Numerical assessment of gun mufflers using finite element method, neural networks, and a genetic algorithm

Abstract

In order to enhance the acoustical performance of gun mufflers, a multi-chamber muffler internally inserting with expansion cones and perforated tubes ducts is presented. Because of the complicated geometry of gun muffler, traditional analytic method used in predicting a muffler’s acoustical performance is difficult; therefore, a finite element method using the COMSOL software is adopted to predict the gun muffler’s sound transmission loss. Moreover, because an objective function (or fitness function) is needed during the optimization process, a simplified mathematical model using Artificial Neural Network (ANN) is used. Here, a polynomial objective function is established by inputting the muffler’s geometric design parameters and the related simulated Sound Transmission Loss (STL) (run on the COMSOL) via the Artificial Neural Network. Furthermore, Genetic Algorithm (GA), an optimizer, is linked to the simplified mathematical model to maximize the gun muffler’s acoustical performance. To pursue a maximal STL at the targeted tones, the geometric parameters of cone’s horizontal length (L1) and first cone’s span (L2) is optimally adjusted. Results demonstrates the STL of gun muffler at the specified frequencies of 1000, 2000, and 4000 Hz can be improved from 15.8 dB, 72.6 dB, 184.8 dB to 18.2 dB, 112.6 dB, and 416.3 dB, respectively. The paper aims to provide an optimal design method of gun muffler using Finite Element Method (FEM), Artificial Neural Network, and Genetic Algorithm. Consequently, the simulated results reveal that the optimally shaped gun muffler can efficiently depress the gun’s shooting noise.