Deep Learning-Based Residual Useful Lifetime Prediction for Assets with Uncertain Failure Modes

TL;DR

This paper presents deep learning-based models for predicting the residual useful lifetime of complex assets with multiple, overlapping failure modes, addressing challenges like unlabeled data and signal similarity in industrial prognostics.

Contribution

It introduces two novel prognostic models combining mixture (log)-location-scale distributions with deep learning, enabling failure mode-agnostic predictions and improved accuracy.

Findings

Models outperform existing methods in numerical studies.

Effectively handle unlabeled data and overlapping signals.

Capture complex nonlinear relationships in degradation data.

Abstract

Industrial prognostics focuses on utilizing degradation signals to forecast and continually update the residual useful life of complex engineering systems. However, existing prognostic models for systems with multiple failure modes face several challenges in real-world applications, including overlapping degradation signals from multiple components, the presence of unlabeled historical data, and the similarity of signals across different failure modes. To tackle these issues, this research introduces two prognostic models that integrate the mixture (log)-location-scale distribution with deep learning. This integration facilitates the modeling of overlapping degradation signals, eliminates the need for explicit failure mode identification, and utilizes deep learning to capture complex nonlinear relationships between degradation signals and residual useful lifetimes. Numerical studies validate the superior performance of these proposed models compared to existing methods.