Fault Identification Enhancement with Reinforcement Learning (FIERL)
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866913344828473344 |
|---|---|
| author | Zaccaria, Valentina Sartor, Davide Del Favero, Simone Susto, Gian Antonio |
| author_facet | Zaccaria, Valentina Sartor, Davide Del Favero, Simone Susto, Gian Antonio |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2405_04938 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Fault Identification Enhancement with Reinforcement Learning (FIERL) Zaccaria, Valentina Sartor, Davide Del Favero, Simone Susto, Gian Antonio Machine Learning 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. |
| title | Fault Identification Enhancement with Reinforcement Learning (FIERL) |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2405.04938 |