Prognostics of Multisensor Systems with Unknown and Unlabeled Failure Modes via Bayesian Nonparametric Process Mixtures

TL;DR

This paper introduces a Bayesian nonparametric framework combining failure mode discovery and prognostics, enabling adaptive, accurate predictions in complex manufacturing systems with unknown failure behaviors.

Contribution

It presents a novel iterative Bayesian approach that jointly learns failure modes and prognostics, allowing for dynamic adaptation to new failure data without prior labels.

Findings

Outperforms existing methods in simulation and aircraft engine datasets.

Demonstrates robust online adaptation for digital twin applications.

Effectively discovers and merges failure modes in real-time.

Abstract

Modern manufacturing systems often experience multiple and unpredictable failure behaviors, yet most existing prognostic models assume a fixed, known set of failure modes with labeled historical data. This assumption limits the use of digital twins for predictive maintenance, especially in high-mix or adaptive production environments, where new failure modes may emerge, and the failure mode labels may be unavailable. To address these challenges, we propose a novel Bayesian nonparametric framework that unifies a Dirichlet process mixture module for unsupervised failure mode discovery with a neural network-based prognostic module. The key innovation lies in an iterative feedback mechanism to jointly learn two modules. These modules iteratively update one another to dynamically infer, expand, or merge failure modes as new data arrive while providing high prognostic accuracy. Experiments on both simulation and aircraft engine datasets show that the proposed approach performs competitively with or significantly better than existing approaches. It also exhibits robust online adaptation capabilities, making it well-suited for digital-twin-based system health management in complex manufacturing environments.