摘要
当永磁同步电机采用有限集模型预测控制时,虽动态性能优异,但存在稳态性能差、计算量大的问题。针对上述问题本文提出了一种基于龙伯格观测器的模型预测控制策略。首先,通过分析传统模型预测控制中占空比控制策略的次优电压矢量所在扇区的分布规律,构造新的电压矢量选择表降低了次优电压矢量的计算次数。此外,针对传统机械传感器的一系列弊端,设计了一种龙伯格观测器计算电机的反电动势,再由锁相环估计永磁同步电机转速和转子位置信息。最后,通过搭建实验平台,与传统有限集模型预测控制进行实验对比分析,实验结果表明本文所提控制策略具有更好的稳态性能和控制精度。
When a permanent magnet synchronous motor is dynamically controlled by a finite set model prediction,although the dynamic performance is excellent,there are problems of poor steady state performance and high computational effort.This paper develops a two vector based model predictive current control strategy depend on the Luenberger observer to solve the above mentioned problem.Firstly,a new voltage vector selection table is constructed by using the conventional duty cycle model to predict the variation law of the sector where the sub-optimal voltage vector for current control is located,and reduces the number of calculations of sub-optimal voltage vectors from six to two.In addition,Luenberger observer is designed to estimate the motor's counter-electromotive force,the phase-locked loop is used to precisely estimate the position and speed information of the rotor of the permanent magnet synchronous motor,effectively solving some of the drawbacks brought about by mechanical sensors.Finally,the experimental platform is set up and compared with the conventional limited set model predictive control.The experimental results show that the control strategy proposed has better steady state performance and control accuracy.
作者
王秀平
蔡旭
曲春雨
董志鹏
李岩
WANG Xiuping;CAI Xu;QU Chunyu;DONG Zhipeng;LI Yan(College of Electric Power,Shenyang Institute of Engineering,Shenyang 110136,China;State Grid Liaoyang Power Supply Company,Liaoyang 111000,China)
出处
《辽宁工程技术大学学报（自然科学版）》
CAS
北大核心
2024年第4期486-493,共8页
Journal of Liaoning Technical University (Natural Science)
基金
辽宁省教育厅科研项目(LJKZ1085)
沈阳市科技计划项目(22-322-3-23)。
关键词
永磁同步电机
双矢量
模型预测控制
龙伯格观测器
无位置传感器
锁相环
permanent magnet synchronous motor
double vector
model predictive control
Luenberger observer
no position sensor
phase-locked loop
