Papers
3
Total Citations
21
H-Index
2
About
Chunhao Han is a rising researcher in computational mathematics and intelligent control, whose work focuses on advancing neural network solvers for dynamic matrix equations—a critical tool for real-time robotic and autonomous systems. Han’s major contributions lie in developing robust, high-performance zeroing neural network (ZNN) models that overcome the limitations of traditional solvers, such as slow convergence and sensitivity to noise. Their most-cited paper, “A modified noise-tolerant ZNN model for solving time-varying Sylvester equation with its application to robot manipulator” (2023, 18 citations), introduces a modified ZNN that not only tolerates noise but also achieves rapid convergence, with a direct application to robot manipulator control—demonstrating real-world impact in automation. Building on this, Han’s 2025 work, “A Novel Robust and Predefined-Time Zeroing Neural Network Solver for Time-Varying Linear Matrix Equation” (2 citations), proposes an innovative activation function that guarantees convergence within a user-specified time, a breakthrough for time-critical tasks. Additionally, their exploration of first/second-order norm-based gradient neural networks (2025, 1 citation) offers new theoretical insights into dynamic equation solving. With a growing citation record and a focus on practical robotics applications, Han is establishing a reputation for bridging theoretical neural network design with tangible engineering solutions.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3