A Machine-learning Framework for Acoustic Design Assessment in Early Design Stages

TL;DR

This paper introduces a machine learning framework that quickly estimates room acoustic parameters during early building design stages using geometric data, reducing reliance on complex simulation tools.

Contribution

The study develops a novel ML-based method with a lightweight model trained on a large dataset to predict acoustic parameters efficiently in early design phases.

Findings

ML models achieved 1-3% average error in predictions

Predicted samples had 2-12% average error after validation

The approach reduces time and expertise needed for acoustic assessment

Abstract

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%.