Surrogate modeling of open-celled metal foam sound absorbers with stepwise property gradients

Abstract

In this paper, we develop a Kriging-based surrogate model to predict the sound absorption performance of open-celled metal foams with user-defined stepwise relative density gradients. An experimentally validated transfer matrix model is used to generate training data capturing the absorption profiles of metal foams with various geometrical parameters. We deploy a spatial analysis method to create influence surfaces around each sample data point and depict its effect on the observed output by using Kriging's basis functions. The surrogate model has an in-built machine learning framework that uses a genetic algorithm and a maximum likelihood function to tune the weights that define these influence surfaces. Using this approach, we successfully developed a data-fed, supervised prediction model that estimates absorption coefficient of a virtual metal foam sample. Post-validation predicted values for unknown sample configurations show satisfactory agreement with their actual absorption coefficients. Finally, we implement the developed metamodel as an iOS application as a potential low-cost tool to reduce testing costs and enable rapid design iterations for acoustic design problems.