An Unsupervised Framework for Dynamic Health Indicator Construction and Its Application in Rolling Bearing Prognostics

TL;DR

This paper introduces an unsupervised framework for constructing dynamic health indicators that capture temporal dependencies in degradation processes, improving prognostics for rolling bearings.

Contribution

It proposes a novel unsupervised method combining autoencoder-based feature learning and a new HI-generating module with temporal modeling, addressing limitations of existing approaches.

Findings

Outperforms existing methods in degradation trend representation

Enhances accuracy of bearing prognostics

Captures dynamic information effectively

Abstract

Health indicator (HI) plays a key role in degradation assessment and prognostics of rolling bearings. Although various HI construction methods have been investigated, most of them rely on expert knowledge for feature extraction and overlook capturing dynamic information hidden in sequential degradation processes, which limits the ability of the constructed HI for degradation trend representation and prognostics. To address these concerns, a novel dynamic HI that considers HI-level temporal dependence is constructed through an unsupervised framework. Specifically, a degradation feature learning module composed of a skip-connection-based autoencoder first maps raw signals to a representative degradation feature space (DFS) to automatically extract essential degradation features without the need for expert knowledge. Subsequently, in this DFS, a new HI-generating module embedded with an inner HI-prediction block is proposed for dynamic HI construction, where the temporal dependence between past and current HI states is guaranteed and modeled explicitly. On this basis, the dynamic HI captures the inherent dynamic contents of the degradation process, ensuring its effectiveness for degradation tendency modeling and future degradation prognostics. The experiment results on two bearing lifecycle datasets demonstrate that the proposed HI construction method outperforms comparison methods, and the constructed dynamic HI is superior for prognostic tasks.