Papers
1
Total Citations
40
H-Index
1
About
Zilin Li is a rising researcher at the forefront of computational mechanics, specializing in the intersection of physics-informed machine learning and nonsmooth dynamics. Their most-cited work, "Physics-informed neural networks for friction-involved nonsmooth dynamics problems" (2024), has already garnered 40 citations, signaling a significant impact in a rapidly evolving field. Li’s key contribution lies in pioneering the use of physics-informed neural networks (PINNs) to model complex frictional contact problems—a notoriously challenging area due to discontinuities and nonlinearities. By embedding physical laws directly into the neural network architecture, Li has developed a framework that bypasses traditional numerical difficulties, enabling more accurate and efficient simulations of systems like granular flows, robotic grasping, and earthquake fault mechanics. This work not only demonstrates a novel synergy between deep learning and classical mechanics but also offers a scalable tool for engineering applications where friction and impact dominate. Li’s research is particularly notable for bridging the gap between data-driven methods and rigorous physical constraints, a direction that promises to reshape how we approach nonsmooth dynamics in both academia and industry. As their citation count grows, Li is establishing themselves as a key voice in the next generation of computational scientists.
Research Focus
Key Achievements
Top Papers
- 1