CMAC神经网络在潜艇操纵控制中的仿真应用

Simulation of submarine maneuvers using CMAC neural networks

基于MATLAB/Simulink软件包,利用拘束模型试验的水动力实验结果,开发了潜艇的六自由度操纵运动预报模型。其典型机动的仿真结果与自航模试验结果吻合较好。在此基础上,成功地将CMAC神经网络技术应用于潜艇操纵运动控制仿真中。仿真结果表明,神经网络控制比单独的PID时的控制效果优越,舵机操舵幅度明显减小,且具有较强的抗干扰能力,鲁棒性强等优点。

A simulation method of MATLAB/Simulink for model of submarine motion is introduced. And the coefficients of submarine＇s motion equation come from the capitive model expriment.The computed results of simulation agree well with the experimental results of the free manoeuvring submarine model.Based on it, the application of the CMAC neural network is successful in manoeuvring and controlling of submarines.The simulation results show that neural network controller is better than traditional PID controller.In addition, the swing of the rudder is decreased obviously. This system has the stable performance and good robustness.