1 February 2022 in Materials Horizons
We present a hybrid neural network and genetic optimization adaptive method incorporating Bézier curves to consider the large design space of lattice structures with superior mechanical properties.
1 July 2021 in Journal of Manufacturing Processes
30 April 2024 in PNAS Nexus
Numerical solutions to partial differential equations (PDEs) are instrumental for material structural design where extensive data screening is needed. However, traditional numerical methods demand significant computational resources, highlighting the need for innovative optimization algorithms to streamline design exploration. Direct gradient-based optimization algorithms, while effective, rely on design initialization and require complex, problem-specific sensitivity derivations. The advent of machine learning offers a promising alternative to handling large parameter spaces. To further mitigate data dependency, researchers have developed physics-informed neural networks (PINNs) to learn directly from PDEs. However, the intrinsic continuity requirement of PINNs restricts their application in structural mechanics problems, especially for composite materials. Our work addresses this discontinuity issue by substituting the PDE residual with a weak formulation in the physics-informed training process. The proposed approach is exemplified in modeling digital materials, which are mathematical representations of complex composites that possess extreme structural discontinuity. This article also introduces an interactive process that integrates physics-informed loss with design objectives, eliminating the need for pretrained surrogate models or analytical sensitivity derivations. The results demonstrate that our approach can preserve the physical accuracy in data-free material surrogate modeling but also accelerates the direct optimization process without model pretraining.
28 September 2022 in Journal of Applied Physics
Engineered piezoelectric metamaterials can possess electro-momentum coupling between the macroscopic momentum and electric stimuli. This indicates the applicability of such metamaterials for wave scattering with an extra design degree of freedom, in the same way as Willis materials. To fully utilize this novel bianisotropy, we derive for the first-time theoretical bounds on electro-momentum coupling in wave scattering via energy conservation. As this coupling acts on both elastodynamics and electromagnetics, the polarizability tensor is generalized to fill their link in the bounds. Our derived bounds are verified via analytical scattering solutions. Results show that the bianisotropic scattering can be of the same order as the non-bianisotropic terms via the aid of electro-momentum coupling even for small Willis coupling. We further reveal the possibility of using electro-momentum coupling for tunable cloaking. This sheds light on the promising potential of piezoelectric metamaterials for tunable scattering devices whose bianisotropy can be modulated by external electric stimuli.
23 September 2023 in Journal of the Mechanics and Physics of Solids