Closed-loop training of static output feedback neural network controllers for large systems: A distillation case study
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866929732953571328 |
|---|---|
| author | Turan, E. M. Jäschke, J. |
| author_facet | Turan, E. M. Jäschke, J. |
| contents | The online implementation of model predictive control for constrained multivariate systems has two main disadvantages: it requires an estimate of the entire model state and an optimisation problem must be solved online. These issues have typically been treated separately. This work proposes an integrated approach for the offline training of an output feedback neural network controller in closed loop. Online this neural network controller computers the plant inputs cheaply using noisy measurements. In addition, the controller can be trained to only make use of certain predefined measurements. Further, a heuristic approach is proposed to perform the automatic selection of important measurements. The proposed method is demonstrated by extensive simulations using a non-linear distillation column model of 50 states. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_19309 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Closed-loop training of static output feedback neural network controllers for large systems: A distillation case study Turan, E. M. Jäschke, J. Systems and Control Optimization and Control The online implementation of model predictive control for constrained multivariate systems has two main disadvantages: it requires an estimate of the entire model state and an optimisation problem must be solved online. These issues have typically been treated separately. This work proposes an integrated approach for the offline training of an output feedback neural network controller in closed loop. Online this neural network controller computers the plant inputs cheaply using noisy measurements. In addition, the controller can be trained to only make use of certain predefined measurements. Further, a heuristic approach is proposed to perform the automatic selection of important measurements. The proposed method is demonstrated by extensive simulations using a non-linear distillation column model of 50 states. |
| title | Closed-loop training of static output feedback neural network controllers for large systems: A distillation case study |
| topic | Systems and Control Optimization and Control |
| url | https://arxiv.org/abs/2402.19309 |