Physics-informed deep learning method for the refrigerant filling mass flow metering

Weimin, Xuan; Lou, Huan; Fu, Shenghua; Zhang, Zhengqian; Ding, Ning

doi:10.1016/j.flowmeasinst.2023.102418

Cited by 2 publications

(1 citation statement)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It was found that compared to benchmark finite element analysis results, the prediction percentage errors of mass loss and moisture distribution remained below 0.23% and 0.33%, respectively, indicating that PINN is an effective computational approach for solving the mass transfer model for a plant cell during drying. 155 Xuan et al 156 introduced an approach that combines physics-informed learning with a residual pointsadding optimization method for refrigerant filling mass flow metering. The results of their study showed the accuracy of the PINN in predicting crucial parameters, such as mass flow rate, pressure, and velocity during refrigerant filling.…”

Section: Mass Transfermentioning

confidence: 99%

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

Wu,

Wang,

et al. 2023

Ind. Eng. Chem. Res.

View full text Add to dashboard Cite

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.

show abstract

Section: Mass Transfermentioning

confidence: 99%