Accounts of using the Tustin-Net architecture on a rotary inverted pendulum
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_ | 1866914920754315264 |
|---|---|
| author | van Esch, Stijn Bonassi, Fabio Schön, Thomas B. |
| author_facet | van Esch, Stijn Bonassi, Fabio Schön, Thomas B. |
| contents | In this report we investigate the use of the Tustin neural network architecture (Tustin-Net) for the identification of a physical rotary inverse pendulum. This physics-based architecture is of particular interest as it builds on the known relationship between velocities and positions. We here aim at discussing the advantages, limitations and performance of Tustin-Nets compared to first-principles grey-box models on a real physical apparatus, showing how, with a standard training procedure, the former can hardly achieve the same accuracy as the latter. To address this limitation, we present a training strategy based on transfer learning that yields Tustin-Nets that are competitive with the first-principles model, without requiring extensive knowledge of the setup as the latter. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2408_12266 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Accounts of using the Tustin-Net architecture on a rotary inverted pendulum van Esch, Stijn Bonassi, Fabio Schön, Thomas B. Systems and Control Machine Learning In this report we investigate the use of the Tustin neural network architecture (Tustin-Net) for the identification of a physical rotary inverse pendulum. This physics-based architecture is of particular interest as it builds on the known relationship between velocities and positions. We here aim at discussing the advantages, limitations and performance of Tustin-Nets compared to first-principles grey-box models on a real physical apparatus, showing how, with a standard training procedure, the former can hardly achieve the same accuracy as the latter. To address this limitation, we present a training strategy based on transfer learning that yields Tustin-Nets that are competitive with the first-principles model, without requiring extensive knowledge of the setup as the latter. |
| title | Accounts of using the Tustin-Net architecture on a rotary inverted pendulum |
| topic | Systems and Control Machine Learning |
| url | https://arxiv.org/abs/2408.12266 |