Process flowsheet optimization with surrogate and implicit formulations of a Gibbs reactor

TL;DR

This paper introduces surrogate and implicit function formulations for optimizing chemical process flowsheets, improving convergence reliability and solve time, especially for complex units like Gibbs reactors, with a trade-off between accuracy and computational efficiency.

Contribution

It presents novel surrogate and implicit formulations that enhance convergence reliability and solve time in flowsheet optimization, outperforming traditional full-space methods.

Findings

Implicit formulation provides exact solutions with similar solve time.

Surrogate models significantly improve convergence reliability.

Implicit and surrogate methods outperform full-space in solve success rate.

Abstract

Alternative formulations for the optimization of chemical process flowsheets are presented that leverage surrogate models and implicit functions to replace and remove, respectively, the algebraic equations that describe a difficult-to-converge Gibbs reactor unit operation. Convergence reliability, solve time, and solution quality of an optimization problem are compared among full-space, ALAMO surrogate, neural network surrogate, and implicit function formulations. Both surrogate and implicit formulations lead to better convergence reliability, with low sensitivity to process parameters. The surrogate formulations are faster at the cost of minor solution error, while the implicit formulation provides exact solutions with similar solve time. In a parameter sweep on an autothermal reformer flowsheet optimization problem, the full space formulation solves 33 out of 64 instances, while the implicit function formulation solves 52 out of 64 instances, the ALAMO polynomial formulation solves 64 out of 64 instances, and the neural network formulation solves 48 out of 64 instances. This work demonstrates the trade-off between accuracy and solve time that exists in current methods for improving convergence reliability of chemical process flowsheet optimization problems.