一种基于RBF神经网络的雷达稳定转台复合控制方法

A compound control method of radar stabilized turntable based on RBF neural network

舰载雷达稳定转台伺服控制系统受舰船姿态角变化的影响会呈现出明显的非线性和时变不确定性。在保证控制精度及系统平稳性方面,传统的PID控制算法对PID参数细分整定繁琐且难以得到完全理想的控制效果。对此提出了采用RBF神经网络和传统PID相结合的控制方法,利用RBF神经网络自学习能力对PID控制参数进行在线整定。将该方法应用于某两轴稳定雷达转台控制系统进行仿真验证,结果表明能取得很好的控制效果。

The servo control system of the shipborne radar stabilized turntable will show obvious non- linearity and time-varying uncertainty due to the change of the attitude angle of the ship. In terms of ensuring control accuracy and system stability, the conventional PID control algorithm is cumbersome for subdivision of the PID parameters and it is difficult to obtain a completely ideal con- trol effect. In this regard, a control method combining the RBF neural network and the conventional PID is proposed. The self-learning ability of the RBF neural network is used to adjust the PID control parameters online. The method is applied to a two-axis stabilized turntable control system for simula- tion and verification. The results show that good control effect can be achieved.