Bi-objective Sound Transmission Loss Optimal Design of Double Panels Using a Genetic Algorithm

This paper presents a bi-objective optimization of double panels for simultaneously minimizing mass while maximizing the weighted sound transmission loss (STL). Firstly, the acoustic model of double panels is introduced based on the wave propagation method and modal superposition method. Secondly, the optimization problem is formulated as a bi-objective programming model, and a solution algorithm based on the non-dominated sorting genetic algorithm II (NSGA-II) is provided to solve the proposed model. Finally, taking a standard window structure on a high speed train as a reference structure, an optimization calculation based on non-dominated sorting genetic algorithm II (NSGA-II) is carried out to get the Pareto front solutions. The fitting formula of the mass and weighted STL (R-w) under the Pareto front solution is obtained, which provides a reference for the design and selection of Rw under different masses. The frequency sound insulation characteristics and its STL mechanism of the optimized double panel are further analyzed, which shed some light on the lightweight design of double panel structures. Relative optimization method can also be applied to airplane's window design.