Physics-informed neural network for acoustic resonance analysis in a one-dimensional acoustic tube

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Yokota, Kazuya, Kurahashi, Takahiko, Abe, Masajiro
Formato: Preprint
Publicado: 2023
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866909244838641664
author Yokota, Kazuya
Kurahashi, Takahiko
Abe, Masajiro
author_facet Yokota, Kazuya
Kurahashi, Takahiko
Abe, Masajiro
contents This study devised a physics-informed neural network (PINN) framework to solve the wave equation for acoustic resonance analysis. The proposed analytical model, ResoNet, minimizes the loss function for periodic solutions and conventional PINN loss functions, thereby effectively using the function approximation capability of neural networks while performing resonance analysis. Additionally, it can be easily applied to inverse problems. The resonance in a one-dimensional acoustic tube, and the effectiveness of the proposed method was validated through the forward and inverse analyses of the wave equation with energy-loss terms. In the forward analysis, the applicability of PINN to the resonance problem was evaluated via comparison with the finite-difference method. The inverse analysis, which included identifying the energy loss term in the wave equation and design optimization of the acoustic tube, was performed with good accuracy.
format Preprint
id arxiv_https___arxiv_org_abs_2310_11804
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Physics-informed neural network for acoustic resonance analysis in a one-dimensional acoustic tube
Yokota, Kazuya
Kurahashi, Takahiko
Abe, Masajiro
Sound
Audio and Speech Processing
This study devised a physics-informed neural network (PINN) framework to solve the wave equation for acoustic resonance analysis. The proposed analytical model, ResoNet, minimizes the loss function for periodic solutions and conventional PINN loss functions, thereby effectively using the function approximation capability of neural networks while performing resonance analysis. Additionally, it can be easily applied to inverse problems. The resonance in a one-dimensional acoustic tube, and the effectiveness of the proposed method was validated through the forward and inverse analyses of the wave equation with energy-loss terms. In the forward analysis, the applicability of PINN to the resonance problem was evaluated via comparison with the finite-difference method. The inverse analysis, which included identifying the energy loss term in the wave equation and design optimization of the acoustic tube, was performed with good accuracy.
title Physics-informed neural network for acoustic resonance analysis in a one-dimensional acoustic tube
topic Sound
Audio and Speech Processing
url https://arxiv.org/abs/2310.11804