Prediction of outdoor sound transmission loss with an artificial neural network

In the present study, the sound transmission loss (STL) of ultrafine glass fiber felts in terms of areal density and sound frequency has been modeled by artificial neural network (ANN), the Law of Theoretic Mass and fitting polynomial, respectively. The STL of ultrafine glass fiber felts with the areal density ranging from 0 to 300 g/m2 and at the sound frequency ranging from 500 to 6300 Hz was employed as training data for ANN. By the optimization of ANN structure, the number of neurons in the two hidden layers was determined to 8 and 4 respectively. The mean squared error of the ANN model was only 0.191 and the correlation coefficient was 0.9989, which showed high accuracy for estimating the STL of the felts. Compared with other two models, the ANN model showed excellent agreement with the measured results and it's very appropriate for the estimation of acoustic properties of ultrafine glass fiber felts.

Download Full-text

An artificial neural network based transmission loss allocation for bilateral contracts

Canadian Conference on Electrical and Computer Engineering, 2005. ◽

10.1109/ccece.2005.1557426 ◽

2006 ◽

Cited By ~ 10

Author(s):

R. Haque ◽

N. Chowdhury

Keyword(s):

Neural Network ◽

Artificial Neural Network ◽

Transmission Loss ◽

Loss Allocation ◽

Bilateral Contracts ◽

Transmission Loss Allocation ◽

Artificial Neural

Download Full-text

Application of Neural Network and Genetic Algorithm to the Optimum Design of Perforated Tube Mufflers

Journal of Mechanics ◽

10.1017/s1727719100002793 ◽

2009 ◽

Vol 25 (3) ◽

pp. N7-N16 ◽

Cited By ~ 2

Author(s):

M.-C. Chiu ◽

Y.-C. Chang

Keyword(s):

Neural Network ◽

Experimental Data ◽

Genetic Algorithm ◽

Mathematical Model ◽

Optimum Design ◽

Transmission Loss ◽

Research Work ◽

Sound Transmission ◽

Optimum Process ◽

Sound Transmission Loss

AbstractResearch on new techniques of perforated silencers has been well addressed. However, the research work on shape optimization for a volume-constrained silencer within a constrained machine room is rare. Therefore, the optimum design of mufflers becomes an essential issue. In this paper, to simplify the optimum process, a simplified mathematical model of the muffler is constructed with a neural network using a series of input design data (muffle dimensions) and output data (theoretical sound transmission loss) obtained by a theoretical mathematical model (TMM). To assess the optimal mufflers, the neural network model (NNM) is used as an objective function in conjunction with a genetic algorithm (GA). Moreover, the numerical cases of sound elimination with respect to pure tones (500, 1000, 2000Hz) are exemplified and discussed.Before the GA operation can be carried out, the accuracy of the TMM is checked by Crocker's experimental data. In addition, both the TMM and NNM are compared. It is found that the TMM and the experimental data are in agreement. Moreover, the TMM and NNM confirm.The results reveal that the maximum value of the sound transmission loss (STL) can be optimally obtained at the desired frequencies. Consequently, it is obvious that the optimum algorithm proposed in this study can provide an efficient way to develop optimal silencers.

Download Full-text