Deep Neural Network-Based Prescribed Performance Control for Strict-Feedback Nonlinear Systems

This paper investigates the prescribed performance control problem for strict-feedback nonlinear systems. A deep neural network whose weights are updated in real-time is introduced to approximate the unknown nonlinearities. Based on this deep neural network, an adaptive control scheme is further developed, which can ensure the prescribed performance of the tracking error. It is shown that the presented control scheme can achieve superior tracking performance over the traditional twolayer neural network-based control scheme. Finally, a numerical example is provided to illustrate the effectiveness of the proposed control scheme.