Predicting Survival Time of Ball Bearings in the Presence of Censoring

TL;DR

This paper introduces a survival analysis approach to predict the failure time of ball bearings, effectively handling censored data and providing probabilistic risk assessments, validated on real datasets with promising accuracy.

Contribution

It presents a novel method combining frequency domain analysis and survival models to predict bearing failure times with censored data, advancing predictive maintenance techniques.

Findings

Achieved a 0.70 concordance-index on XJTU dataset.

Achieved a 0.76 concordance-index on PRONOSTIA dataset.

Demonstrated the effectiveness of survival models in bearing failure prediction.

Abstract

Ball bearings find widespread use in various manufacturing and mechanical domains, and methods based on machine learning have been widely adopted in the field to monitor wear and spot defects before they lead to failures. Few studies, however, have addressed the problem of censored data, in which failure is not observed. In this paper, we propose a novel approach to predict the time to failure in ball bearings using survival analysis. First, we analyze bearing data in the frequency domain and annotate when a bearing fails by comparing the Kullback-Leibler divergence and the standard deviation between its break-in frequency bins and its break-out frequency bins. Second, we train several survival models to estimate the time to failure based on the annotated data and covariates extracted from the time domain, such as skewness, kurtosis and entropy. The models give a probabilistic prediction of risk over time and allow us to compare the survival function between groups of bearings. We demonstrate our approach on the XJTU and PRONOSTIA datasets. On XJTU, the best result is a 0.70 concordance-index and 0.21 integrated Brier score. On PRONOSTIA, the best is a 0.76 concordance-index and 0.19 integrated Brier score. Our work motivates further work on incorporating censored data in models for predictive maintenance.