发表机构
SINTEF Industry; KU Leuven; Norwegian University of Science and Technology（辛特夫工业; 荷语鲁汶大学; 挪威科技大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
提出一种双时间尺度强化学习框架，同时调整RTO和ENMPC参数以应对模型失配，实验验证表明其经济利润比标称ENMPC高8.6%，并保持可行性。
AI 中文摘要
我们提出了一种强化学习（RL）框架，用于调整实时优化（RTO）和经济非线性模型预测控制（ENMPC），以解决过程系统中的模型与工厂失配问题。基于修正器自适应概念，该方法对动态模型、阶段成本、约束和RTO修正器进行参数化，并使用Q学习在两个时间尺度上调整这些参数：对ENMPC层进行快速更新，对RTO层进行慢速更新。该框架在模拟三井海底采油网络的实验室装置上进行了实验验证。利用工厂测量数据，所提出的RTO-RLMPC方案比标称ENMPC实现了8.6%更高的经济利润，保持了所部署ENMPC策略的输入可行性，并在扰动和测量噪声下经验上满足路径约束，同时将学习到的模型参数沿对经济目标影响最大的方向推向参考工厂值（这些值由实验数据独立识别）。这项工作提供了RL调优的ENMPC与RTO集成的最早实验演示之一。
英文摘要
We propose a reinforcement learning (RL) framework that tunes both Real-Time Optimization (RTO) and Economic Nonlinear Model Predictive Control (ENMPC) to address plant--model mismatch in process systems. Drawing on modifier-adaptation concepts, the method parameterizes the dynamic model, stage costs, constraints, and RTO modifiers, and uses Q-learning to adjust these parameters at two timescales: a fast update for the ENMPC layer and a slow update for the RTO layer. The framework is experimentally validated on a laboratory rig emulating a three-well subsea oil-production network. Using plant measurement data, the proposed RTO-RLMPC scheme achieves 8.6% higher economic profit than nominal ENMPC, preserves input feasibility of the deployed ENMPC policy and empirically satisfies the path constraints under disturbances and measurement noise, and drives the learned model parameters toward reference plant values, independently identified from experimental data, along the directions that most affect the economic objective. This work provides one of the first experimental demonstrations of RL-tuned ENMPC integrated with RTO.
Comments12 pages, submitted to Journal of Process Control
