TY - JOUR
T1 - Toward signed distance function based metamaterial design
T2 - Neural operator transformer for forward prediction and diffusion model for inverse design
AU - Liu, Qibang
AU - Koric, Seid
AU - Abueidda, Diab
AU - Meidani, Hadi
AU - Geubelle, Philippe
N1 - The authors would like to thank the National Center for Supercomputing Applications (NCSA) at the University of Illinois Urbana-Champaign, and particularly its Research Computing Directorate, Industry Program, and Center for Artificial Intelligence Innovation (CAII) for support and hardware resources. This research used both the DeltaAI advanced computing and data resource, which is supported by the National Science Foundation(award OAC 2320345) and the State of Illinois, and the Delta advanced computing and data resource which is supported by the National Science Foundation (award OAC 2005572) and the State of Illinois. Delta and DeltaAI are joint efforts of the University of Illinois Urbana-Champaign and its National Center for Supercomputing Applications. This work used Delta/DeltaAI at NCSA through allocation MAT240113 from the Advanced Cyberinfrastructure Coordination Ecosystem: Services & Support (ACCESS) program, which is supported by U.S. National Science Foundation grants #2138259, #2138286, #2138307, #2137603, and #2138296.
PY - 2025/11/1
Y1 - 2025/11/1
N2 - The inverse design of metamaterial architectures presents a significant challenge, particularly for nonlinear mechanical properties involving large deformations, buckling, contact, and plasticity. Traditional methods, such as gradient-based optimization, and recent generative deep-learning approaches often rely on binary pixel-based representations, which introduce jagged edges that hinder finite element (FE) simulations and 3D printing. To overcome these challenges, we propose an inverse design framework that utilizes a signed distance function (SDF) representation combined with a conditional diffusion model. The SDF provides a smooth boundary representation, eliminating the need for post-processing and ensuring compatibility with FE simulations and manufacturing methods. A classifier-free guided diffusion model is trained to generate SDFs conditioned on target macroscopic stress-strain curves, enabling efficient one-shot design synthesis. To assess the mechanical response and the quality of the generated designs, we introduce a forward prediction model based on Neural Operator Transformers (NOT), which accurately predicts homogenized stress-strain curves and local solution fields for arbitrary geometries with irregular query meshes. This approach enables a closed-loop process for general metamaterial design, offering a pathway for the development of advanced functional materials.
AB - The inverse design of metamaterial architectures presents a significant challenge, particularly for nonlinear mechanical properties involving large deformations, buckling, contact, and plasticity. Traditional methods, such as gradient-based optimization, and recent generative deep-learning approaches often rely on binary pixel-based representations, which introduce jagged edges that hinder finite element (FE) simulations and 3D printing. To overcome these challenges, we propose an inverse design framework that utilizes a signed distance function (SDF) representation combined with a conditional diffusion model. The SDF provides a smooth boundary representation, eliminating the need for post-processing and ensuring compatibility with FE simulations and manufacturing methods. A classifier-free guided diffusion model is trained to generate SDFs conditioned on target macroscopic stress-strain curves, enabling efficient one-shot design synthesis. To assess the mechanical response and the quality of the generated designs, we introduce a forward prediction model based on Neural Operator Transformers (NOT), which accurately predicts homogenized stress-strain curves and local solution fields for arbitrary geometries with irregular query meshes. This approach enables a closed-loop process for general metamaterial design, offering a pathway for the development of advanced functional materials.
KW - Arbitrary geometry
KW - Diffusion model
KW - Generative AI
KW - Inverse design
KW - Metamaterial
KW - Neural operator transformer
UR - https://www.scopus.com/pages/publications/105013290494
UR - https://www.scopus.com/pages/publications/105013290494#tab=citedBy
U2 - 10.1016/j.cma.2025.118316
DO - 10.1016/j.cma.2025.118316
M3 - Article
AN - SCOPUS:105013290494
SN - 0045-7825
VL - 446
JO - Computer Methods in Applied Mechanics and Engineering
JF - Computer Methods in Applied Mechanics and Engineering
M1 - 118316
ER -