The Application of Physics-Informed Machine Learning in Multiphysics Modeling in Chemical Engineering

Abstract

Physics-Informed Machine Learning (PIML) is an emerging computing paradigm that offers a new approach to tackle multiphysics modeling problems prevalent in the field of chemical engineering. These problems often involve complex transport processes, nonlinear reaction kinetics, and multiphysics coupling. This Review provides a detailed account of the main contributions of PIML with a specific emphasis on modeling momentum transfer, heat transfer, mass transfer, and chemical reactions. The progress in method development (e.g., algorithm and architecture), software libraries, and specific applications (e.g., multiphysics coupling and surrogate modeling) are detailed. On this basis, future challenges highlight the importance of developing more practical solutions and strategies for PIML, including turbulence models, domain decomposition, training acceleration, surrogate modeling, hybrid modeling, and geometry module creation.

Integrating Graph Neural Network-Based Surrogate Modeling with Inverse Design for Granular Flows

“…The recent application of machine learning in engineering science, motivated by the need for process modeling, prediction, design, optimization, and control, has led to significant advancement in this field. − In the evolving landscape of process engineering, concepts such as digital twins and surrogate models have become pivotal, offering dynamic virtual replicas of physical systems. These models, widely applied across various sectors, enable quick response and prediction, enhancing efficiency in pharmaceutical manufacturing and energy management. − This study’s exploration of surrogate models in granular flow modeling aligns with this trend, demonstrating the potential of digital models in addressing complex engineering challenges.…”

Adaptive Data-Driven Deep-Learning Surrogate Model for Frontal Polymerization in Dicyclopentadiene

“…Over the past decade, deep learning (DL) has been used in many fields, including fluid mechanics, , solid mechanics, , materials science, composite/additive manufacturing, − and sensitivity analysis and uncertainty quantification . In these applications, training of the DNN is performed by minimizing the distance between the prediction and training data.…”