Title :
A grid-connected current control technique of single-phase voltage source inverter based on BP neural network
Author :
Han, Gujing ; Xia, Yunhong ; Min, Wuzhi
Author_Institution :
Sch. of Electron. & Electr. Eng., Wuhan Textile Univ., Wuhan, China
Abstract :
Aiming at the output current of grid-connected inverter of LCL filter, this paper put forward a PR (Proportion Resonant) control technology based on BP (Back Propagation) neural network. Combining the traditional digital PID control technology and the novel PR control technology, an increment PR controller algorithm as well as its parameter self-tuning method based on BP neural network were proposed, Simulation experiment, confirmed that the output current of gird-connected inverter controlled by PR control technology based on BP neural network had better steady state adaptive ability and self-learning ability. Trained results turn out to be a good effect of control of grid-connected current.
Keywords :
adaptive control; backpropagation; electric current control; neurocontrollers; self-adjusting systems; three-term control; voltage control; LCL filter; back propagation neural network; digital PID control technology; grid connected current control; grid connected inverter; increment PR controller algorithm; parameter self-tuning method; proportion resonant control technology; self-learning ability; single phase voltage source inverter; steady state adaptive ability; Capacitors; Current control; Frequency control; Inverters; Neural networks; Pulse width modulation; Resonant frequency; BP Neural Network; PR controller; current control; grid-connected inverter;
Conference_Titel :
Computer Science and Automation Engineering (CSAE), 2012 IEEE International Conference on
Conference_Location :
Zhangjiajie
Print_ISBN :
978-1-4673-0088-9
DOI :
10.1109/CSAE.2012.6272657