Prediction of Sound Insulation of Sandwich Partition Panels by Means of Artificial Neural Networks
IR@NPL: CSIR-National Physical Laboratory, New Delhi
View Archive InfoField | Value | |
Title |
Prediction of Sound Insulation of Sandwich Partition Panels by Means of Artificial Neural Networks
|
|
Creator |
Garg, Naveen
Dhruw, Siddharth Gandhi, Laghu |
|
Subject |
Acoustics
|
|
Description |
The paper presents the application of Artificial Neural Networks (ANN) in predicting sound insulation through multi-layered sandwich gypsum partition panels. The objective of the work is to develop an Artificial Neural Network (ANN) model to estimate the R-w and STC value of sandwich gypsum constructions. The experimental results reported by National Research Council, Canada for Gypsum board walls (Halliwell et al., 1998) were utilized to develop the model. A multilayer feed-forward approach comprising of 13 input parameters was developed for predicting the R-w and STC value of sandwich gypsum constructions. The Levenberg-Marquardt optimization technique has been used to update the weights in back-propagation algorithm. The presented approach could be very useful for design and optimization of acoustic performance of new sandwich partition panels providing higher sound insulation. The developed ANN model shows a prediction error of +/- 3 dB or points with a confidence level higher than 95%.
|
|
Publisher |
Polish Scientific Publishers
|
|
Date |
2017
|
|
Type |
Article
PeerReviewed |
|
Format |
application/pdf
|
|
Identifier |
http://npl.csircentral.net/2827/1/Prediction%20of%20Sound%20Insulation%20.pdf
Garg, Naveen and Dhruw, Siddharth and Gandhi, Laghu (2017) Prediction of Sound Insulation of Sandwich Partition Panels by Means of Artificial Neural Networks. Archives of Acoustics, 42. pp. 643-651. ISSN 0137-5075 |
|
Relation |
http://npl.csircentral.net/2827/
|
|