What question did this study set out to answer?

The central aim is to create an accurate surrogate model for 2D steady-state acoustic scattering problems.

March 26, 2026Open Access

Construction of the surrogate model for 2D steady-state acoustic scattering problems using boundary integral equation

Key Points

The central aim is to create an accurate surrogate model for 2D steady-state acoustic scattering problems.
Developed a Physics-Informed Neural Network for acoustic problems.
Integrated Boundary Integral Equation into loss function to enhance model performance.
Applied Isogeometric Boundary Element Method for effective boundary discretization.
Conducted numerical experiments to validate the model's predictions.
The surrogate model accurately predicted sound pressure at unseen source positions.
Integration of BMBIE into the loss function improved prediction accuracy.
Demonstrated mitigation of fictitious eigenvalue problems in acoustic modeling.

Abstract

This study introduces a novel Physics-Informed Neural Network (PINN) for 2D acoustic scattering problems, parametrically representing sound source position and wavenumber. A key innovation involves integrating the Burton—Miller-type Boundary Integral Equation (BMBIE) directly into the loss function, mitigating the “fictitious eigenvalue problem” and improving existing BIE-based PINN methods. The model utilizes the Isogeometric Boundary Element Method (IGBEM) for boundary discretization. Numerical experiments showed that the developed surrogate model made an accurate prediction of sound pressure for an unseen source position.

Construction of the surrogate model for 2D steady-state acoustic scattering problems using boundary integral equation

Key Points

Abstract

Cite This Study