Prediction of Sound Insulation Using Artificial Neural Networks—Part II: Lightweight Wooden Façade Structures

Abstract

A prediction model based on artificial neural networks is adapted to forecast the acoustic performance of airborne sound insulation of various lightweight wooden façade walls. A total of 100 insulation curves were used to develop the prediction model. The data are laboratory measurements of façade walls in one-third-octave bands (50 Hz–5 kHz). For each façade wall, geometric and physical information (material type, dimensions, thicknesses, densities, and more) are used as input parameters. The model shows a satisfactory predictive capability for airborne sound reduction. A higher accuracy is obtained at middle frequencies (250 Hz–1 kHz), while lower and higher frequency ranges often show higher deviations. The weighted airborne sound reduction index (Rw) of façades can be estimated with a maximum difference of 3 dB. Sometimes, the model shows high variations within fundamental and critical frequencies that influence the predictive precision. A sensitivity analysis is implemented to investigate the significance of parameters in insulation estimations. The material density (i.e., cross-laminated timber panel, gypsum board), thickness of the insulation materials, thickness and spacing between interior studs and the total density of façades are factors of significant weight on predictions. The results also emphasize the importance of façade thickness and the total density of the clustered exterior layers.

Study of Technological Advancement and Challenges of Façade System for Sustainable Building: Current Design Practice

“…This can lead to savings on heating and cooling costs in the long run [147]. Furthermore, timber is a lighter material than concrete or steel, which reduces the weight of a building's structure [148]. This can potentially save money on the building's foundation and structural support [149].…”

Acoustic prediction and testing for "Basajaun" EU Project demo building using neural network, prediction for innovative wooden partition wall with composites and bio-based insulation

“…The validation set is used to optimize the hyperparameters of the model, such as the number of hidden layers and neurons. Since the predictions are continuous values (insulation curves), the root mean-square error (RMSE) function can be used as a cost function to evaluate the predictive capability [11,12] .…”

“…ANN perform good predictions with a good confident domain. In early articles Bader Eddin [11] and [12] could evaluate the predictive capability on wooden walls, wooden facades and wooden floors. Concerning proposals 1, 2 and 3, ANN calculation can be used with a good confident domain.…”

A Low-Stress Method for Determining Static and Dynamic Material Parameters for Vibration Isolation with the Use of VMQ Silicone

“…There are methods that allow the estimation of airborne [38] and impact noise [39] transmission reduction for floating floors. However, these methods are simplified and do not take into account the possible increase in low-frequency noise and changes in the perception of vibrations by building users [40][41][42]. In the case of flexible joints, the reduction in vibration transmission, including those responsible for noise, can be estimated at the structural node [43,44].…”