Machine learning and deep learning in phononic crystals and metamaterials – A review

Abstract

Machine learning (ML), as a component of artificial intelligence, encourages structural design exploration which leads to new technological advancements. By developing and generating data-driven methodologies that supplement conventional physics and formula-based approaches, deep learning (DL), a subset of machine learning offers an efficient way to understand and harness artificial materials and structures. Recently, acoustic and mechanics communities have observed a surge of research interest in implementing machine learning and deep learning methods in the design and optimization of artificial materials. In this review we evaluate the recent developments and present a state-of-the-art literature survey in machine learning and deep learning based phononic crystals and metamaterial designs by giving historical context, discussing network architectures and working principles. We also explain the application of these network architectures adopted for design and optimization of artificial structures. Since this multidisciplinary research field is evolving, a summary of the future prospects is also covered. This review article serves to update the acoustics, mechanics, physics, material science and deep learning communities about the recent developments in this newly emerging research direction