A data-driven optimization algorithm for differential algebraic equations with numerical infeasibilities

作     者：Beykal, Burcu Onel, Melis Onel, Onur Pistikopoulos, Efstratios N. 

作者机构：Texas A&M Univ Artie McFerrin Dept Chem Engn College Stn TX 77843 USA Texas A&M Univ Texas A&M Energy Inst College Stn TX USA Princeton Univ Dept Chem & Biol Engn Princeton NJ 08544 USA 

出 版 物：《AICHE JOURNAL》 (美国化学工程师协会志)

年 卷 期：2020年第66卷第10期

页      面：e16657-e16657页

核心收录：

学科分类：0817[工学-化学工程与技术] 08[工学] 

基　　金：U.S. National Institutes of Health Superfund Research Program [NIH P42-ES027704] National Institute of Environmental Health Sciences [P42ES027704] Funding Source: NIH RePORTER 

主　　题：data-driven optimization differential algebraic equations dynamic optimization steam cracking support vector machines 

摘      要：Support vector machines (SVMs) based optimization framework is presented for the data-driven optimization of numerically infeasible differential algebraic equations (DAEs) without the full discretization of the underlying first-principles model. By formulating the stability constraint of the numerical integration of a DAE system as a supervised classification problem, we are able to demonstrate that SVMs can accurately map the boundary of numerical infeasibility. The necessity of this data-driven approach is demonstrated on a two-dimensional motivating example, where highly accurate SVM models are trained, validated, and tested using the data collected from the numerical integration of DAEs. Furthermore, this methodology is extended and tested for a multidimensional case study from reaction engineering (i.e., thermal cracking of natural gas liquids). The data-driven optimization of this complex case study is explored through integrating the SVM models with a constrained global grey-box optimization algorithm, namely the ARGONAUT framework.