摘要
电主轴感应电动机伺服系统要求有良好的动静态性能。按转子磁场定向的感应电动机矢量控制中转速PI调节器在控制对象参数和工作环境变化时其性能较差。为了改善电主轴伺服系统的性能,提出了用单神经元自适应PID控制器代替传统PI调节器。为了提高单神经元PID控制器的学习能力,将无监督的Hebb学习规则与有监督的Delta学习规则相结合,实现单神经元控制器的参数优化与在线自调。仿真和实验结果表明,伺服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抗扰性。伺服系统可用于航空航天、智能机器人和数控机床等高性能控制系统当中。
Good static and dynamic performance is required in spindle motor servo system. It was ai- ming to the less robust performance for the speed PI regulator in the rotor flux field oriented vector control system with changing parameters and aiming to improving the performance of vector control system, but single neuron had the abilities of self-learning and adaptiving, so it was presented that single neuron adaptive PID controller substitutes the speed PI controller. In order to enhance the self-study ability of single neuron PID controller, the supervisory Delta study rule was combined with non-supervisory Hebb study rule, which realized parameter optimization and self-tuning on line for single neuron controller. The vector control system based on the single neuron adaptive PID controller was structured. Simulation and experiment results showed that the system is not only had good static and dynamic performance, but also had strong self-adaptability and resisting disturb. The spindle motor servo system can be used in CNC and robot system.
出处
《微电机》
北大核心
2009年第4期52-55,共4页
Micromotors
基金
湖南省教育厅科研基金项目(07C674)
