Nearfield acoustic holography in a moving medium based on particle velocity input using nonsingular propagator

Nearfield acoustic holography in a moving medium is a technique which is typically suitable for sound sources identification in a flow. In the process of sound field reconstruction, sound pressure is usually used as the input, but it may contain considerable background noise due to the interactions between microphones and flow moving at a high velocity. To avoid this problem, particle velocity is an alternative input, which can be obtained by using Laser Doppler Velocimetry in a non-intrusive way. However, there is a singular problem in the conventional propagator relating the particle velocity to the pressure, and it could lead to significant errors or even false results. In view of this, in this paper nonsingular propagators are deduced to realize accurate reconstruction in both cases that the hologram is parallel to and perpendicular to the flow direction. The advantages of the proposed method are analyzed, and simulations are conducted to verify the validation. The results show that the method can overcome the singular problem effectively, and the reconstruction errors are at a low level for different flow velocities, frequencies, and signal-to-noise ratios.

A Physics-Informed Neural Network Approach for Nearfield Acoustic Holography

In this manuscript, we describe a novel methodology for nearfield acoustic holography (NAH). The proposed technique is based on convolutional neural networks, with autoencoder architecture, to reconstruct the pressure and velocity fields on the surface of the vibrating structure using the sampled pressure soundfield on the holographic plane as input. The loss function used for training the network is based on a combination of two components. The first component is the error in the reconstructed velocity. The second component is the error between the sound pressure on the holographic plane and its estimate obtained from forward propagating the pressure and velocity fields on the structure through the Kirchhoff–Helmholtz integral; thus, bringing some knowledge about the physics of the process under study into the estimation algorithm. Due to the explicit presence of the Kirchhoff–Helmholtz integral in the loss function, we name the proposed technique the Kirchhoff–Helmholtz-based convolutional neural network, KHCNN. KHCNN has been tested on two large datasets of rectangular plates and violin shells. Results show that it attains very good accuracy, with a gain in the NMSE of the estimated velocity field that can top 10 dB, with respect to state-of-the-art techniques. The same trend is observed if the normalized cross correlation is used as a metric.