RL-ACID: Reinforcement Learning-Optimized Adaptive Causal Discovery for Robust Anomaly Detection in Industrial Systems
发布时间：2026-02-12 点击次数：
姚羽（教授）
+
- 博士生导师 硕士生导师
- 电子邮箱：
- 职务：复杂网络系统安全保障技术教育部工程研究中心主任
- 学历：博士研究生毕业
- 性别：男
- 联系方式：yaoyu@mail.neu.edu.cn
- 学位：博士
- 毕业院校：东北大学
- 所属院系：计算机科学与工程学院
- 学科：
计算机应用技术
计算机软件与理论
计算机系统结构
- 发表刊物：IEEE Transactions on Industrial Informatics
- 影响因子：9.9
- 摘要：Anomaly detection is essential for the security of industrial control systems. However, dynamic operating conditions introduce nonstationarity and time-varying causal structures, degrading performance and undermining interpretability. To address this, we propose RL-ACID, a lightweight reinforcement learning framework for adaptive causal discovery. It reformulates anomaly detection as sequential causal discovery, introducing the first unified architecture that integrates lightweight reinforcement learning-based search with causal clustering to resolve the adaptability, efficiency, and interpretability tradeoff. Our framework employs a joint time-frequency encoder to extract and construct candidate causal graphs. Building upon this, we design the causal reinforcement learning-based lightweight search algorithm, which formulates graph exploration as a sequential decision process under sparsity and acyclicity constraints, enabling iterative causal structure optimization. To further enhance adaptability in dynamic environments, we introduce a causal clustering module that softly assigns time-varying graphs to latent operational modes through structural experts, thereby distinguishing normal operational fluctuations from true anomalies. Extensive experiments on multiple industrial benchmarks demonstrate the superior performance of RL-ACID. Our framework not only achieves higher accuracy than baselines but also provides interpretable anomaly analysis through causal path tracing.
- 论文类型：SCI JCR Q1
- 备注：https://ieeexplore.ieee.org/document/11365582
- 学科门类：工学
- 文献类型：JCR 一区
- 是否译文：否