Learning reduced-order Quadratic-Linear models in Process Engineering using Operator Inference

TL;DR

This paper presents a data-driven approach using operator inference to efficiently learn reduced-order models for dynamical systems in process engineering, demonstrated on CO2 methanation to enable fast digital twins.

Contribution

It introduces a non-intrusive operator inference method for reduced-order modeling in process engineering, applied to a relevant chemical reaction.

Findings

Reduced-order models accurately replicate system dynamics

Operator inference enables fast surrogate modeling

Potential for real-time digital twin applications

Abstract

In this work, we address the challenge of efficiently modeling dynamical systems in process engineering. We use reduced-order model learning, specifically operator inference. This is a non-intrusive, data-driven method for learning dynamical systems from time-domain data. The application in our study is carbon dioxide methanation, an important reaction within the Power-to-X framework, to demonstrate its potential. The numerical results show the ability of the reduced-order models constructed with operator inference to provide a reduced yet accurate surrogate solution. This represents an important milestone towards the implementation of fast and reliable digital twin architectures.