Simultaneous Process Design and Control Optimization using Reinforcement Learning

被引:5
作者
Sachio, Steven [1 ]
Chanona, Antonio E. del-Rio [1 ]
Petsagkourakis, Panagiotis [1 ]
机构
[1] Imperial Coll London, Dept Chem Engn, London SW7 2AZ, England
基金
英国工程与自然科学研究理事会;
关键词
process design; process control; reinforcement learning; policy gradient; optimization; DYNAMIC OPTIMIZATION;
D O I
10.1016/j.ifacol.2021.08.293
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
The performance of a chemical plant is highly affected by its design and control. A design cannot be accurately evaluated without its controls and vice versa. To optimally address design and control simultaneously, one must formulate a bi-level mixed-integer nonlinear program with a dynamic optimization problem as the inner problem; this is intractable. However, by computing an optimal policy using reinforcement learning, a controller with a closed-form expression can be computed and embedded into the mathematical program. In this work, an approach that uses a policy gradient method to compute the optimal policy, which is then embedded into the mathematical program is proposed. The approach is tested in a tank design case study and the performance of the controller is evaluated. It is shown that the proposed approach outperforms current state-of-the-art control strategies. This opens a whole new range of possibilities to address the simultaneous design and control of engineering systems. Copyright (C) 2021 The Authors.
引用
收藏
页码:510 / 515
页数:6
相关论文
共 23 条
[1]  
Agarap Abien Fred, 2018, Deep learning using rectified linear units (relu), P7
[2]   A model-based methodology for simultaneous design and control of a bioethanol production process [J].
Alvarado-Morales, Merlin ;
Abd Hamid, Mohd Kamaruddin ;
Sin, Gurkan ;
Gernaey, Krist V. ;
Woodley, John M. ;
Gani, Rafiqul .
COMPUTERS & CHEMICAL ENGINEERING, 2010, 34 (12) :2043-2061
[3]  
[Anonymous], ARXIV170706347
[4]   Feed-forward neural networks [J].
Bebis, George ;
Georgiopoulos, Michael .
IEEE Potentials, 1994, 13 (04) :27-31
[5]   The explicit linear quadratic regulator for constrained systems [J].
Bemporad, A ;
Morari, M ;
Dua, V ;
Pistikopoulos, EN .
AUTOMATICA, 2002, 38 (01) :3-20
[6]   DOMINO: Data-driven Optimization of bi-level Mixed-Integer NOnlinear Problems [J].
Beykal, Burcu ;
Avraamidou, Styliani ;
Pistikopoulos, Ioannis P. E. ;
Onel, Melis ;
Pistikopoulos, Efstratios N. .
JOURNAL OF GLOBAL OPTIMIZATION, 2020, 78 (01) :1-36
[7]   COORDINATED DESIGN AND CONTROL OPTIMIZATION OF NONLINEAR PROCESSES [J].
BRENGEL, DD ;
SEIDER, WD .
COMPUTERS & CHEMICAL ENGINEERING, 1992, 16 (09) :861-886
[8]   Towards the Grand Unification of Process Design, Scheduling, and Control-Utopia or Reality? [J].
Burnak, Baris ;
Diangelakis, Nikolaos A. ;
Pistikopoulos, Efstratios N. .
PROCESSES, 2019, 7 (07)
[9]   Integrated Scheduling and Dynamic Optimization by Stackelberg Game: Bilevel Model Formulation and Efficient Solution Algorithm [J].
Chu, Yunfei ;
You, Fengqi .
INDUSTRIAL & ENGINEERING CHEMISTRY RESEARCH, 2014, 53 (13) :5564-5581
[10]   Process Design and Control Optimization: A Simultaneous Approach by Multi-Parametric Programming [J].
Diangelakis, Nikolaos A. ;
Burnak, Baris ;
Katz, Justin ;
Pistikopoulos, Efstratios N. .
AICHE JOURNAL, 2017, 63 (11) :4827-4846