Title :
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
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);
Conference_Titel :
Innovative Smart Grid Technologies - Asia (ISGT Asia), 2012 IEEE
Conference_Location :
Tianjin
Print_ISBN :
978-1-4673-1221-9
DOI :
10.1109/ISGT-Asia.2012.6303343
