Acoustic Field Reconstruction in Tubes via Physics-Informed Neural Networks

TL;DR

This paper demonstrates that Physics-Informed Neural Networks can effectively reconstruct acoustic fields in tubes from limited, noisy data, even when the radiation model is unknown, outperforming traditional optimization methods.

Contribution

The study introduces a PINNs framework and a novel fine-tuning method for acoustic field reconstruction in tubes with unknown radiation parameters, enhancing noise robustness.

Findings

PINNs accurately reconstruct acoustic fields under noisy conditions.

PINN-FTM outperforms traditional optimization in predicting radiation coefficients.

The approach is robust to limited and noisy observational data.

Abstract

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.