Combining reinforcement learning with mathematical programming: An approach for optimal design of heat exchanger networks

Hui Tan; Xiaodong Hong; Zuwei Liao; Jingyuan Sun; Yao Yang; Jingdai Wang; Yongrong Yang

doi:10.1016/j.cjche.2023.12.005

Your Location：

Home >

Browse articles >

Combining reinforcement learning with mathematical programming: An approach for optimal design of heat exchanger networks

Updated：2026-01-06

- Combining reinforcement learning with mathematical programming: An approach for optimal design of heat exchanger networks
- Combining reinforcement learning with mathematical programming: An approach for optimal design of heat exchanger networks
- 中国化学工程学报（英文版） 2024年69卷第5期页码：63-71
- Affiliations：
  
  1. State Key Laboratory of Chemical Engineering, College of Chemical and Biological Engineering, Zhejiang University,Hangzhou,China,310027
  2. ZJU-Hangzhou Global Scientific and Technological Innovation Center,Hangzhou,China,311215
- Author bio：
- Funds：
- DOI：10.1016/j.cjche.2023.12.005
  中图分类号：
- 纸质出版：2024
- Accepted：
Scan QR Code
Hui Tan, Xiaodong Hong, Zuwei Liao, 等. Combining reinforcement learning with mathematical programming: An approach for optimal design of heat exchanger networks[J]. 中国化学工程学报（英文版）, 2024,69(5):63-71.

Hui Tan, Xiaodong Hong, Zuwei Liao, Jingyuan Sun, Yao Yang, Jingdai Wang, Yongrong Yang. Combining reinforcement learning with mathematical programming: An approach for optimal design of heat exchanger networks[J]. Chinese Journal of Chemical Engineering, 2024, 69(5): 63-71.
Hui Tan, Xiaodong Hong, Zuwei Liao, 等. Combining reinforcement learning with mathematical programming: An approach for optimal design of heat exchanger networks[J]. 中国化学工程学报（英文版）, 2024,69(5):63-71. DOI： 10.1016/j.cjche.2023.12.005.

Hui Tan, Xiaodong Hong, Zuwei Liao, Jingyuan Sun, Yao Yang, Jingdai Wang, Yongrong Yang. Combining reinforcement learning with mathematical programming: An approach for optimal design of heat exchanger networks[J]. Chinese Journal of Chemical Engineering, 2024, 69(5): 63-71. DOI： 10.1016/j.cjche.2023.12.005.

摘要

Abstract

Heat integration is important for energy-saving in the process industry. It is linked to the persistently challenging task of optimal design of heat exchanger networks (HEN). Due to the inherent highly nonconvex nonlinear and combinatorial nature of the HEN problem

it is not easy to find solutions of high quality for large-scale problems. The reinforcement learning (RL) method

which learns strategies through ongoing exploration and exploitation

reveals advantages in such area. However

due to the complexity of the HEN design problem

the RL method for HEN should be dedicated and designed. A hybrid strategy combining RL with mathematical programming is proposed to take better advantage of both methods. An insightful state representation of the HEN structure as well as a customized reward function is introduced. A

-learning algorithm is applied to update the HEN structure using the

-greedy strategy. Better results are obtained from three literature cases of different scales.

关键词

Keywords

references

浏览量

185

Downloads

CSCD

文章被引用时，请邮件提醒。

Submit

工具集

关联资源

Advances in conceptual process design: From conventional strategies to AI-assisted methods

Scheduling and heat integration of multi-product plant based on genetic algorithm

Process design and intensification of multicomponent azeotropes special distillation separation via molecular simulation and system optimization

Fuzzy optimization design of multicomponent refinery hydrogen network

Vapor recompressed dividing-wall distillation columns: Structure and performance