Acoustic Optimization Design of Lecture Hall Based on CNN Algorithm

Acoustic Optimization Design of Lecture Hall Based on CNN Algorithm

Teams
Jia Wenlong, Chen Longde, Mu Haiming, Fan Shengyan,

Jiang Wei, Zhang Jiaojiao, Chen Haoran.

Tutors
Zhong Ximing, Li Kun


Abstract

The overall goal of this project is to enable architects to design indoor sound environments with the best possible diffuse sound fields based on some site conditions, needs and specifications for lecture halls and other venue types (i.e., with certain requirements for sound environments) when conducting design projects.


Research

This research project is a series of outcomes from the AI architecture course launched by Archiford and Xi’an University of Architecture and Technology. The course aims to use deep learning methods to design and advance architectural design solutions.

The problem studied in this project is to enable architects to design indoor acoustic environments with the best possible diffuse sound field according to some site conditions, needs and indicators of lecture halls and other venue types (i.e., with certain requirements for acoustic environments) when conducting design projects for lecture halls.

The design process of the building will be associated with several professions, especially with the intersection of acoustics, optics, thermodynamics, and other disciplines that provide the indoor physical environment. Therefore, in the design phase, there is an urgent need for a “key” that can guide designers to fully consider the indoor acoustic environment.



Methods and Evaluations

In this way, we promote the cross-fertilization of the architectural discipline with the field of building physical acoustics by receiving some indicators and actual conditions from the client and outputting some solutions with good acoustical benefits for the indoor acoustic environment. This is a guide to how architecture can fully consider the physical environment of Al design.

A convenient, fast, and accurate prediction model is established by the machine learning inspection method, which can obtain various acoustical indicators of the air question without the need for 3D modeling or simulation software.

Leave a Comment

Leave a Comment

您的电子邮箱地址不会被公开。 必填项已用*标注