Study On Fuzzy Neural Excitation Contoller Of Turbine Genertor

Excitation controllers of turbine generators are very important and complex equipment of power system. With the larger and larger scale of power system, the problem that the traditional control theories of excitation controllers of turbine generator are not competent as before appears, however, the developing Intelligent Control (1C) theory supplies some solutions to this problem.At the beginning of this dissertation, the actuality and trend of the control scheme of excitation control system of turbine generator and 1C theory are stated. After briefly introducing Fuzzy Control (FC) and Neural Network Control (NNC) of 1C, the Combination of FC and NNC桭uzzy Neural Network Control (FNNC) is introduced, and a sort of FNNC桝NFIS, based on multiplayer forward neural network, is detailed. With excitation system of a turbine generator, some sample data is classified by two clustering methods, and some fuzzy membership functions and rules are obtained by analyzing the clustering centers. According to these functions and rules, a fuzzy neural excitation controller of turbine generator is designed using ANFIS. Then some parameters of the controller are modulated by hybrid learning algorithm of ladder descent (LD) and least square error (LSE) so as to attain better control precision. After modulation, the favorable dynamic control ability of the designed controller is proved by simulation. AT the end of the dissertation, some numerical simulations of the influence, which the designed controller brings about on single generator and infinite power system, are performed by MATLAB. The results suggest that ANFIS excitation system could greatly improve the static stability extreme of the system, offer effective damp when the system suffers from big and small disturbs, and could improve the static and transient stability of the system remarkably.