A Machine-learning Framework for Acoustic Design Assessment in Early Design Stages
This addresses the high cost, expertise requirement, and time-consuming nature of acoustic simulations for architects and designers, though it is incremental as it applies existing ML methods to a new dataset.
The paper tackles the problem of predicting acoustic performance in building design by introducing a machine learning framework that uses geometric data to estimate room acoustic parameters, achieving average errors between 1% to 3% for trained models and 2% to 12% for new predictions.
In time-cost scale model studies, predicting acoustic performance by using simulation methods is a commonly used method that is preferred. In this field, building acoustic simulation tools are complicated by several challenges, including the high cost of acoustic tools, the need for acoustic expertise, and the time-consuming process of acoustic simulation. The goal of this project is to introduce a simple model with a short calculation time to estimate the room acoustic condition in the early design stages of the building. This paper presents a working prototype for a new method of machine learning (ML) to approximate a series of typical room acoustic parameters using only geometric data as input characteristics. A novel dataset consisting of acoustical simulations of a single room with 2916 different configurations are used to train and test the proposed model. In the stimulation process, features that include room dimensions, window size, material absorption coefficient, furniture, and shading type have been analysed by using Pachyderm acoustic software. The mentioned dataset is used as the input of seven machine-learning models based on fully connected Deep Neural Networks (DNN). The average error of ML models is between 1% to 3%, and the average error of the new predicted samples after the validation process is between 2% to 12%.