Acoustic Field Reconstruction in Tubes via Physics-Informed Neural Networks
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916742673989632 |
|---|---|
| author | Luan, Xinmeng Yokota, Kazuya Scavone, Gary |
| author_facet | Luan, Xinmeng Yokota, Kazuya Scavone, Gary |
| contents | This study investigates the application of Physics-Informed Neural Networks (PINNs) to inverse problems in acoustic tube analysis, focusing on reconstructing acoustic fields from noisy and limited observation data. Specifically, we address scenarios where the radiation model is unknown, and pressure data is only available at the tube's radiation end. A PINNs framework is proposed to reconstruct the acoustic field, along with the PINN Fine-Tuning Method (PINN-FTM) and a traditional optimization method (TOM) for predicting radiation model coefficients. The results demonstrate that PINNs can effectively reconstruct the tube's acoustic field under noisy conditions, even with unknown radiation parameters. PINN-FTM outperforms TOM by delivering balanced and reliable predictions and exhibiting robust noise-tolerance capabilities. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_12557 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Acoustic Field Reconstruction in Tubes via Physics-Informed Neural Networks Luan, Xinmeng Yokota, Kazuya Scavone, Gary Audio and Speech Processing Sound Signal Processing Applied Physics This study investigates the application of Physics-Informed Neural Networks (PINNs) to inverse problems in acoustic tube analysis, focusing on reconstructing acoustic fields from noisy and limited observation data. Specifically, we address scenarios where the radiation model is unknown, and pressure data is only available at the tube's radiation end. A PINNs framework is proposed to reconstruct the acoustic field, along with the PINN Fine-Tuning Method (PINN-FTM) and a traditional optimization method (TOM) for predicting radiation model coefficients. The results demonstrate that PINNs can effectively reconstruct the tube's acoustic field under noisy conditions, even with unknown radiation parameters. PINN-FTM outperforms TOM by delivering balanced and reliable predictions and exhibiting robust noise-tolerance capabilities. |
| title | Acoustic Field Reconstruction in Tubes via Physics-Informed Neural Networks |
| topic | Audio and Speech Processing Sound Signal Processing Applied Physics |
| url | https://arxiv.org/abs/2505.12557 |