Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

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

Kani Fu, Sanduni S Disanayaka Mudiyanselage, Chunli Dai, Minhee Kim

TL;DR

A novel Bayesian nonparametric framework that unifies a Dirichlet process mixture module for unsupervised failure mode discovery with a neural network-based prognostic module that iteratively update one another to dynamically infer, expand, or merge failure modes as new data arrive while providing high prognostic accuracy.

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.

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

TL;DR

A novel Bayesian nonparametric framework that unifies a Dirichlet process mixture module for unsupervised failure mode discovery with a neural network-based prognostic module that iteratively update one another to dynamically infer, expand, or merge failure modes as new data arrive while providing high prognostic accuracy.

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.
Paper Structure (27 sections, 29 equations, 9 figures, 8 tables, 2 algorithms)

This paper contains 27 sections, 29 equations, 9 figures, 8 tables, 2 algorithms.

Table of Contents

  1. Introduction
  2. Literature Review
  3. Prognostics without Failure Mode Identification
  4. Prognostics with Failure Mode Identification
  5. Preliminary - Dirichlet Process and Stick-Breaking
  6. Proposed Method
  7. Nonparametric Modeling of Degradation Data under Unknown and Unlabeled Failure Modes
  8. Failure Mode-Informed RUL Prognostics
  9. Inference and Parameter Estimation
  10. Variational Inference of Failure Mode Identification Module
  11. Training of Prognostics Module
  12. Online Variational Inference for Interaction between Two Modules
  13. Birth Moves to Escape Local Optima
  14. Merge Moves to Jointly Optimize Two Modules
  15. Simulation studies
  16. ...and 12 more sections

Figures (9)

  • Figure 1: (a) Stick-breaking process. (b) A sample draw from a DP.
  • Figure 2: Overview of the DPMM-RUL
  • Figure 3: Graphical representation of the proposed framework. Shaded nodes indicate observed variables, while unshaded nodes indicate latent (unobserved) variables or parameters.
  • Figure 4: Neural network structure of RUL prediction model
  • Figure 5: Simulation sensor signal plots for the eight sensor signals of three systems (different shapes) per failure mode.
  • ...and 4 more figures