基于遗忘因子多新息随机梯度算法PMSM参数辨识  

Parameter Identification for PMSM Based on Forgetting Factor Multi-Innovation Stochastic Gradient Identification Algorithm

作　　者：张建宇[1] 吴定会[1] 

机构地区：[1]江南大学轻工过程先进控制教育部重点实验室,无锡214122

出　　处：《微特电机》2016年第11期66-69,共4页Small & Special Electrical Machines

基　　金：国家高技术研究发展计划项目(2013AA040405);江苏省食品先进制造装备技术重点实验室项目(FM-201408);江苏省"六大人才高峰"项目(WLW-008)

摘　　要：针对传统辨识算法结果不精确以及电机参数变化问题,提出了基于遗忘因子多新息随机梯度辨识算法。结合永磁同步电机系统电压方程,构建离散辨识模型。采用矢量控制方法控制电机,获得辨识模型输入输出数据,对转子电阻和电感参数进行在线辨识。仿真结果表明,该算法能够实现对永磁同步电机参数的辨识。In view of the problem that the results of traditional identification algorithm are not accurate and parameters variation of motor, a new algorithm based on the forgetting factor multi-innovation stochastic gradient identification algo- rithm is proposed. Combined with permanent magnet synchronous motor （PMSM） system voltage equation, a discrete iden- tification model is constructed. By using vector control method, the input and output data of the identification model are ob- tained to identify the rotor resistance and inductance. The simulation results show that this identification algorithm can ob- tain the accurate parameters of the PMSM model.

关 键 词：永磁同步电机 SVPWM矢量控制 遗忘因子 多新息随机梯度算法 参数辨识 

分 类 号：TM351[电气工程—电机] TM341