PC-Gym: Benchmark Environments For Process Control Problems
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866913598879563776 |
|---|---|
| author | Bloor, Maximilian Torraca, José Sandoval, Ilya Orson Ahmed, Akhil White, Martha Mercangöz, Mehmet Tsay, Calvin Chanona, Ehecatl Antonio Del Rio Mowbray, Max |
| author_facet | Bloor, Maximilian Torraca, José Sandoval, Ilya Orson Ahmed, Akhil White, Martha Mercangöz, Mehmet Tsay, Calvin Chanona, Ehecatl Antonio Del Rio Mowbray, Max |
| contents | PC-Gym is an open-source tool for developing and evaluating reinforcement learning (RL) algorithms in chemical process control. It features environments that simulate various chemical processes, incorporating nonlinear dynamics, disturbances, and constraints. The tool includes customizable constraint handling, disturbance generation, reward function design, and enables comparison of RL algorithms against Nonlinear Model Predictive Control (NMPC) across different scenarios. Case studies demonstrate the framework's effectiveness in evaluating RL approaches for systems like continuously stirred tank reactors, multistage extraction processes, and crystallization reactors. The results reveal performance gaps between RL algorithms and NMPC oracles, highlighting areas for improvement and enabling benchmarking. By providing a standardized platform, PC-Gym aims to accelerate research at the intersection of machine learning, control, and process systems engineering. By connecting theoretical RL advances with practical industrial process control applications, offering researchers a tool for exploring data-driven control solutions. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_22093 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | PC-Gym: Benchmark Environments For Process Control Problems Bloor, Maximilian Torraca, José Sandoval, Ilya Orson Ahmed, Akhil White, Martha Mercangöz, Mehmet Tsay, Calvin Chanona, Ehecatl Antonio Del Rio Mowbray, Max Systems and Control PC-Gym is an open-source tool for developing and evaluating reinforcement learning (RL) algorithms in chemical process control. It features environments that simulate various chemical processes, incorporating nonlinear dynamics, disturbances, and constraints. The tool includes customizable constraint handling, disturbance generation, reward function design, and enables comparison of RL algorithms against Nonlinear Model Predictive Control (NMPC) across different scenarios. Case studies demonstrate the framework's effectiveness in evaluating RL approaches for systems like continuously stirred tank reactors, multistage extraction processes, and crystallization reactors. The results reveal performance gaps between RL algorithms and NMPC oracles, highlighting areas for improvement and enabling benchmarking. By providing a standardized platform, PC-Gym aims to accelerate research at the intersection of machine learning, control, and process systems engineering. By connecting theoretical RL advances with practical industrial process control applications, offering researchers a tool for exploring data-driven control solutions. |
| title | PC-Gym: Benchmark Environments For Process Control Problems |
| topic | Systems and Control |
| url | https://arxiv.org/abs/2410.22093 |