Physics‐Aware Machine‐Learning‐Driven Inverse Design of Broadband Ultra‐Open Acoustic Metamaterials
Advanced Science · 2026-11 · 13 (62)
DOI: 10.1002/advs.76894 ↗At a glance
Journal article in Advanced Science, published online on 2026-08-12. Written by Zhiwei Yang and 5 co-authors. Institution: Department of Mechanical Engineering, Boston University, Boston, Massachusetts, USA. 59 references. The full text is freely available (open access, CC BY 4.0). Funded by: Boston University Photonics Center, Rajen Kilachand Fund for Integrated Life Science and Engineering for funding.
Abstract (original language)
Ventilated acoustic silencers combining strong sound attenuation with high ventilation are pivotal for advanced noise control. However, balancing attenuation, bandwidth, openness, and thickness remains a high‐dimensional challenge. Here, we present a physics‐aware machine‐learning‐driven inverse design framework for broadband ultra‐open acoustic silencers (UAS). Based on Green's function parameterization, the design space is physically decoupled into spectral and radial space, ensuring physical interpretability while reducing complexity. A two‐stage coarse‐to‐fine surrogate model captures both broadband envelopes and sharp resonant features. Coupled with a population‐based, hybrid‐objective parallel (PHP) inverse strategy, our framework enables rapid exploration of non‐convex landscapes, identifying hundreds of optimized candidates within seconds each. Crucially, this framework reveals the intrinsic relationship among thickness, ventilation, and spectral response, and uncovers hidden linear design rules that serve as geometric proxies for impedance‐matching. We experimentally validate multiple architectures: UAS‐2 represents the monolithic, single‐mode design with high ventilation, whereas UAS‐3 exploits multi‐mode interference for improved spectral performance. To circumvent the trade‐off ceiling of single‐unit resonators, a parallel‐composite architecture (UAS‐4) is introduced to enhance performance. Results confirm a broadband bandwidth exceeding 830 Hz within 1000‐2000 Hz, with ultra‐thin profile (0.1–0.2λ, 4–8 cm) and 80% ventilation. This work establishes a data‐driven paradigm for discovering design principles in functional metamaterials.
Subjects
Author keywords
Authors and institutions
- Department of Mechanical Engineering, Boston University, Boston, Massachusetts, USA.
- Photonics Center, Boston University, Boston, Massachusetts, USA.
- Division of Materials Science & Engineering, Boston University, Boston, Massachusetts, USA.
- Department of Electrical & Computer Engineering, Boston University, Boston, Massachusetts, USA.
- Department of Biomedical Engineering, Boston University, Boston, Massachusetts, USA.
ORCID profiles: Thomas G Bifano, Xin Zhang
Funding
- Boston University Photonics Center
- Rajen Kilachand Fund for Integrated Life Science and Engineering for funding
Cite
APA
Yang, Z., Li, M., Xie, X., Chen, A., Bifano, T. G., & Zhang, X. (2026). Physics‐Aware Machine‐Learning‐Driven Inverse Design of Broadband Ultra‐Open Acoustic Metamaterials. Advanced Science, 13(62). https://doi.org/10.1002/advs.76894
Vancouver
Yang Z, Li M, Xie X, Chen A, Bifano TG, Zhang X. Physics‐Aware Machine‐Learning‐Driven Inverse Design of Broadband Ultra‐Open Acoustic Metamaterials. Advanced Science. 2026;13(62). doi:10.1002/advs.76894
BibTeX
@article{Yang2026,
author = {Yang, Zhiwei and Li, Mengyu and Xie, Xiaohang and Chen, Ao and Bifano, Thomas G and Zhang, Xin},
title = {Physics‐Aware Machine‐Learning‐Driven Inverse Design of Broadband Ultra‐Open Acoustic Metamaterials},
journal = {Advanced Science},
year = {2026},
volume = {13},
number = {62},
doi = {10.1002/advs.76894}
}
EUVIMED