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

Fujita, Kazuhiro

doi:10.1049/ell2.12469

Cited by 5 publications

(15 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…41 Unlike Ref. [28], in this paper, boundary data for PINN are generated with the nonperturbative model based on Eqs. 30, 31 including Eq.…”

Section: Kirchhoff's Boundary Integral Representation Of Electromagne...mentioning

confidence: 99%

“…17 was given in Ref. [28], its derivation was omitted. In the following, we present a detailed formulation for the data and equation scaling.…”

Section: Data and Equation Scalingmentioning

confidence: 99%

“…Nonperturbative cases are also not yet discussed in this context. The purpose of this paper is therefore to extend the previous study [28] to the nonperturbative modeling of coupling impedances and wakefields in multilayer vacuum chambers. This study will be the first application of PINN to this subject.…”

Section: Introductionmentioning

confidence: 99%

“…Very recently, PINN was extended to the case when a vacuum chamber has finite wall conductivity in Ref. [28], where the surface impedance concept was combined with PINN. A single-layer circular vacuum chamber with a finite wall thickness and a small conductivity was analyzed in [28], where it is assumed that the magnetic field on the resistive wall is the same as that on the perfectly electric conductor (PEC) wall; the effect of finite wall conductivity on the magnetic field is enough small.…”

Section: Introductionmentioning

confidence: 99%

“…To the best of the author's knowledge, the modeling of multilayer vacuum chambers with more than two layers in particle accelerators has never been studied in the framework of PINN, although its possibility has been mentioned in Ref. [28]. Nonperturbative cases are also not yet discussed in this context.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Electromagnetic field computation of multilayer vacuum chambers with physics-informed neural networks

Fujita

2022

Front. Phys.

Self Cite

View full text Add to dashboard Cite

The electromagnetic interaction of a charged particle beam with multilayer vacuum chambers is of particular interest in accelerator physics. This paper presents a deep learning-based approach for calculating electromagnetic fields generated by the beam in infinitely long multilayer vacuum chambers with arbitrary cross section. The presented approach is based on physics-informed neural networks and the surface impedance boundary condition of a multilayer structure derived from the transmission line theory. Deep neural networks (DNNs) are utilized to approximate the solution of partial differential equations (PDEs) describing the physics of electromagnetic fields self-generated by a charged particle beam traveling in a particle accelerator. A residual network is constructed from the output of DNNs, the PDEs and boundary conditions are embedded into the loss function and differential operators are calculated using the automatic differentiation. As a result, the presented approach is regarded to be mesh-free. The approach is applied to circular and elliptical vacuum chambers with a three-layer structure. It is verified in comparison with the recently proposed boundary element method. The effects of chamber geometries and multilayer structure on the beam coupling impedance are demonstrated.

show abstract

“…41 Unlike Ref. [28], in this paper, boundary data for PINN are generated with the nonperturbative model based on Eqs. 30, 31 including Eq.…”

Section: Kirchhoff's Boundary Integral Representation Of Electromagne...mentioning

confidence: 99%

“…17 was given in Ref. [28], its derivation was omitted. In the following, we present a detailed formulation for the data and equation scaling.…”

Section: Data and Equation Scalingmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Electromagnetic field computation of multilayer vacuum chambers with physics-informed neural networks

Fujita

2022

Front. Phys.

Self Cite

View full text Add to dashboard Cite

show abstract

Comparison of physics-informed neural networks in solving electromagnetic interior scattering problems including a relativistic beam current

Fujita

2024

JASSE

Self Cite

View full text Add to dashboard Cite

The strength of electromagnetic interaction between a relativistic beam and its surrounding environment in a particle accelerator can be characterized by the coupling impedance. Recently, the physics-informed neural networks (PINN) have been introduced into the impedance modeling in accelerator physics. Total-field (TF) and scattered-field (SF) formulations are available in calculating the coupling impedance with PINN. In this paper, direct comparison of the two PINNs based on the TF and SF formulations is presented with application to an elliptical vacuum chamber with practical geometry parameters. The numbers of iterations for the training processes and the accuracy of indirect space charge impedance are assessed for the two different PINNs in this comparison.

show abstract

Impedance modeling of accelerator beams with discontinuous charge density using scattered-field physics-informed neural networks

Fujita

2023

IEICE Electron. Express

Self Cite

View full text Add to dashboard Cite

A physics-informed neural network method for solving electrodynamic interaction problems including a relativistic beam of charged particles in particle accelerators has been recently proposed. However, the method still has a limitation on modeling accelerator beams with discontinuous charge density. To remove this limitation, the scattered field formulation is introduced into this method. This approach allows us to model the field of discontinuous beam charge density such as point and ring charges. Its numerical error is shown to be smaller than that of the boundary element method. The presented approach is applied to three different vacuum chambers.

show abstract

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

Cited by 5 publications

References 14 publications

Electromagnetic field computation of multilayer vacuum chambers with physics-informed neural networks

Electromagnetic field computation of multilayer vacuum chambers with physics-informed neural networks

Comparison of physics-informed neural networks in solving electromagnetic interior scattering problems including a relativistic beam current

Impedance modeling of accelerator beams with discontinuous charge density using scattered-field physics-informed neural networks

Contact Info

Product

Resources

About