摘要
由递归神经网络构成综合负载转矩观测器 ,从而把综合负载转矩视为可测干扰 ,并利用极点配置自校正前馈控制策略实现了永磁同步电机的速度控制 ,解决了永磁同步电机系统中参数变化和负载扰动等不确定性问题。
A neural-network-based synthetical load torque observer is designed, and the synthetical load torque is considered as measurable disturbance. A pole placement self-tuning feedforward control of PM synchronous motor (PMSM) is implemented.The uncertainties of parameter variations and load disturbances for PM synchronous motor drive system are overcome. The simulation results show that the proposed control scheme has stronger robustness.
出处
《控制与决策》
EI
CSCD
北大核心
2001年第B11期681-684,共4页
Control and Decision
基金
辽宁省自然科学基金项目 (0 0 2 0 11)
关键词
极点配置
自校正前馈控制
递归神经网络
永磁同步电机
负载转矩
观测器
pole placement self-tuning feedforward control
recurrent neural networks
PM synchronous motor
load torque observer
