期刊
COMPUTERS & CHEMICAL ENGINEERING
卷 179, 期 -, 页码 -出版社
PERGAMON-ELSEVIER SCIENCE LTD
DOI: 10.1016/j.compchemeng.2023.108411
关键词
Optimization formulations; Surrogate modeling; Data-driven optimization; Optimization under uncertainty; Software tools
This paper investigates the application of data-driven surrogate models in process optimization, discussing the requirements for robustness and accurate extrapolation and comparing the perspectives of surrogate-led and mathematical programming-led approaches. It also explores the verification problem and validates the effectiveness of surrogate-based optimization through two case studies.
Recent developments in data science and machine learning have inspired a new wave of research into data-driven modeling for mathematical optimization of process applications. This paper first considers essential conditions for robustness to uncertainties and accurate extrapolation, which are required to integrate surrogates into process optimization. Next we consider two perspectives for developing process engineering surrogates: a surrogate-led and a mathematical programming-led approach. As these data-driven surrogate models must be integrated into a larger process optimization problem, we discuss the verification problem, i.e., checking that the optimum of the surrogate corresponds to the optimum of the truth model. The paper investigates two case studies on surrogate-based optimization for heat exchanger network synthesis and drill scheduling.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据