On Machine Learning-Driven Surrogates for Sound Transmission Loss Simulations

TL;DR

This paper explores four machine learning approaches to create surrogate models for Sound Transmission Loss, addressing challenges in vibroacoustic simulations by enhancing accuracy, interpretability, and physical consistency.

Contribution

It introduces novel ML-based surrogate modeling techniques for STL that incorporate feature engineering to improve model performance and interpretability.

Findings

Improved surrogate accuracy through feature importance analysis

Enhanced model interpretability and physical consistency

Discussion on transferability and limitations of ML surrogates

Abstract

Surrogate models are data-based approximations of computationally expensive simulations that enable efficient exploration of the model's design space and informed decision-making in many physical domains. The usage of surrogate models in the vibroacoustic domain, however, is challenging due to the non-smooth, complex behavior of wave phenomena. This paper investigates four Machine Learning (ML) approaches in the modelling of surrogates of Sound Transmission Loss (STL). Feature importance and feature engineering are used to improve the models' accuracy while increasing their interpretability and physical consistency. The transfer of the proposed techniques to other problems in the vibroacoustic domain and possible limitations of the models are discussed.