一种寻优的BP神经网络飞行轨迹实时跟踪算法

Real-time Flight Trajectory Tracking Algorithm Using Optimized Back-propagated Neural Network

实时跟踪飞行轨迹可以有效地观测偏离预定航迹的程度,为位姿修正提供了参考。提出了一种寻优的BP神经网略实时跟踪飞机飞行轨迹,基于误差平方和最小化原则确定最优的隐层神经元个数。不同的飞行状态对应不同的位姿、速度等数据,飞行数据和飞行条件可以通过神经网络的权值和阈值来表征。通过仿真结果可以看出,设计的寻优BP神经网络具有可靠、准确及快速跟踪等优点。

Real-time following flight trajectory can effectively observe extent of predicted flight path departure and supply position-altitude correct reference. Optimized Back Propagate（BP） neural network is introduced for real-time tracking flight trajectory,hidden neurons are determined based on minimum of mean square error. Different state of flight corresponding different position,altitude and velocity. The relation between flight data and flight conditions can be displayed with threshold and weight of BP neural network. The results of simulation show that the BP neural network is a reliable,accurate and fast tracking methodology.