小脑模型神经网络控制器在天线跟踪指向控制中的应用

分析了天线跟踪指向控制系统的特点和影响系统跟踪性能的主要因素,建立了系统数学模型。根据系统特点,给出了小脑模型神经网络控制器(CMAC)和PID相结合的复合自适应控制方法的设计过程,并分析了该算法适用于天线跟踪指向控制系统的优势。该方法利用传统的PID控制,结合CMAC神经网络算法的快速自学习、精确逼近的优点,既满足了天线跟踪指向控制系统快速实时跟踪的要求,又提高了跟踪精度和跟踪平稳性。仿真结果表明,该方法对摩擦力矩有很好的抑制作用,跟踪精度较单独采用PID控制提高一个数量级,且输出稳定,具有较强的鲁棒性。

Cerebellar model articulation controller (CMAC) for antenna pointing and tracking system

The characteristics and main factors of antenna pointing and tracking system for tracking performance are analyzed,and the mathematic model is establish for the system. According to the system characteristics,the design process of Cerebellar Model Articulation Controller ( CMAC) network combined with PID control method is described. The advantages of the proposed method are analyzed. This method uses the fast self-learning and precise approaching of CMAC networks as the feed-forward control to get the object model; then together with the traditional PID control method it can have the advantages of fast response,high precision and robustness. Simulation results show that the proposed control method can effectively inhibit friction torque and provide stable output and robustness. The tracking precision of the proposed control method is one order of magnitude higher than that of PID control method alone.