Adaptive early initial degradation point detection and outlier correction for bearings

Abstract

This paper delves into the accurate detection of the early initial degradation point (IDP) in bearings, and proposes, for the first time, a comprehensive adaptive IDP detection framework for bearings under variable operating conditions, along with an outlier data repair strategy. First, this study introduces the adaptive early initial degradation point detection (AEIDPD) method, which incorporates least-squares fitting to compute the slope and intercept of health indicators, and t-tests are used to construct the “sum-of-slopes” indicator. An adaptive IDP threshold construction method that adapts to variable operating conditions is proposed, establishing a strategy for IDP detection based on sum-of-slopes and adaptive thresholds. To enhance the robustness of AEIDPD in variable operating conditions, this paper introduces synchronized wavelet transform to obtain the "synchronous pseudo-speed" signal of bearing vibration, and constructs a condition interference elimination strategy based on velocity and sliding window averaging to mitigate the effects of variable operating conditions. Additionally, the study constructs upper and lower bounds for the root mean square feature of vibration signals using empirical parameters to correct outliers, providing more accurate data to support bearing life predictions. Experimental results demonstrate the effectiveness and robustness of the proposed methods.