【作者】 王卫红； 于镭；

【Author】 WANG Wei-hong1, YU Lei2 (1.Automatic Control Department, Beijing University of Aeronautics and Astronautics, Beijing 100083, China; 2.Automation Institute, Qingdao University of Science and Technology, Qingdao 266053, China)

【机构】 北京航空航天大学自动控制系； 青岛科技大学自动化学院；

【摘要】 提出一种基于RBF辨识的伺服系统CMAC复合控制器,并进行了仿真研究。采用RBF神经网络辨识被控对象模型,根据辨识结果调节单神经元控制器的参数,由单神经元PID控制器与小脑模型前馈控制器组成复合控制结构,通过搜索使控制器尽快地进入合适的参数空间,实现了控制的快速性要求。仿真结果表明,该控制方法能够缩短系统暂态响应时间,提高系统的动态跟踪精度,增加系统鲁棒稳定性。更多还原

【Abstract】 A kind of CMAC controller for servo system based on RBF identifier was proposed. The controller consists of the RBF identifier, the single neuron PID controller and the CMAC feedforward controller. The RBF neural network is used to identify the model of the plant and adjust the single neuron PID controller’s parameter. The suitable parameter of the controller is given as fast as possible by used searching. This method could shorten transient response time clearly. The simulation experiment proves the method can improve control precision and the response rapidness.更多还原