Performance evaluation of 3D printed acoustic metamaterial using soft computing approach

This paper introduces a novel methodology for predicting the acoustic absorption coefficient of DENORMS cell based acoustic metamaterial. The samples were printed from resin using Digital Light Processing based 3D printing technique. The manufactured samples were tested in an Impedance tube using the two Microphone method. A virtual simulation test rig was used to generate data sets for geometrically distinct DENORMS cell based metamaterial. Four distinct soft computing techniques specifically the "Neural Networks (NN), Random Forests (RF), Decision Trees (Rpart) and Generalized Linear Model (GLM)", were employed and compared to develop an accurate prediction model for forecasting the absorption coefficient of the developed metamaterial. The machine learning techniques were used due to their higher speed and lower computational power requirement compared to numerical simulations to determine the absorption coefficient. The input variables consist of the Spherical Diameter, Cylindrical Diameter, Cylinder Length of the DENORMS cell and Frequency of Incident noise. The performance of the four prediction models was evaluated based on criteria such as Root mean square error, Coefficient of determination, Correlation and Accuracy. Ten-Fold cross validation is performed to test the robustness of the model.