Prediction of Sound Insulation Using Artificial Neural Networks—Part I : LightweightWooden Floor Structures
(2022) In Acoustics 4(1). p.203-226- Abstract
The artificial neural networks approach is applied to estimate the acoustic performance for airborne and impact sound insulation curves of different lightweight wooden floors. The prediction model is developed based on 252 standardized laboratory measurement curves in one-third octave bands (50-5000 Hz). Physical and geometric characteristics of each floor structure (materials, thickness, density, dimensions, mass and more) are utilized as network parameters. The predictive capability is satisfactory, and the model can estimate airborne sound better than impact sound cases especially in the middle-frequency range (250-1000 Hz), while higher frequency bands often show high errors. The forecast of the weighted airborne sound reduction... (More)
The artificial neural networks approach is applied to estimate the acoustic performance for airborne and impact sound insulation curves of different lightweight wooden floors. The prediction model is developed based on 252 standardized laboratory measurement curves in one-third octave bands (50-5000 Hz). Physical and geometric characteristics of each floor structure (materials, thickness, density, dimensions, mass and more) are utilized as network parameters. The predictive capability is satisfactory, and the model can estimate airborne sound better than impact sound cases especially in the middle-frequency range (250-1000 Hz), while higher frequency bands often show high errors. The forecast of the weighted airborne sound reduction index Rw was calculated with a maximum error of 2 dB. However, the error increased up to 5 dB in the worse case prediction of the weighted normalized impact sound pressure level Ln,w. The model showed high variations near the fundamental and critical frequency areas which affect the accuracy. A feature attribution analysis explored the essential parameters on estimation of sound insulation. The thickness of the insulation materials, the density of cross-laminated timber slab and the concrete floating floors and the total density of floor structures seem to affect predictions the most. A comparison between wet and dry floor solution systems indicated the importance of the upper part of floors to estimate airborne and impact sound in low frequencies.
(Less)
- author
- Eddin, Mohamad Bader ; Ménard, Sylvain ; Hagberg, Delphine Bard LU ; Kouyoumji, Jean Luc and Vardaxis, Nikolaos Georgios LU
- organization
- publishing date
- 2022
- type
- Contribution to journal
- publication status
- published
- subject
- keywords
- Airborne sound, Artificial neural networks, Impact sound, Insulation, Prediction model
- in
- Acoustics
- volume
- 4
- issue
- 1
- pages
- 24 pages
- publisher
- MDPI AG
- external identifiers
-
- scopus:85130010083
- ISSN
- 2624-599X
- DOI
- 10.3390/acoustics4010013
- language
- English
- LU publication?
- yes
- id
- fa2c5008-2496-453b-9f68-dfd783950bf2
- date added to LUP
- 2022-08-25 11:21:33
- date last changed
- 2023-09-14 11:41:47
@article{fa2c5008-2496-453b-9f68-dfd783950bf2,
abstract = {{<p>The artificial neural networks approach is applied to estimate the acoustic performance for airborne and impact sound insulation curves of different lightweight wooden floors. The prediction model is developed based on 252 standardized laboratory measurement curves in one-third octave bands (50-5000 Hz). Physical and geometric characteristics of each floor structure (materials, thickness, density, dimensions, mass and more) are utilized as network parameters. The predictive capability is satisfactory, and the model can estimate airborne sound better than impact sound cases especially in the middle-frequency range (250-1000 Hz), while higher frequency bands often show high errors. The forecast of the weighted airborne sound reduction index R<sub>w</sub> was calculated with a maximum error of 2 dB. However, the error increased up to 5 dB in the worse case prediction of the weighted normalized impact sound pressure level L<sub>n,w</sub>. The model showed high variations near the fundamental and critical frequency areas which affect the accuracy. A feature attribution analysis explored the essential parameters on estimation of sound insulation. The thickness of the insulation materials, the density of cross-laminated timber slab and the concrete floating floors and the total density of floor structures seem to affect predictions the most. A comparison between wet and dry floor solution systems indicated the importance of the upper part of floors to estimate airborne and impact sound in low frequencies.</p>}},
author = {{Eddin, Mohamad Bader and Ménard, Sylvain and Hagberg, Delphine Bard and Kouyoumji, Jean Luc and Vardaxis, Nikolaos Georgios}},
issn = {{2624-599X}},
keywords = {{Airborne sound; Artificial neural networks; Impact sound; Insulation; Prediction model}},
language = {{eng}},
number = {{1}},
pages = {{203--226}},
publisher = {{MDPI AG}},
series = {{Acoustics}},
title = {{Prediction of Sound Insulation Using Artificial Neural Networks—Part I : LightweightWooden Floor Structures}},
url = {{http://dx.doi.org/10.3390/acoustics4010013}},
doi = {{10.3390/acoustics4010013}},
volume = {{4}},
year = {{2022}},
}