用强化学习训练柯尔莫哥洛夫模型，实现大型空分装置的经济型模型预测控制。
End-to-End Reinforcement Learning of Koopman Models for eNMPC of an Air Separation Unit
- 基于强化学习端到端训练柯尔莫哥洛夫代理模型。
- 在真实可测变量下保持经济性能并避免约束违规。
- 适合需要稳定约束满足的工业过程控制场景。
基于我们近期提出的强化学习方法（Mayfrank 等，2024，Comput. Chem. Eng. 190），柯尔莫哥洛夫代理模型可在特定（经济）非线性模型预测控制((e)NMPC)应用中实现最优性能。此前该方法仅在小规模案例中验证。本文展示其可扩展至更具挑战性的需求响应案例，基于单产品（氮气）空分装置的大规模模型。所有数值实验均假设仅有少数实际可测的工厂变量可观测。相较于纯系统辨识的柯尔莫哥洛夫 eNMPC（带来微小经济收益但频繁违反约束），本方法在相似经济表现下完全避免了约束违规。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。