In situ estimation of the acoustic surface impedance using simulation-based inference

2025-09-10

AI Summary

To address the challenge of accurately modeling boundary impedance *in situ* for acoustic simulations in enclosed spaces, this paper proposes a Bayesian inversion framework based on simulation-based inference (SBI). Methodologically, it integrates a fractional-order damped oscillator physical model, finite-element simulations, and a deep neural network surrogate—bypassing conventional Markov chain Monte Carlo sampling to enable efficient, physics-consistent estimation of frequency-dependent surface impedance and rigorous uncertainty quantification in high-dimensional parameter spaces. Posterior predictive checks and coverage diagnostics ensure calibration reliability. Validated on both a cubic room and a numerical automotive cabin model, the framework successfully infers impedance parameters for six independent boundaries simultaneously. Results align closely with impedance-tube measurements (mean absolute error <5%), demonstrating high accuracy, strong generalizability, and practical engineering applicability.

Technology Category

• Search and Optimization: Sampling/Simulation-based Search
• Machine Learning: Bayesian Learning
• Reasoning under Uncertainty: Probabilistic Inference

Application Category

• User Modeling, Personalization and Recommendation: User modeling and simulation for interactive and conversational systems
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Graph Algorithms and Modeling for the Web: Algorithms and analysis for incomplete, noisy, or partially observed Web-related graphs

Abstract

Accurate acoustic simulations of enclosed spaces require precise boundary conditions, typically expressed through surface impedances for wave-based methods. Conventional measurement techniques often rely on simplifying assumptions about the sound field and mounting conditions, limiting their validity for real-world scenarios. To overcome these limitations, this study introduces a Bayesian framework for the in situ estimation of frequency-dependent acoustic surface impedances from sparse interior sound pressure measurements. The approach employs simulation-based inference, which leverages the expressiveness of modern neural network architectures to directly map simulated data to posterior distributions of model parameters, bypassing conventional sampling-based Bayesian approaches and offering advantages for high-dimensional inference problems. Impedance behavior is modeled using a damped oscillator model extended with a fractional calculus term. The framework is verified on a finite element model of a cuboid room and further tested with impedance tube measurements used as reference, achieving robust and accurate estimation of all six individual impedances. Application to a numerical car cabin model further demonstrates reliable uncertainty quantification and high predictive accuracy even for complex-shaped geometries. Posterior predictive checks and coverage diagnostics confirm well-calibrated inference, highlighting the method's potential for generalizable, efficient, and physically consistent characterization of acoustic boundary conditions in real-world interior environments.

Problem

• Estimating acoustic surface impedance in situ
• Overcoming limitations of conventional measurement techniques
• Using Bayesian inference for impedance from sparse measurements

Innovation

• Bayesian framework for in situ impedance estimation
• Simulation-based inference using neural networks
• Fractional calculus damped oscillator impedance model