Formulating data-driven surrogate models for process optimization

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.

Automated summary

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.