Physics-informed neural network method for modelling beam-wall interactions

TL;DR

This paper introduces a physics-informed neural network approach to model beam-wall interactions in particle accelerators, providing a mesh-free, surrogate solution that aligns with physical equations and surface impedance concepts.

Contribution

The paper presents a novel physics-informed neural network method for accurately modeling beam-wall interactions, integrating PDEs and surface impedance without mesh dependency.

Findings

Successfully modeled coupling impedance of accelerator chambers

Validated neural network results against analytical formulas

Demonstrated mesh-free approach effectiveness

Abstract

A mesh-free approach for modelling beam-wall interactions in particle accelerators is proposed. The key idea of our method is to use a deep neural network as a surrogate for the solution to a set of partial differential equations involving the particle beam, and the surface impedance concept. The proposed approach is applied to the coupling impedance of an accelerator vacuum chamber with thin conductive coating, and also verified in comparison with the existing analytical formula.