with LMD. And then, with the PFs, two statistical variables control limits as the state characteristics were calculated with PCA. The boundaries of the safety region and the identification results of four states were obtained based on two control limits data classification using two-classification LSSVM and multi-classification LSSVM respectively. Finally, the test results indicated that the accuracies of the safety region estimation and state identification are both satisfying, and the effective ness and feasibility of LMD-PCA-LSSVM method are verified.