HEAT AND MASS EXCHANGE PROCESSES FOR PHYSICAL AND MACHINE SIMULATIONS OF THE DRYING PROCESS

Abstract

Drying is a complex process of simultaneous heat, mass, and momentum transfer with continuous phase transitions. Numerical modeling is one of the most effective tools for mechanistic expression of various physical phenomena of drying processes, which allows for accurate prediction of drying kinetics and understanding of morphological changes during drying. However, mathematical modeling of drying processes is a complex process and requires large computational resources due to the multiphysics and multiscale nature of heat and mass transfer during drying. Process physics-informed machine learning (PIML) modeling has the potential to overcome these shortcomings and can be a promising addition to drying research. It allows for the description of drying processes by integrating basic transport laws and constraints into machine learning models. To develop such a novel PIML-based model for drying applications, it is necessary to have a fundamental understanding of heat, mass, and momentum transfer processes, as well as their mathematical formulation, in addition to knowledge of data-driven modeling. Based on a comprehensive literature review, this paper presents two types of information: fundamental physical aspects of drying processes and data-driven modeling strategies for developing PIML models for drying applications. The current state of physically based and PIML-based models is discussed, as well as their limitations. An example of a PIML modeling framework for drying applications is presented. Finally, the challenges associated with simultaneously considering heat, mass, and momentum transfer in PIML modeling for drying process optimization are highlighted. The information presented in this manuscript will be useful for the further development of this field.