摘要
针对转子磁场定向矢量控制中转速PI调节器鲁棒性能较差的问题,提出了用单神经元自适应PID控制器代替转速PI控制器,进一步改善了异步电动机矢量控制系统的性能；将无监督的Hebb学习规则与有监督的Delta学习规則相结合,提高了单神经元自适应PID控制器的学习能力,实现了单神经元控制器的参数优化与在线自调。构造了基于单神经元自适应PID控制器和空间矢量脉宽调制(SVPWM)的异步电机矢量控制系统。仿真实验结果表明,该系统不仅具有很好的静、动态性能,而且又具有很强的自适应性和鲁棒性。
Aiming at the less robust performance for the speed PI regulator in the Rotor Flux Field Oriented Vector Control System, it is presented that single neuron adaptive PID controller substitutes the speed PI controller, which further improves the performance of asynchronous motor vector control system. The supervisory Delta study rule is combined with non-supervisory Hebb study rule, which enhances the selfstudy ability of single neuron PID controller and realizes parameter optimization and self-tuning on line for single neuron controller. The asynchronous motor vector control system based on the single neuron adaptive PID controller and Space Vector Pulse Width Modulation （SVPWM） is structured. Results of simulation show that the system not only has good static and dynamic performance but also has strong self-adaptability and robustness.
出处
《电机与控制学报》
EI
CSCD
北大核心
2007年第2期130-133,137,共5页
Electric Machines and Control
