A method based on Dempster-Shafer theory and support vector regression-particle filter for remaining useful life prediction of crusher roller sleeve

Abstract

In order to solve the problem of accurately predicting the remaining useful life (RUL) of crusher roller sleeve under the partially observable and nonlinear nonstationary running state, a new method of RUL prediction based on Dempster-Shafer (D-S) data fusion and support vector regression-particle filter (SVR-PF) is proposed. First, it adopts the correlation analysis to select the features of temperature and vibration signal, and subsequently utilize wavelet to denoising the features. Lastly, comparing the prediction performance of the proposed method integrates temperature and vibration signal sources to predict the RUL with the prediction performance of single source and other prediction methods. The experiment results indicate that the proposed prediction method is capable of fusing different data sources to predict the RUL and the prediction accuracy of RUL can be improved when data are less available.