Jingcan Zhu

Hunan University of Science and Technology

Papers

Total Citations

139

H-Index

About

Jingcan Zhu is a leading researcher in computational intelligence, specializing in neural network theory and dynamic system solving. Their work centers on advancing zeroing neural networks (ZNNs) for time-varying problems, with a strong emphasis on robustness, convergence, and noise tolerance. Zhu’s most influential contribution, “A Robust Predefined-Time Convergence Zeroing Neural Network for Dynamic Matrix Inversion” (2022, 102 citations), introduces a groundbreaking framework that guarantees convergence within a user-defined timeframe, even under challenging conditions—a critical advancement for real-time applications in robotics and control systems. Building on this, Zhu developed a noise-tolerant parameter-variable ZNN (2023, 20 citations) and extended recurrent neural networks to text classification and dynamic Sylvester equation solving (2023, 17 citations), bridging theoretical rigor with practical utility. With over 140 citations across their top papers, Zhu’s work has significantly enhanced the reliability and efficiency of neural solvers for engineering and scientific computing. Their research is widely recognized for pushing the boundaries of predefined-time stability and adaptive parameter design, making Zhu a key figure in the evolution of intelligent dynamic systems.