Health Index Estimation Through Integration of General Knowledge with Unsupervised Learning

TL;DR

This paper introduces an unsupervised hybrid approach that integrates general degradation knowledge into a convolutional autoencoder to estimate Health Index across different systems, improving transferability and RUL prediction.

Contribution

It presents a novel unsupervised hybrid method that incorporates general knowledge into deep learning models for health index estimation, enhancing cross-system applicability.

Findings

Outperforms residual-based methods in HI quality.

Comparable to supervised models trained with HI labels.

Effective in diverse domains like engines and batteries.

Abstract

Accurately estimating a Health Index (HI) from condition monitoring data (CM) is essential for reliable and interpretable prognostics and health management (PHM) in complex systems. In most scenarios, complex systems operate under varying operating conditions and can exhibit different fault modes, making unsupervised inference of an HI from CM data a significant challenge. Hybrid models combining prior knowledge about degradation with deep learning models have been proposed to overcome this challenge. However, previously suggested hybrid models for HI estimation usually rely heavily on system-specific information, limiting their transferability to other systems. In this work, we propose an unsupervised hybrid method for HI estimation that integrates general knowledge about degradation into the convolutional autoencoder's model architecture and learning algorithm, enhancing its applicability across various systems. The effectiveness of the proposed method is demonstrated in two case studies from different domains: turbofan engines and lithium batteries. The results show that the proposed method outperforms other competitive alternatives, including residual-based methods, in terms of HI quality and their utility for Remaining Useful Life (RUL) predictions. The case studies also highlight the comparable performance of our proposed method with a supervised model trained with HI labels.