Papers
5
Total Citations
120
H-Index
4
About
Bing Zheng is a leading researcher in computational intelligence and neural dynamics, whose work focuses on developing advanced zeroing neural network (ZNN) models for solving complex time-varying matrix equations. His major contributions lie in enhancing the robustness, convergence speed, and noise tolerance of ZNN solvers, particularly for the time-varying Sylvester equation—a fundamental problem in control theory and robotics. Zheng’s most cited paper, “Improved recurrent neural networks for solving Moore-Penrose inverse of real-time full-rank matrix” (2020, 40 citations), established foundational methods for real-time matrix computation. He further advanced the field with “Accelerating noise-tolerant zeroing neural network with fixed-time convergence” (2021, 36 citations), which introduced fixed-time convergence guarantees under noisy conditions. Notably, his 2022 work on a Takagi–Sugeno fuzzy ZNN (24 citations) pioneered self-adaptive convergence parameters using fuzzy logic, significantly improving model efficiency. Zheng’s research has practical impact, demonstrated by applying a modified noise-tolerant ZNN to robot manipulator control (2023, 18 citations). His most recent 2025 paper on predefined-time convergence (2 citations) continues to push boundaries, offering simpler design for real-time applications. With over 120 total citations, Zheng’s work is essential reading for researchers in neural networks, matrix computation, and robotic control.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3
- 4
- 5