Excitation System Control Based On Ann And ADRC

Excitation controller, as a main part of excitation system in the synchronic generator, affects the safe and steady operation of generators and power system. With its scale become larger and larger and the structure and run mode are increasingly complication, the power system requires the excitation system has better operation performance, higher reliability, better economical efficiency and flexibleness.Through the unknown perturbation and uncertain estimation of the system, and feedback the estimation to the control system, the active disturbance rejection controller thus realizes the dynamic feedback linearization of the dynamic systems. Because the ADRC theory is unique, and the method is simple, it is very suited to the non-linear an uncertain excitation system of the hydroelectric power sets.This paper analysis the ADRC standard form of single machine-infinite bus system based on the fifth-order hydroelectric generator model, furthermore design the excitation system, and then through simulation confirm the theory to be correct and effective, thus provide theoretical sustain to the reliable excitation control policy under strong nonlinear and uncertain disturbance conditions.This paper combines the artificial neural network and ADRC based on the characteristic of ADRC and ESO and compensate some changes of target to lighten the burden of ESO , thus get a stronger controller. The simulation results show that ADRC which base on ANN is efficacious when applied to excitation system whose parameters change largely and quickly.