International Conference on Sensing, Measurement & Data Analytics in the era of Artificial Intelligence (ICSMD 2022)

Rolling element bearing is a critical component in a machinery, so its remaining useful life (RUL) prediction becomes a research hotspot in recent years. In this work, a RUL prediction method based on stack denoising autoencoder (SDA) and non-overlapping sliding window (NOSW) threshold method is proposed. The health indicator is constructed by the SDA from 19 time-domain features, which balances the sensitivity and robustness of different features. A novel NOSW threshold method is used to identify the degradation initial time and divide the life cycle into normal operating stage and degradation stage. A state-space model based on the Paris-Erdogan model is established and its noise intensity is estimated by a smoothing estimation method. The particle filtering is employed to track the degradation path and quantify the uncertainty of RUL prediction.

remaining useful life;stack denoising autoencoder;particle filter;Paris-Erdogan model;state-space model