Rotor Speed Identification of Doubly-Fed Generator System Based on Neural Network

摘要

According to the mathematic model of doubly-fed induction generator, the adjustable model and reference model based on MRAS are found. The adjustable model of model reference adaptive system based on neural network is derived by backward differentiation method and the algorithm for magnetic flux linkage is determined using two-layer neural network . Besides, the speed identification of doubly-fed induction generator is obtained by training of two-layer neural network using error back propagation. Finally, the simulation results show that compared with the speed identification of model reference adaptive system, the rotor speed can be reflected actually, and the speed estimation precision is effectively improved when neural network speed estimator is applied.