Data-driven optimization of the periodic beam with multiple acoustic black holes

This paper presents data-driven optimization study of a periodic beam with multiple acoustic black holes (ABH) for better dynamic performance. The vibration and sound radiation of the structure are analyzed by the spectral element method (SEM). A data-driven multi-objective optimization method is proposed to investigate the design problems for minimizing the structural weight and maximizing the sound transmission loss. Several cases are presented to demonstrate the accuracy of the SEM compared with the finite element method, and the multi-objective optimal designs of the ABH beam. Numerical results indicate that the data-driven method can significantly improve the computational efficiency. Pareto solutions provide a variety of design options and reveal the mechanisms about band gaps of the periodic beam. (C) 2020 Elsevier Ltd. All rights reserved.

Automated summary

This paper presents a data-driven optimization study of a periodic beam with multiple acoustic black holes, demonstrating that the method significantly improves computational efficiency and provides multiple design options while revealing the mechanisms of the band gaps in the periodic beam.