Event‐Triggered Finite‐Time Adaptive Nonlinear Gradient Descent Neural Network Control for a Class of Nonlinear Systems

ABSTRACT This paper proposes an event‐triggered finite‐time adaptive nonlinear gradient descent neural network control strategy for a class of nonlinear system with nonlinear unmodeled dynamics. The proposed approach aims to address the challenges brought about by the system's unmodeled dynamics and external disturbances, while ensuring finite‐time convergence and robust performance. By utilizing a nonlinear gradient descent‐based adaptive neural network weight update law, the learning efficiency of the neural network is enhanced, and its approximation ability is guaranteed. The event‐triggered mechanism is introduced to reduce communication and computational overheads, activating control updates only when necessary, thus improving the communication efficiency of the system. The stability of the closed‐loop system is proven using Lyapunov theory, and the control law ensures that all closed‐loop signals converge within a finite‐time interval without Zeno behavior. Finally, the simulation results demonstrate the effectiveness and robustness of the proposed control strategy.