Neural network based approach for solving problems in plane wave duct acoustics
Preprint
Abstract
Neural networks have emerged as a tool for solving differential equations in many branches of engineering and science. But their progress in frequency domain acoustics is limited by the vanishing gradient problem that occurs at higher frequencies. This paper discusses a formulation that can address this issue. The problem of solving the governing differential equation along with the boundary conditions is posed as an unconstrained optimization problem. The acoustic field is approximated to the output of a neural network which is constructed in such a way that it always satisfies the boundary conditions. The applicability of the formulation is demonstrated on popular problems in plane wave acoustic theory. The predicted solution from the neural network formulation is compared with those obtained from the analytical solution. A good agreement is observed between the two solutions. The method of transfer learning to calculate the particle velocity from the existing acoustic pressure field is demonstrated with and without mean flow effects. The sensitivity of the training process to the choice of the activation function and the number of collocation points is studied.Keywords
All Related Versions
- Version 1, 2024-05-07, ArXiv
- Published version: Journal of Sound and Vibration, 585.
This publication has 36 references indexed in Scilit:
- Transfer learning based physics-informed neural networks for solving inverse problems in engineering structures under different loading scenariosComputer Methods in Applied Mechanics and Engineering, 2022
- Optimally weighted loss functions for solving PDEs with Neural NetworksJournal of Computational and Applied Mathematics, 2022
- Wavefield solutions from machine learned functions constrained by the Helmholtz equationArtificial Intelligence in Geosciences, 2021
- Benchmarking preconditioned boundary integral formulations for acousticsInternational Journal for Numerical Methods in Engineering, 2021
- Artificial neural network method for solving the Navier–Stokes equationsNeural Computing and Applications, 2014
- Propagation of Sound in Porous Media2009
- An adaptive fast multipole boundary element method for three-dimensional acoustic wave problems based on the Burton–Miller formulationComputational Mechanics, 2006
- Finite element solution of the Helmholtz equation with high wave number Part I: The h-version of the FEMComputers & Mathematics with Applications, 1995
- A modified segmentation approach for analyzing plane wave propagation in non-uniform ducts with mean flowJournal of Sound and Vibration, 1995
- Multilayer feedforward networks are universal approximatorsNeural Networks, 1989