基于RBF神经网络PID的无人动力伞控制

动力伞是一个复杂的非线性动力学对象,难以用精确的数学模型描述。对于这种具有非线性、时变和强耦合特性的综合系统,采用传统PID控制方法不能得到满意的控制效果,因此提出一种基于RBF神经网络的PID控制方法。该方法利用RBF神经网络的自学习、自适应能力自调整系统的控制参数,从而实现对PID控制器各参数的优化整定。在Mat-lab软件中的仿真结果表明,该方法可实现对动力伞有效的控制,并且与传统PID相比,具有更短的调节时间,更好的稳定性、自适应性和鲁棒性。

Unmanned Powered Parachute Aircraft Control Based on RBF Neural Network PID

Unmanned powered parachute aircraft is a complicated nonlinear dynamics object.It is difficult to describe by precise mathematical model.For the integrated system with nonlinear time-varying and strong coupling characters,since it cannot acquire the satisfied control result using the traditional PID control method,a self-turning PID control strategy based on RBF network is put forward in this paper.This method uses the ability of self-study and self-adaptability of RBF network to turn parameters of system,accordingly,realizes the setting of PID controller parameters.Simulation result in Matlab indicates that it can get satisfied control result,shorter adjusting time,better stability,better self-adaptability and robustness using this method.