摘要
构造了一个两层的神经网络系统辨识器(NNPI),自适应地在线辨识出系统的集中不确定量,并应用辨识出来的集中不确定量在线调整速度控制器的输出量。仿真实验表明,与常规的控制器相比,本文设计的速度控制方案能取得优良的控制性能,且在负载转矩和电机内部参数变化的情况下有很强的鲁棒性。
This paper proposes a speed control scheme of Induction Motor based on Neural-Network Identifier. The Neural-Network Plant Identifier(NNPI) is constructed via a two-layer Neural-Network. NNPI is used to provide a real time and adaptive identification of the lumped uncertainty which is used to adjust the output of the speed controller adaptively, Computer simulations demonstrate that the proposed scheme can obtain satisfied performances and a robust control compared to the conventional controller.
出处
《电机与控制应用》
北大核心
2005年第9期41-44,共4页
Electric machines & control application
基金
广东省自然科学基金资助项目(020118)