Physics-informed neural networks need a physicist to be accurate: the case of mass and heat transport in Fischer-Tropsch catalyst particles

TL;DR

This paper demonstrates that Physics-Informed Neural Networks (PINNs) require domain expertise and modifications to reliably simulate mass and heat transport in Fischer-Tropsch catalyst particles, ensuring stability and accuracy in complex chemical processes.

Contribution

The study introduces domain knowledge-based modifications to PINNs and an improved numerical scheme to enhance stability and accuracy in simulating coupled reaction-diffusion and heat transfer equations.

Findings

Modified PINN architecture improves stability at parameter extremes

Hybrid numerical scheme enhances simulation reliability

Proposed method preserves PINN speed-up benefits

Abstract

Physics-Informed Neural Networks (PINNs) have emerged as an influential technology, merging the swift and automated capabilities of machine learning with the precision and dependability of simulations grounded in theoretical physics. PINNs are often employed to solve algebraic or differential equations to replace some or even all steps of multi-stage computational workflows, leading to their significant speed-up. However, wide adoption of PINNs is still hindered by reliability issues, particularly at extreme ends of the input parameter ranges. In this study, we demonstrate this in the context of a system of coupled non-linear differential reaction-diffusion and heat transfer equations related to Fischer-Tropsch synthesis, which are solved by a finite-difference method with a PINN used in evaluating their source terms. It is shown that the testing strategies traditionally used to assess the accuracy of neural networks as function approximators can overlook the peculiarities which ultimately cause instabilities of the finite-difference solver. We propose a domain knowledge-based modifications to the PINN architecture ensuring its correct asymptotic behavior. When combined with an improved numerical scheme employed as an initial guess generator, the proposed modifications are shown to recover the overall stability of the simulations, while preserving the speed-up brought by PINN as the workflow component. We discuss the possible applications of the proposed hybrid transport equation solver in context of chemical reactors simulations.