Simiao Fei
Papers
1
Total Citations
2
H-Index
1
About
Simiao Fei is a researcher advancing the frontier of physics-informed machine learning, with a primary focus on Hamiltonian neural networks and rigid body dynamics. In their most cited work, "Hamiltonian Neural Network 6-DoF Rigid Body Dynamic Modeling Based on Energy Variation Estimation" (2023), Fei introduces a novel deep modeling methodology that leverages energy variation estimation to capture the complex dynamics of six-degree-of-freedom rigid body systems. This approach directly addresses longstanding challenges in modeling accuracy and computational complexity for controlled rigid body dynamics. By embedding Hamiltonian mechanics into neural network architectures, Fei's work enables more physically consistent and energy-conserving predictions, offering significant improvements over traditional black-box models. Although early in their career, with this paper garnering 2 citations, the work represents a meaningful step toward integrating fundamental physics with deep learning for robotics and aerospace applications. Fei's research sits at the intersection of dynamical systems theory, energy-based modeling, and neural network design, promising to influence how engineers simulate and control complex mechanical systems with greater fidelity and interpretability.
Research Focus
Key Achievements
Top Papers
- 1