| Summary: | 碩士 === 國立中央大學 === 電機工程研究所 === 100 === This thesis presents a wavelet fuzzy neural network (WFNN) intelligent controller to control the squirrel-cage induction generator (SCIG) system for grid-connected power application, and a hybrid intelligent controller to control the DC-link voltage of squirrel cage induction generator system.This system can detect the phase angle of the grid accurately and also provide a stable active power and reactive power to the grid at the testing conditions of the fixed speed and the variable speed of the wind. The field-oriented mechanism is implemented for the control of the SCIG system in this thesis. Moreover, the WFNN intelligent controller is proposed to improve the transient and steady-state responses of the SCIG system at different operating conditions. The on line trained WFNNs using backpropagation learning algorithm are implemented as the controllers for the DC-link voltage of the AC/DC power converter and the active power and reactive power outputs of the DC/AC power inverter. Furthermore, the network structure and the on line learning algorithm of the WFNN are introduced in detail. In addition, the control scheme and the analysis of stability of the hybrid intelligent controller are also introduced in this thesis. Additionally, some simulated results are given to verify the design of the SCIG system via PSIM. Finally, the feasibility of the proposed control scheme is verified through experimentation.
|
|---|
