Papers
2
Total Citations
29
H-Index
2
About
Sukheon Kang is at the forefront of computational mechanics and metamaterial design, pioneering data-driven approaches to create materials with unprecedented, programmable properties. His primary research centers on developing advanced machine learning frameworks to solve complex inverse design problems in mechanics. Kang’s most impactful work introduces a **Constrained Generative Inverse Design Network (CGIDN)** for customizable mechanical metamaterials. This framework, detailed in his highly cited 2024 paper (27 citations), allows for the precise tailoring of a material’s strain-dependent Poisson’s ratio. By employing a novel PCA-weighted loss function, he significantly enhanced the training efficiency and accuracy of deep neural networks, achieving high-fidelity inverse designs validated through both finite element analysis and physical experiments. More recently, Kang has extended his expertise to **physics-informed neural networks (PINNs)** for origami metamaterials, tackling the challenge of controlling the complex, nonlinear deployment of these lightweight structures. His work represents a significant leap forward, moving from passive materials to intelligent, programmable systems with vast potential in aerospace, robotics, and biomedical devices.
Research Focus
Key Achievements
Top Papers
- 1
- 2