三相高功率因数整流器的神经网络内模控制

摘要

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.%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.