Health Index Estimation Through Integration of General Knowledge with Unsupervised Learning
This work addresses the problem of reliable and interpretable prognostics and health management for complex systems like engines and batteries, offering a more transferable solution than previous system-specific methods, though it is incremental as it builds on existing hybrid models.
The authors tackled the challenge of estimating a Health Index from condition monitoring data under varying conditions and fault modes by proposing an unsupervised hybrid method that integrates general degradation knowledge into a convolutional autoencoder, enhancing transferability across systems. The method outperformed competitive alternatives in two case studies (turbofan engines and lithium batteries), showing improved HI quality and utility for Remaining Useful Life predictions, with performance comparable to supervised models.
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.