RESIDUAL LiFE PREDICTION OF HIGH SPEED ROLLING ELEMENT BEARING BY USING SOFT COMPUTING TECHNIQUES

Abstract

Prognostic of future health state relies on the estimation of the Remaining Useful Life (RUL) of physical systems or components based on their current health state. There are three model methods model base, experience base and data-driven based that is used for the prediction of life of ball bearing. Data driven prognostics method is used which is based on the transformation of the data provided by the sensors into models that are able to characterize the behavior of the degradation of bearings. For this reason I have used Mixture of Gaussian Hidden Markov Models (MoG-FIMMs) for the analysis of RUL of ball bearing. Where wavelet transform is taken as feature extraction parameter for the input of calculating the parameter of MOG-HMM.