A Feature-Enhanced Physics Informed Neural Network for Trajectory Simulation of Charged Particles

28 Pages Posted: 23 May 2025

See all articles by Fan Yang

Fan Yang

affiliation not provided to SSRN

Xuan Liu

affiliation not provided to SSRN

Pengbo Wang

Chongqing University

Xinheng Li

affiliation not provided to SSRN

Abstract

Physics-Informed Neural Networks (PINN) have shown great potential in Computational Electromagnetics. This paper proposes a Feature-Enhanced PINN (FE-PINN) framework for the simulation of charged particle dynamics, improving computational efficiency by elimination of mesh discretization and node mapping. For electromagnetic fields with evolving internal sources and complex geometries, Feature-Enhanced PINN eliminates the need for network retraining under varying space charge distributions, and applies targeted enhancement in collocation strategies and network structure to improve convergence and accuracy in intricate field domains. Built upon FE-PINN electromagnetic field solutions, particle trajectory simulation is achieved by iteratively solving the Poisson’s equation and particle motion equation under a fixed magnetic field. The proposed method is validated using the magnetron injection gun of an 800 GHz gyrotron with results compared with finite difference method . Numerical results indicate that the proposed simulation method achieves higher computational efficiency while maintaining the same level of accuracy.

Keywords: Physics-Informed Neural Networks, charged particle dynamics, Electromagnetic Field Computation, Space Charge Effect

Suggested Citation

Yang, Fan and Liu, Xuan and Wang, Pengbo and Li, Xinheng, A Feature-Enhanced Physics Informed Neural Network for Trajectory Simulation of Charged Particles. Available at SSRN: https://ssrn.com/abstract=5265458 or http://dx.doi.org/10.2139/ssrn.5265458

Fan Yang

affiliation not provided to SSRN ( email )

Xuan Liu

affiliation not provided to SSRN ( email )

Pengbo Wang (Contact Author)

Chongqing University ( email )

Shazheng Str 174, Shapingba District
Shazheng street, Shapingba district
Chongqing 400044, 400030
China

Xinheng Li

affiliation not provided to SSRN ( email )

Do you have a job opening that you would like to promote on SSRN?

Paper statistics

Downloads
13
Abstract Views
40
PlumX Metrics