无需故障标签，用逆强化学习预测设备寿命
Label-free Industrial Fault Detection via Adversarial Inverse Reinforcement Learning: A System for Run-to-Failure Prognostics
- 通过逆强化学习从状态转移中自动学习健康奖励函数
- 在三个真实数据集上均实现持续稳定的故障检测
- 适合缺乏标注数据的工业设备运维场景
机械故障检测（MFD）仍严重依赖有监督学习，而实际场景中故障标签稀缺。尽管强化学习（RL）能建模退化过程的时序特性，现有基于RL的方法却将问题简化为静态上下文赌博机（CB）：忽略状态转移并舍弃时间折扣因子，最终退化为标准分类。本文提出对抗式逆强化学习（AIRL）框架，将MFD视为离线逆强化学习问题。与依赖静态误差阈值的重构方法或忽略动态特性的CB不同，本方法直接从观测状态转移中恢复内在“健康”奖励，无需人工设计奖励或故障标签。在三个跑至失效基准数据集（HUMS2023、IMS、XJTU-SY）上，AIRL是唯一在所有数据集上均实现非饱和后检测一致性的方法，而CB基线无法检测渐进退化，重构模型则陷入始终异常的状态。代码与数据：https://github.com/dhirajneupane/AIRL-MFD-DN。
原文摘要 · Abstract (English)
Machinery fault detection (MFD) remains heavily reliant on supervised learning, which struggles with the scarcity of fault labels in real-world settings. While reinforcement learning (RL) offers a framework to model the sequential nature of degradation, current ``RL-based'' MFD methods reduce the problem to a static contextual bandit (CB) formulation: by ignoring state transitions and discarding the temporal discount factor, they collapse to standard supervised classification. We propose an adversarial inverse reinforcement learning (AIRL) framework that treats MFD as an offline IRL problem. Unlike reconstruction-based approaches that rely on static error margins, or CBs that ignore dynamics, our method recovers an intrinsic "health" reward directly from observational state transitions, requiring neither manual reward engineering nor fault labels. On three run-to-failure benchmarks (HUMS2023, IMS, XJTU-SY), AIRL is the only method achieving non-saturated post-detection consistency across all datasets, while CB baselines fail to detect gradual degradation and reconstruction models collapse into always-anomalous states. Code and data: https://github.com/dhirajneupane/AIRL-MFD-DN.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。