Uncertainty Quantification as a Complementary Latent Health Indicator for Remaining Useful Life Prediction on Turbofan Engines

TL;DR

This paper introduces a novel uncertainty-aware framework for health indicator construction using autoencoders, significantly improving remaining useful life predictions for turbofan engines by effectively separating and utilizing different types of uncertainties.

Contribution

The paper presents a new method integrating uncertainty quantification into autoencoder-based health indicators, enhancing RUL prediction accuracy over existing approaches.

Findings

Outperforms traditional health indicator methods on NASA C-MAPSS dataset

Effective separation of aleatoric and epistemic uncertainties improves RUL prediction

Demonstrates the importance of uncertainty quantification in health assessment

Abstract

Health Indicators (HIs) are essential for predicting system failures in predictive maintenance. While methods like RaPP (Reconstruction along Projected Pathways) improve traditional HI approaches by leveraging autoencoder latent spaces, their performance can be hindered by both aleatoric and epistemic uncertainties. In this paper, we propose a novel framework that integrates uncertainty quantification into autoencoder-based latent spaces, enhancing RaPP-generated HIs. We demonstrate that separating aleatoric uncertainty from epistemic uncertainty and cross combining HI information is the driver of accuracy improvements in Remaining Useful Life (RUL) prediction. Our method employs both standard and variational autoencoders to construct these HIs, which are then used to train a machine learning model for RUL prediction. Benchmarked on the NASA C-MAPSS turbofan dataset, our approach outperforms traditional HI-based methods and end-to-end RUL prediction models and is competitive with RUL estimation methods. These results underscore the importance of uncertainty quantification in health assessment and showcase its significant impact on predictive performance when incorporated into the HI construction process.