AI-based tool “SoundLab AI” can predict sound insulation values

In a recently presented joint case study, Michael Drass, Michael Anton Kraus, Henrik Riedel (all M&M Network-Eng) and Ingo Stelzer, Kuraray Europe GmbH, developed an AI-based software tool to derive insulation values acoustics of arbitrary glass assemblies. The idea was to predict the weighted sound insulation value for glazing systems, since this value can only be determined by very complex numerical simulations or expensive experiments in classical approaches.

The presented ML tool was trained on structured data in a supervised learning procedure. The data was obtained through an extensive experimental program. The accuracy of the prediction error graph shows a very high predictive ability, which could be proved by an R2=0.996 for the training data and R2=0.982 for the validation data. Additionally, the ML model was also checked for previously untapped test data.

The authors concluded that the developed tool is a suitable method for making predictions on the sound insulation of arbitrary glass structures quickly, cost-effectively and efficiently, which is of great benefit to architects and design engineers, especially in the early stages of the project.

The detailed case study and the corresponding tool, the app, are offered on the Kuraray Europe Gmbh website and can be downloaded here: https://www.trosifol.com/soundlab-ai/?no_cache=1

Comments are closed.