arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2511.04522cs.LGmath.OC
收藏

端到端强化学习用于空气分离单元经济非线性模型预测控制的Koopman模型

End-to-End Reinforcement Learning of Koopman Models for eNMPC of an Air Separation Unit

Forschungszentrum Jülich GmbH, Institute of Climate and Energy Systems, Energy Systems Engineering (ICE-1)(贾格尔中心Jülich GmbH,气候与能源系统研究所,能源系统工程(ICE-1));RWTH Aachen University, Process Systems Engineering (AVT.SVT)(亚琛工业大学,过程系统工程(AVT.SVT));JARA-ENERGY, Jülich 52425(JARA-ENERGY,Jülich 52425);RWTH Aachen University(亚琛工业大学)

Daniel Mayfrank, Kayra Dernek, Laura Lang, Alexander Mitsos, Manuel Dahmen

AI总结:

本文提出了一种端到端强化学习方法,用于在空气分离单元中实现经济非线性模型预测控制,通过Koopman模型在保持经济性能的同时避免约束违反。

摘要:

基于我们最近提出的方法(Mayfrank等人,2024,Comput. Chem. Eng. 190),Koopman替代模型可以针对特定(经济)非线性模型预测控制((e)NMPC)应用进行训练,以实现最优性能。迄今为止,我们的方法仅在小型案例研究中得到演示。在此,我们展示了该方法能够扩展到一个更具挑战性的需求响应案例研究,该案例研究基于一个单产品(氮气)空气分离单元的大型模型。在所有数值实验中,我们假设仅可观测到少量实际可测量的工艺变量。与基于纯系统识别的Koopman eNMPC相比,后者虽然产生较小的经济节省,但经常违反约束,我们的方法在经济性能上相似,同时避免了约束违反。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑