Event-based Adaptive Neural Network Tracking Control Of Uncertain Nonlinear Systems With Unknown Disturbance And Input Delay

In this paper, we delve into the analysis of a specific category of constrained nonlinear systems exhibiting strict feedback, incorporating input time delay as well as time-varying perturbations. We introduce an adaptive control strategy utilizing event-triggered neural networks, complemented by a nonlinear disturbance observer (NDO) aimed at estimating the unknown composite disturbance, encompassing external perturbations and approximation errors. The approximation of the unknown nonlinear functions is achieved through radial basis functions neural networks (RBFNN). To address the challenges posed by input time delay, we employ the Padé approximation for effective compensation. To address the state constraint problem, we employ the Barrier Lyapunov function (BLF). Leveraging the Lyapunov stability theory, we demonstrate that all signals within the closed-loop system are ultimately semi-globally consistent ultimately bounded (SGUUB). Furthermore, the analysis reveals minimal tracking error between the system’s output and the reference signal. The effectiveness of the proposed approach is validated through numerical simulations.