Nonlinear Delay Systems Adaptive Neural Network Control

In recent years, nonlinear control systems has become a hot topic. Many of these studies aimed at the time-delay nonlinear systems, while the adaptive control theory as a nonlinear control strategy applies to complex nonlinear systems especially. Furtherly backstepping method based on adaptive neural network control has become one of the major hot topic. Applying the time-delay neural network theory into nonlinear systems has achieved a good control effect. Aiming at a class of time-delay nonlinear systems with unknown nonlinear term and some unknown parameters, this paper presented a robust adaptive neural network control design based on the Lyapunov stability theory, combined with the self-adaptive neural network design and backstepping design.This kind of design not only reduced the calculation of the neural network, but also ensured the control performance of the closed-loop system, and furtherly gave the promotion and application of the control strategy. The simulation results showed the effectiveness of the proposed method.This paper is divided into five chapters, chapter 1 gives the research status and significance of a class of time-delay nonlinear systems, and also introduced the research object and content.Chapter2 considers the adaptive stabilization of a class of time-delay nonlinear systems. Firstly, we design a adaptive stabilization controller by lyapunov function and Backstepping design method, then construct lyapunov function and stabilizing controller at the same time by recursive principle, and then we decompose the complicated nonlinear system into several sub-systems whose order is smaller than the original system's. Then partial lyapunov function and the middle fictious con(?)rolling scale will be designed for every sub-system, following that we pushed backwards to the whole system. Later, we consider the whole adaptive nonlinear system, and at last we choose lyapunov function.The above work insured the globle stablation of the closed-loop system.Chapter 3,an adaptive neural network control output-feedback regulation for a class of unknown nonlinear time-delay systems is proposed. We only use an NN to compensate for all unknown upper bounding functions. The proposed design method is proved to converge to a small neighborhood of the origin. Finally, simulation results show the effectiveness of the method. Chapter 4, adaptive neural network control is proposed for a class of strict-feedback nonlinear time-delay systems. Unknown smooth function vectors and unknown timo-delay functions are approximated by two neural networks, respectively, such that the requirement on the unknown time-delay functions is relaxed. In addition, the proposed systematic backstepping design method has been proven to be able to guarantee semi-globally uniformly ultimately bounded of closed loop signals, and the output of the system has been proven to converge to a small neighborhood of the desired trajectory. Finally, simulation result is presented to demonstrate the effectiveness of the approach.Chapter5 summarizes the main results cf this paper and a prospect of the future research work.