Skip to main content

Lund University Publications

LUND UNIVERSITY LIBRARIES

A sound insulation prediction model for floor structures in wooden buildings using neural networks approach

Bader Eddin, Mohamad ; Menard, Sylvain ; Bard, Delphine LU ; Kouyoumji, Jean Luc and Vardaxis, Nikolas Georgios LU (2021) 50th International Congress and Exposition of Noise Control Engineering, INTER-NOISE 2021 In Proceedings of INTER-NOISE 2021 - 2021 International Congress and Exposition of Noise Control Engineering
Abstract

Reliable prediction tools are yet to be developed for estimating the accurate acoustic performance of lightweight structures, which are vital especially in the design process. This paper presents a sound insulation prediction model based on artificial Neural Networks (NN) to estimate acoustic performance for airborne and impact sound insulation of floor structures. At an initial stage, the prediction model was developed and tested for a small amount of data, specifically 67 laboratory measurement curves in one third octave bands. The results indicate that the model can predict the weighted airborne reduction index Rw for various floors with a maximum error of 1 dB. The accuracy decreases with errors up to 9 dB for the... (More)

Reliable prediction tools are yet to be developed for estimating the accurate acoustic performance of lightweight structures, which are vital especially in the design process. This paper presents a sound insulation prediction model based on artificial Neural Networks (NN) to estimate acoustic performance for airborne and impact sound insulation of floor structures. At an initial stage, the prediction model was developed and tested for a small amount of data, specifically 67 laboratory measurement curves in one third octave bands. The results indicate that the model can predict the weighted airborne reduction index Rw for various floors with a maximum error of 1 dB. The accuracy decreases with errors up to 9 dB for the weighted index for impact sound Ln,w, in cases of complex floor configurations due to large error deviations in high frequency bands between the real and estimated values. The model also shows a very good accuracy in predicting the airborne and impact sound insulation curves in the low frequencies, which are of higher interest usually in building acoustics.

(Less)
Please use this url to cite or link to this publication:
author
; ; ; and
organization
publishing date
type
Chapter in Book/Report/Conference proceeding
publication status
published
subject
keywords
Airborne sound, Building acoustics, Impact sound, Neural networks, Prediction model
host publication
Proceedings of INTER-NOISE 2021 - 2021 International Congress and Exposition of Noise Control Engineering
series title
Proceedings of INTER-NOISE 2021 - 2021 International Congress and Exposition of Noise Control Engineering
editor
Dare, Tyler ; Bolton, Stuart ; Davies, Patricia ; Xue, Yutong and Ebbitt, Gordon
publisher
The Institute of Noise Control Engineering of the USA, Inc.
conference name
50th International Congress and Exposition of Noise Control Engineering, INTER-NOISE 2021
conference location
Washington, United States
conference dates
2021-08-01 - 2021-08-05
external identifiers
  • scopus:85117367817
ISSN
0736-2935
ISBN
9781732598652
DOI
10.3397/IN-2021-2619
language
English
LU publication?
yes
additional info
Publisher Copyright: © INTER-NOISE 2021 .All right reserved.
id
1f8834cc-e4c8-405c-b16c-bee2b79eefde
date added to LUP
2021-11-16 10:06:46
date last changed
2022-04-27 05:38:17
@inproceedings{1f8834cc-e4c8-405c-b16c-bee2b79eefde,
  abstract     = {{<p>Reliable prediction tools are yet to be developed for estimating the accurate acoustic performance of lightweight structures, which are vital especially in the design process. This paper presents a sound insulation prediction model based on artificial Neural Networks (NN) to estimate acoustic performance for airborne and impact sound insulation of floor structures. At an initial stage, the prediction model was developed and tested for a small amount of data, specifically 67 laboratory measurement curves in one third octave bands. The results indicate that the model can predict the weighted airborne reduction index R<sub>w</sub> for various floors with a maximum error of 1 dB. The accuracy decreases with errors up to 9 dB for the weighted index for impact sound L<sub>n,w</sub>, in cases of complex floor configurations due to large error deviations in high frequency bands between the real and estimated values. The model also shows a very good accuracy in predicting the airborne and impact sound insulation curves in the low frequencies, which are of higher interest usually in building acoustics.</p>}},
  author       = {{Bader Eddin, Mohamad and Menard, Sylvain and Bard, Delphine and Kouyoumji, Jean Luc and Vardaxis, Nikolas Georgios}},
  booktitle    = {{Proceedings of INTER-NOISE 2021 - 2021 International Congress and Exposition of Noise Control Engineering}},
  editor       = {{Dare, Tyler and Bolton, Stuart and Davies, Patricia and Xue, Yutong and Ebbitt, Gordon}},
  isbn         = {{9781732598652}},
  issn         = {{0736-2935}},
  keywords     = {{Airborne sound; Building acoustics; Impact sound; Neural networks; Prediction model}},
  language     = {{eng}},
  publisher    = {{The Institute of Noise Control Engineering of the USA, Inc.}},
  series       = {{Proceedings of INTER-NOISE 2021 - 2021 International Congress and Exposition of Noise Control Engineering}},
  title        = {{A sound insulation prediction model for floor structures in wooden buildings using neural networks approach}},
  url          = {{http://dx.doi.org/10.3397/IN-2021-2619}},
  doi          = {{10.3397/IN-2021-2619}},
  year         = {{2021}},
}