基于神经网络的联合智能滤波在导航系统中的应用

Intelligent Filter Based on Neural Networks for Integrated Navigation System

针对INS/GPS/CNS组合导航系统的特点,运用神经网络理论代替传统卡尔曼滤波器,利用INS/GPS、INS/CNS两个局部滤波器的输出值,通过综合滤波器进行线性最优估计,且进行了计算机仿真。仿真结果表明,该系统具有较高的导航精度,改善了系统的稳定性和容错性,而且与以往滤波器比较,系统的实时性、鲁棒性也有所改善。

According to the characteristic of INS/GPS/CNS Integrated Navigation System, the paper constructed the filter with neural networks theory, and did linear optimal estimation with two local filter＇s outputs. Simulation results show that the system can obtain higher accuracy, and has better performance of fault tolerant and stability. In addition that the performance of real time and robust are better than that of the former system.