Boundary integrated neural networks and code for acoustic radiation and scattering
Authors:
Open Access
- 4 June 2024
- journal article
- research article
- Published by Wiley in International Journal of Mechanical System Dynamics
- Vol. 4 (2) , 131-141
Abstract
This paper presents a novel approach called the boundary integrated neural networks (BINNs) for analyzing acoustic radiation and scattering. The method introduces fundamental solutions of the time‐harmonic wave equation to encode the boundary integral equations (BIEs) within the neural networks, replacing the conventional use of the governing equation in physics‐informed neural networks (PINNs). This approach offers several advantages. First, the input data for the neural networks in the BINNs only require the coordinates of “boundary” collocation points, making it highly suitable for analyzing acoustic fields in unbounded domains. Second, the loss function of the BINNs is not a composite form and has a fast convergence. Third, the BINNs achieve comparable precision to the PINNs using fewer collocation points and hidden layers/neurons. Finally, the semianalytic characteristic of the BIEs contributes to the higher precision of the BINNs. Numerical examples are presented to demonstrate the performance of the proposed method, and a MATLAB code implementation is provided as supplementary material.Keywords
All Related Versions
Funding Information
- National Natural Science Foundation of China (300102253502)
- Natural Science Foundation of Shandong Province (202203)
This publication has 27 references indexed in Scilit:
- BINN: A deep learning approach for computational mechanics problems based on boundary integral equationsComputer Methods in Applied Mechanics and Engineering, 2023
- Deep Neural Networks Motivated by Partial Differential EquationsJournal of Mathematical Imaging and Vision, 2019
- A family of non-conforming crack front elements of quadrilateral and triangular types for 3D crack problems using the boundary element methodFrontiers of Mechanical Engineering, 2019
- A wideband fast multipole accelerated singular boundary method for three-dimensional acoustic problemsComputers & Structures, 2018
- The Deep Ritz Method: A Deep Learning-Based Numerical Algorithm for Solving Variational ProblemsCommunications in Mathematics and Statistics, 2018
- Calculation of stress intensity factor along the 3D crack front by dual BIE with new crack front elementsActa Mechanica, 2017
- Diagonal form fast multipole singular boundary method applied to the solution of high‐frequency acoustic radiation and scatteringInternational Journal for Numerical Methods in Engineering, 2017
- A wideband FMBEM for 2D acoustic design sensitivity analysis based on direct differentiation methodComputational Mechanics, 2013
- Eighty years of Sommerfeld's radiation conditionHistoria Mathematica, 1992
- Direct computation of Cauchy principal value integrals in advanced boundary elementsInternational Journal for Numerical Methods in Engineering, 1987