The Research On Fuzzy Neural Networks Control Theory And Methods For Chaotic Systems

The dissertation focuses on intelligent control and synchronization of uncertain chaotic systems in nonlinear dynamics. The main research work of this dissertation listed as follows:Firstly, the development history and its importance of chaos exploration are reviewed, also, the definitions and applications of chaos are summarized. Moreover, Some kinds of representative strategies and their characteristics for control of chaotic systems in last decades are introduced in detail. The significance of research on the thesis is presented as well.Secondly, by incorporating the temporal difference prediction technique with the genetic algorithm, a novel hybrid genetic neural networks for controlling nonlinear chaotic system based on the scheme of small perturbations and the use of gradient descent learning method is presented (known as HyGANN strategy). The scheme requires no knowledge about both the system's mathematical model and input-output training pairs which must be provided for supervised learning. By means of the proposed reinforcement learning algorithm and modified genetic algorithm, neural network controller whose weights are optimized could generate time series small perturbation signals to convert chaotic oscillations of chaotic systems into desired regular ones. The computer simulations on controlling Henon map and Logistic chaotic system have demonstrated the capacity of the presented strategy by suppressing lower periodic orbits such as period-1 and period-2. Meanwhile, the periodic control methodology is utilized, the higher periods such as period-4 can also be successfully directed to expected periodic orbits. Moreover, the approach need not know the nonlinear dynamics such as state dimensions and fixed points of chaotic system. Besides, it is reasonably robust to noise, thus, it may be extended to control other chaotic systems.Thirdly, an adaptive fuzzy neural networks (FNNs) controller for a class of uncertain nonlinear chaotic system is presented. Only small fuzzy rules ("IF-THEN"rule base) are selected,the FNNs may be applied to approximate the unknown chaotic system. Using a Lyapunov synthesis approach and the parameters projection algorithm, the free parameters of adaptive FNNs controller can be tuned on-line. Also, the supervisory controller is appended into the FNNs controller to force the system states to remain within constrains. Moreover the boundary pre-determined in the...