INVERSE DESIGN OF METAPOROUS MATERIALS WITH ANTICIPATED BROADBAND SOUND ABSORPTION PERFORMANCE VIA DENOISING DIFFUSION MODELS

The inverse design of acoustic metamaterials with anticipated manipulation characteristic holds great potential for reducing computational costs and facilitating metamaterial design process. To this end, a generative algorithm based on novel denoising diffusion models is proposed to tailor diverse metaporous materials with specified sound absorption properties. The denoising diffusion model adopts the 2D U-Net framework to extract the feature of acoustic metamaterials. The proposed generative algorithm can efficiently obtain multiple design structures by randomly sampling from the noise distribution. The denoising diffusion model exhibits superior performance in terms of training stability, image quality and design diversity. In addition, the denoising diffusion model is remarkably capable of generating creative structures which combine the features of different structures and achieve much improved broadband sound absorption performance. Consequently, this work presents a new design strategy for acoustic metamaterials and shows immense potential to be further extended to designing other classes of metamaterials such as mechanical and optical metamaterials.