Physics informed neural network model for multi-particle interaction forces--颗粒学报PARTICUOLOGY

Zhou, Y., Wang, H., Wu, B., Wang, L., & Chen, X. (2025). Physics informed neural network model for multi-particle interaction forces. Particuology, 96, 126-138. https://doi.org/10.1016/j.partic.2024.11.002

Physics informed neural network model for multi-particle interaction forces

Yuanye Zhou^{a *}, Hongqiang Wang^b, Borun Wu^c, LiGe Wang^d, Xizhong Chen^e

a Shanghai Academy of AI for Science, Shanghai, 200232, China
b College of Software, Beihang University, Beijing, 100191, China
c School of Mechanical Engineering, Taiyuan University of Science and Technology, Taiyuan, 030024, China
d Shenzhen Research Institute of Shandong University, Shenzhen, 518057, China
e Department of Chemical Engineering, School of Chemistry and Chemical Engineering, Shanghai Jiao Tong University, Shanghai, 200240, China

10.1016/j.partic.2024.11.002

Volume 96, January 2025, Pages 126-138

Received 29 February 2024, Revised 6 October 2024, Accepted 5 November 2024, Available online 22 November 2024, Version of Record 3 December 2024.

E-mail: zhyy2009@163.com

Highlights

• An artificial neural network model combining ResNet with PINN is proposed to simulate multiple particle-particle interaction force.

• Interaction force includes contact force and electrostatic force between particles.

• Newton's third law on internal force is adopted as PINN's physical loss.

• ResNet-PINN model has an accuracy of R² > 0.93 compared with DEM model, but 7–10 times faster than DEM.

Abstract

The discrete element method (DEM) model calculates interaction forces between each pair of particles. However, it becomes computational expensive especially when the number of particles is large. In this study, a novel artificial neural network (ANN) model is proposed to replace the model of interaction forces between multiple particles in DEM including contact force and electrostatic force. The ANN model combines the residual network (ResNet) with the physics informed neural network (PINN). The physical loss term is derived from the Newton's third law about internal forces in multi-particle system. The performance of the ANN model is evaluated based on the DEM simulation data of 100, 200, and 300-particle system in a wall-bounded 2D swirling flow. It is found that the computing time is reduced nearly an order of magnitude (7–10 times) compared with the DEM model. In addition, the accuracy of the ANN model achieves the R² > 0.93 with only ≤ 2% particles are not well predicted.

Graphical abstract

Keywords

Artificial neural network; ResNet; PINN; Multiphase; DEM; Particle interaction force

文章导读