Learning Rewards, Not Labels: Adversarial Inverse Reinforcement Learning for Machinery Fault Detection

TL;DR

This paper introduces an adversarial inverse reinforcement learning framework for machinery fault detection that learns reward functions directly from healthy operational data, enabling early and robust fault detection without manual reward engineering.

Contribution

It formulates machinery fault detection as an offline inverse reinforcement learning problem and employs adversarial training to learn reward functions from normal data, improving fault detection accuracy.

Findings

Consistently distinguishes normal and faulty samples across datasets

Enables early fault detection with low false positives

Outperforms traditional methods in benchmark tests

Abstract

Reinforcement learning (RL) offers significant promise for machinery fault detection (MFD). However, most existing RL-based MFD approaches do not fully exploit RL's sequential decision-making strengths, often treating MFD as a simple guessing game (Contextual Bandits). To bridge this gap, we formulate MFD as an offline inverse reinforcement learning problem, where the agent learns the reward dynamics directly from healthy operational sequences, thereby bypassing the need for manual reward engineering and fault labels. Our framework employs Adversarial Inverse Reinforcement Learning to train a discriminator that distinguishes between normal (expert) and policy-generated transitions. The discriminator's learned reward serves as an anomaly score, indicating deviations from normal operating behaviour. When evaluated on three run-to-failure benchmark datasets (HUMS2023, IMS, and XJTU-SY), the model consistently assigns low anomaly scores to normal samples and high scores to faulty ones, enabling early and robust fault detection. By aligning RL's sequential reasoning with MFD's temporal structure, this work opens a path toward RL-based diagnostics in data-driven industrial settings.