Meta-learning of data-driven controllers with automatic model reference tuning: theory and experimental case study
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914723318988800 |
|---|---|
| author | Busetto, Riccardo Breschi, Valentina Baracchi, Federica Formentin, Simone |
| author_facet | Busetto, Riccardo Breschi, Valentina Baracchi, Federica Formentin, Simone |
| contents | Data-driven control offers a viable option for control scenarios where constructing a system model is expensive or time-consuming. Nonetheless, many of these algorithms are not entirely automated, often necessitating the adjustment of multiple hyperparameters through cumbersome trial-and-error processes and demanding significant amounts of data. In this paper, we explore a meta-learning approach to leverage potentially existing prior knowledge about analogous (though not identical) systems, aiming to reduce both the experimental workload and ease the tuning of the available degrees of freedom. We validate this methodology through an experimental case study involving the tuning of proportional, integral (PI) controllers for brushless DC (BLDC) motors with variable loads and architectures. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_14500 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Meta-learning of data-driven controllers with automatic model reference tuning: theory and experimental case study Busetto, Riccardo Breschi, Valentina Baracchi, Federica Formentin, Simone Systems and Control Data-driven control offers a viable option for control scenarios where constructing a system model is expensive or time-consuming. Nonetheless, many of these algorithms are not entirely automated, often necessitating the adjustment of multiple hyperparameters through cumbersome trial-and-error processes and demanding significant amounts of data. In this paper, we explore a meta-learning approach to leverage potentially existing prior knowledge about analogous (though not identical) systems, aiming to reduce both the experimental workload and ease the tuning of the available degrees of freedom. We validate this methodology through an experimental case study involving the tuning of proportional, integral (PI) controllers for brushless DC (BLDC) motors with variable loads and architectures. |
| title | Meta-learning of data-driven controllers with automatic model reference tuning: theory and experimental case study |
| topic | Systems and Control |
| url | https://arxiv.org/abs/2403.14500 |