Risk-Based Prognostics and Health Management

TL;DR

This paper presents a risk-based prognostics approach using continuous-time Bayesian networks to better integrate risk assessment with fault prediction, aiding decision support and logistics.

Contribution

It introduces a novel framework that tightly couples risk assessment with prognostics using Bayesian networks, and reviews techniques for model derivation from data.

Findings

Demonstrates how Bayesian networks can model risk and prognostics jointly

Provides an overview of data-driven techniques for model construction

Shows practical applications in decision support and logistics

Abstract

It is often the case that risk assessment and prognostics are viewed as related but separate tasks. This chapter describes a risk-based approach to prognostics that seeks to provide a tighter coupling between risk assessment and fault prediction. We show how this can be achieved using the continuous-time Bayesian network as the underlying modeling framework. Furthermore, we provide an overview of the techniques that are available to derive these models from data and show how they might be used in practice to achieve tasks like decision support and performance-based logistics. This work is intended to provide an overview of the recent developments related to risk-based prognostics, and we hope that it will serve as a tutorial of sorts that will assist others in adopting these techniques.