Remaining useful life prediction of rolling bearings based on Pearson correlation-KPCA multi-feature fusion

Abstract

In the feature selection process, a subset of features is selected from the original set of features based on the feature redundancy and importance. However, most of the existing methods for fusing multiple features ignore the connection between original features which leads to increased redundancy and affects the final classification results. To address this issue, in this study, an effective feature fusion method is proposed for predicting the remaining useful life (RUL) of rolling bearings based on Pearson correlation coefficient and kernel principal component analysis (KPCA). Firstly, the multi-domain features reflecting the bearing degradation state are extracted, and the correlation between the multi-domain features is obtained by Pearson correlation analysis before the feature fusion by KPCA. The features are grouped in such a way that that the correlation between the fused features is higher and the redundancy is lower. Secondly, a RUL prediction model of bearings is established based on the long short-term memory (LSTM) neural network and the Cox proportional-hazards model. In this model, the fused feature set is input into the LSTM neural network to predict the bearing performance degradation trend, which is then used as a multi-dimensional covariate in the Cox proportional-hazards model to assess the reliability of the bearing over time, thereby predicting the bearing RUL. Finally, based on experimental verification, the bearing failure prediction error for two different bearings is obtained to be 1.6 % and 3.4 %, which indicates the feasibility and efficacy of the proposed method for RUL prediction of mechanical equipment.