Shape optimization of mufflers hybridized with multiple connected tubes using the boundary element method, neural networks, and genetic algorithm
Recently, research on new mufflers hybridized with connected curved tubes using phase cancellation techniques has been well addressed in the industrial field. Most researchers have explored noise reduction effects based on the transfer matrix method and the stiffness matrix method. However, the maximum noise reduction of a silencer within a constrained space, which frequently occurs in engineering problems, has been neglected. Therefore, the optimum design of mufflers becomes an essential issue. In this article, two kinds of phase-cancellation mufflers (a two-connected tube and a three-connected tube) within a fixed length are assessed. In order to speed up the assessment of optimal mufflers hybridized with multiple connected curved tubes, a simplified objective function (OBJ) is established by linking the boundary element model (BEM; developed by the commercialized software SYSNOISE) with a polynomial neural network fitted with a series of real data: input design data (muffler dimensions) and output data approximated by BEM data in advance. To assess the optimal mufflers, a genetic algorithm is applied. Optimal results reveal that the maximum value of the sound transmission loss can be improved at the desired frequencies. Consequently, the optimum algorithm proposed in this study can provide an efficient way to develop optimal silencers for industry.