Neural Network FOPID Power Control for Grid-tied Wind Energy Conversion Systems

• Main Authors: Wei-Jei Hong, 洪偉傑
• Other Authors: Chian-Song Chiu
• Format: Others
• Language: en_US
• Published: 2014
• Online Access: http://ndltd.ncl.edu.tw/handle/19111405293438678775

碩士 === 中原大學 === 電機工程研究所 === 102 === The main purpose of thesis is to design a grid-tied wind power generating system with maximum power point tracking (MPPT) performance. To transfer the wind power to electric power access the utility grid, a two-stage power converters containing a z-source converter and a full-bridge DC/AC inverter are applied on the wind power generating system. In order to achieve high efficiency and to stabilize output power, we design a neural network based fractional-order PID (FOPID) for the output current tracking of the DC/AC inverter. The neural network based fractional order PID controller can adjust the control parameter by itself for different environment. The numerical simulation and experimental results can show the response of the NN-FOPID controller is better than PI controller. Therefore, fast convergence of the MPPT can be assured even if the wind speed is rapidly varying.