Active Power Filter based on PIDNN controller

Author

Dong, Weijie ; Bai, Xiaomin ; Zhu, Ninghui ; Wang, Haiying

Author_Institution

China Electr. Power Res. Inst., Beijing, China

fYear

2012

fDate

21-24 May 2012

Firstpage

1

Lastpage

4

Abstract

Because of the limitation of PI controller in Shunt Active Power Filter (APF), this paper proposes to apply PID neural network (PIDNN) into APF control loop as to improve the dynamic characteristics. The model of APF which can filter the silicon controlled rectifier load current is built in MATLAB/SIMULINK. Simulation results show that the adoption of PIDNN controller can achieve the same effect as PI controller, while PIDNN can resolve the problem that the PI controller parameters are difficult to be adjusted.

Keywords

active filters; neurocontrollers; power filters; rectifiers; three-term control; APF control loop; PI controller parameters; PIDNN controller; proportion integral differential neural network control; shunt active power filter; silicon controlled rectifier load current; Active filters; Mathematical model; Neural networks; Space vector pulse width modulation; Switches; Vectors; Voltage control; Active Power Filter (APF); PID neural network (PIDNN); voltage space vector (SVPWM);

fLanguage

English

Publisher

ieee

Conference_Titel

Innovative Smart Grid Technologies - Asia (ISGT Asia), 2012 IEEE

Conference_Location

Tianjin

Print_ISBN

978-1-4673-1221-9

Type

conf

DOI

10.1109/ISGT-Asia.2012.6303343

Filename

6303343