Reinforcement learning-based integrated active fault diagnosis and tracking control. (January 2023)

• Record Type: Journal Article
• Authors: Yan, Zichen; Xu, Feng; Tan, Junbo; Liu, Houde; Liang, Bin
• Is Part Of: ISA transactions. Volume 132(2023)
• Page Start: 364
• Page End: 376
• Publication Date: 2023-01
• Subjects: Active fault diagnosis -- Fault-tolerant control -- Constrained reinforcement learning -- Maximum mean discrepancy; Engineering instruments -- Periodicals; Engineering instruments; Periodicals; Electronic journals; 629.805
• DOI: 10.1016/j.isatra.2022.06.020
• Languages: English
• ISSNs: 0019-0578

Abstract

Abstract: Reliable and real-time active diagnosis of system faults with uncertainties is strongly dependent on the input design. This paper establishes a data-driven framework for integrated design of active fault diagnosis and control while ensuring the tracking performance. To be specific, the input design is formulated as a constrained optimization problem that can be solved with the aid of constrained reinforcement learning algorithms. Moreover, based on the maximum mean discrepancy metric, a novel active fault isolation scheme is proposed to implement model discrimination using system outputs. At the end, the effectiveness of the proposed approach is evaluated in two case studies in the presence of probabilistic disturbances and uncertainties. Highlights: A data-driven framework for active fault diagnosis with tracking performance guarantees. Constrained reinforcement learning is applied in the integrated design of active inputs. A fault isolation strategy to implement model discrimination based on system outputs.