Fault Identification Enhancement with Reinforcement Learning (FIERL)
This work addresses fault identification in systems like actuators, offering a general method that is incremental as it builds on existing AFD literature by explicitly framing it in a two-part structure.
The paper tackles the problem of Active Fault Detection by separating it into Passive Fault Detection and control input design, introducing FIERL, a simulation-based approach using Constrained Reinforcement Learning to optimize control strategies for arbitrary passive detectors, which demonstrated robustness by generalizing to unseen fault dynamics in a benchmark actuator fault diagnosis test.
This letter presents a novel approach in the field of Active Fault Detection (AFD), by explicitly separating the task into two parts: Passive Fault Detection (PFD) and control input design. This formulation is very general, and most existing AFD literature can be viewed through this lens. By recognizing this separation, PFD methods can be leveraged to provide components that make efficient use of the available information, while the control input is designed in order to optimize the gathering of information. The core contribution of this work is FIERL, a general simulation-based approach for the design of such control strategies, using Constrained Reinforcement Learning (CRL) to optimize the performance of arbitrary passive detectors. The control policy is learned without the need of knowing the passive detector inner workings, making FIERL broadly applicable. However, it is especially useful when paired with the design of an efficient passive component. Unlike most AFD approaches, FIERL can handle fairly complex scenarios such as continuous sets of fault modes. The effectiveness of FIERL is tested on a benchmark problem for actuator fault diagnosis, where FIERL is shown to be fairly robust, being able to generalize to fault dynamics not seen in training.