Physics-informed neural network method for modelling beam-wall interactions
This work addresses a domain-specific problem in particle accelerator physics, offering an incremental improvement by applying a known method to a new context.
The authors tackled the problem of modeling beam-wall interactions in particle accelerators by proposing a mesh-free physics-informed neural network method, which was applied to the coupling impedance of an accelerator vacuum chamber with thin conductive coating and verified against existing analytical formulas, showing successful application and verification.
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.