A Grid-Structured Model of Tubular Reactors

TL;DR

This paper introduces a grid-structured computational model for tubular reactors that combines PDE-based physics with machine learning components, enabling state reconstruction from limited data.

Contribution

It presents a novel hybrid model architecture inspired by PDE solvers, capable of learning reactor dynamics and reconstructing unmeasured states with limited data.

Findings

Model accurately predicts reactor states

Reconstructs unmeasured catalyst activity

Effective with limited training data

Abstract

We propose a grid-like computational model of tubular reactors. The architecture is inspired by the computations performed by solvers of partial differential equations which describe the dynamics of the chemical process inside a tubular reactor. The proposed model may be entirely based on the known form of the partial differential equations or it may contain generic machine learning components such as multi-layer perceptrons. We show that the proposed model can be trained using limited amounts of data to describe the state of a fixed-bed catalytic reactor. The trained model can reconstruct unmeasured states such as the catalyst activity using the measurements of inlet concentrations and temperatures along the reactor.