基于自结构动态递归模糊神经网络的无人机姿态控制

Motion control for unmanned aircraft vehicle based on self-structuring recurrent fuzzy neural network

针对无人机非线性、强耦合等特点,提出了基于该自结构动态递归模糊神经网络的姿态控制系统,给出了基于Lyapunov函数的系统稳定性证明。对四层模糊神经网络进行了优化和改进,设计了自结构动态递归模糊神经网络,该网络可以根据系统状态在线更新权值、创建/删除节点、优化网络结构。仿真表明:该控制方法的突出优点是,在兼顾考虑了系统中的不确定性因素、非线性因素及外部干扰并存的情况下,保证系统的稳定性和跟踪性能;同时此网络结构比固定结构的模糊神经网络响应速度快,因此更具优越性。

This paper designed motion control system of micro aircraft vehicle based on self-organizing dynamic recurrent fuzzy neural network,and proved the stability of the motion control system based on Lyapunov function.It proposed a new self-organizing dynamic recurrent fuzzy neural network based on the fuzzy neural networks with four layers,the weights and nodes of the proposed network could be updated online for network structure optimization.Simulation results demonstrate that the proposed control scheme can effectively improve stability and tracking performance with strong uncertainty,nonlinear and extern disturbance.Compared with fixed structured fuzzy neural network,the proposed self-organizing dynamic recurrent fuzzy neural network has advantages in estimation speed.