Preprint
Aug 2026
Physics-informed neural network for inverse modeling of granular flows
A physics-informed neural network framework driven by both physical mechanisms and measurement data is developed to reconstruct the steady-state full-field distribution of granular flows in a pipe, establishing a robust methodological framework for flow-field reconstruction in complex granular flow systems.
Bing Wan, Bidan Zhao, Junwu Wang
· 0 citations