三相高功率因数整流器的神经网络内模控制  

The control method of three-phase high-factor rectifier based on neural network internal model theory

作　　者：郜克存[1,2] 戴瑜兴[1] 杨金辉[1] 蒋近[1] 

机构地区：[1]湖南大学电气与信息工程学院,湖南长沙410082 [2]青岛创统集团,山东青岛266101

出　　处：《电机与控制学报》2012年第2期44-49,共6页Electric Machines and Control

基　　金：国家科技重大专项(2009ZX02011-02);住房和城乡建设部科技项目

摘　　要：针对三相高功率因数整流器采用常规PID控制效果差的问题,利用坐标变换,提出一种基于神经网络内模原理的整流器电流波形控制方案。用神经网络预估器作为整流器的内部模型,用神经网络辨识预估整流器正模型及其逆模型,在线修正、补偿内部模型与被控整流器之间的模型失配。分析结果表明,在该方案控制下系统稳压精确度高,有较快的动态响应,网侧电流谐波畸变率小。实验结果验证了该方法的可行性和有效性。Aiming at the problem of proportion integration differentitation（PID） control for three-phase high-factor rectifier,according to the characteristic of three-phase rectifier based on coordinate transformation,a control scheme of rectifier current output waveform based on neural network internal model theory was presented.The control scheme took a neural network estimate model as the internal model of three-phase rectifier to estimate the actual output waveform.As a result,highly accurate steady output,fast response and less distorted waveform is gained.The simulation and experiment verify the scheme can work well.

关 键 词：三相高功率因数整流器 电流波形 内模控制 神经网络 

分 类 号：TM921.5[电气工程—电力电子与电力传动]