Inverse design of nonlinear mechanical metamaterials via video denoising diffusion models

Abstract

The accelerated inverse design of complex material properties—such as identifying a material with a given stress–strain response over a nonlinear deformation path—holds great potential for addressing challenges from soft robotics to biomedical implants and impact mitigation. Although machine learning models have provided such inverse mappings, they are typically restricted to linear target properties such as stiffness. Here, to tailor the nonlinear response, we show that video diffusion generative models trained on full-field data of periodic stochastic cellular structures can successfully predict and tune their nonlinear deformation and stress response under compression in the large-strain regime, including buckling and contact. Key to success is to break from the common strategy of directly learning a map from property to design and to extend the framework to intrinsically estimate the expected deformation path and the full-field internal stress distribution, which closely agree with finite element simulations. This work thus has the potential to simplify and accelerate the identification of materials with complex target performance.

Rational Design of Flexible Mechanical Force Sensors for Healthcare and Diagnosis

“…These metrics subsequently function as the design objectives for the force sensor. The diverse sensor architectures, in turn, provide the design space, and the implementation of an AI-enabled reverse design strategy for the sensor architecture could help accelerate the process of customization [ 146 , 263 , 264 , 265 , 266 , 267 , 268 , 269 , 270 , 271 , 272 , 273 , 274 , 275 , 276 , 277 , 278 , 279 , 280 ].…”

Inverse design of Bézier curve-based mechanical metamaterials with programmable negative thermal expansion and negative Poisson's ratio via a data augmented deep autoencoder

“…34–39 Such innovations in structural inverse design with deep learning have enabled various attempts in MM design, such as lattice structures with superior elastic modulus, controllable auxeticity, and the inverse design of MMs exhibiting target stress–strain curves. 40–45 However, a deep learning-based inverse design framework for MMs with target NTE and NPR has not yet been proposed.…”