Doubly Fed Induction Generator Control Using Artificial Neural Network for Wind Generation System

Due to the electricity demand and environmental concerns, alternative clean forms of energy have been widely researched in recent years, in which wind energy is in evidence. To convert the mechanical energy generated by the wind turbines, the wind generation system needs generators. The doubly fed induction generator is the most commonly used due to its high energy transfer efficiency, reliability, and low maintenance cost. The control of DFIG parameters is crucial to the dynamic performance of the wind generation system. This thesis aims to develop an artificial neural network (ANN) controller for the doubly fed induction generator in wind generation system. It was proposed a data acquisition method using the system outcome with the conventional PI controller in order to train and test the ANN controller. The ANN controller was then designed and implemented in the system to control the machine speed, DC link voltage, and dq rotor and stator currents. In order to simulate the complete wind generation system, the models of DFIG, wind turbine, and converter were developed. The simulation results via Matlab Simulink indicate that it is possible to control the DFIG using an ANN controller. The results also show that the proposed ANN controller outperformed the conventional PI controller performances during the transient response, decreasing the overshoot for both machine speed and DC link voltage control. Outcomes found in this thesis combined with future works could potentially incentive the use of ANN for control purposes in wind generation systems. Furthermore, this research provides a guide on how to collect data for the training and testing of ANN controller for this kind of system.

Name thesis:degree_name

Master of Applied Science (MASc)

Level thesis:degree_level

Master's

Discipline thesis:degree_discipline

Engineering - Industrial Systems

Grantor dc:publisher

Faculty of Graduate Studies and Research, University of Regina

Year dc:date.issued

2021

Author dc:creator

• Silva de Siqueira, Luanna Maria

Advisor dc:contributor.advisor

• Peng, Wei

Committee members dc:contributor.committeemember

• Mayorga, Rene
• Dai, Liming
• Wu, Peng

Language dc:language.iso

en

DOI

https://doi.org/10.82465/4146

OAI identifier oai:identifier

oai:uregina.scholaris.ca:10294/14984