Surface impedance inference via neural fields and sparse acoustic data obtained by a compact array
This provides a robust method for in-situ boundary condition characterization in architectural and automotive acoustics, addressing deviations from idealized lab conditions, but it is incremental as it builds on neural fields and sparse data techniques.
The paper tackles the problem of in-situ acoustic characterization of absorbing materials by proposing a physics-informed neural field that reconstructs near-surface sound fields from sparse pressure samples to directly infer complex surface impedance, achieving accurate retrieval with a small number of sensors under realistic conditions, as validated in numerical and laboratory experiments including a vehicle cabin application.
Standardized laboratory characterizations for absorbing materials rely on idealized sound field assumptions, which deviate largely from real-life conditions. Consequently, \emph{in-situ} acoustic characterization has become essential for accurate diagnosis and virtual prototyping. We propose a physics-informed neural field that reconstructs local, near-surface broadband sound fields from sparse pressure samples to directly infer complex surface impedance. A parallel, multi-frequency architecture enables a broadband impedance retrieval within runtimes on the order of seconds to minutes. To validate the method, we developed a compact microphone array with low hardware complexity. Numerical verifications and laboratory experiments demonstrate accurate impedance retrieval with a small number of sensors under realistic conditions. We further showcase the approach in a vehicle cabin to provide practical guidance on measurement locations that avoid strong interference. Here, we show that this approach offers a robust means of characterizing \emph{in-situ} boundary conditions for architectural and automotive acoustics.