Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2511.04522 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908710883819520 |
|---|---|
| author | Mayfrank, Daniel Dernek, Kayra Lang, Laura Mitsos, Alexander Dahmen, Manuel |
| author_facet | Mayfrank, Daniel Dernek, Kayra Lang, Laura Mitsos, Alexander Dahmen, Manuel |
| contents | With our recently proposed method based on reinforcement learning (Mayfrank et al. (2024), Comput. Chem. Eng. 190), Koopman surrogate models can be trained for optimal performance in specific (economic) nonlinear model predictive control ((e)NMPC) applications. So far, our method has exclusively been demonstrated on a small-scale case study. Herein, we show that our method scales well to a more challenging demand response case study built on a large-scale model of a single-product (nitrogen) air separation unit. Across all numerical experiments, we assume observability of only a few realistically measurable plant variables. Compared to a purely system identification-based Koopman eNMPC, which generates small economic savings but frequently violates constraints, our method delivers similar economic performance while avoiding constraint violations. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_04522 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | End-to-End Reinforcement Learning of Koopman Models for eNMPC of an Air Separation Unit Mayfrank, Daniel Dernek, Kayra Lang, Laura Mitsos, Alexander Dahmen, Manuel Machine Learning Optimization and Control With our recently proposed method based on reinforcement learning (Mayfrank et al. (2024), Comput. Chem. Eng. 190), Koopman surrogate models can be trained for optimal performance in specific (economic) nonlinear model predictive control ((e)NMPC) applications. So far, our method has exclusively been demonstrated on a small-scale case study. Herein, we show that our method scales well to a more challenging demand response case study built on a large-scale model of a single-product (nitrogen) air separation unit. Across all numerical experiments, we assume observability of only a few realistically measurable plant variables. Compared to a purely system identification-based Koopman eNMPC, which generates small economic savings but frequently violates constraints, our method delivers similar economic performance while avoiding constraint violations. |
| title | End-to-End Reinforcement Learning of Koopman Models for eNMPC of an Air Separation Unit |
| topic | Machine Learning Optimization and Control |
| url | https://arxiv.org/abs/2511.04522 |