基于ANFIS神经网络的GPS/INS组合导航信息融合

GPS/INS Integrated Navigation Fusion Algorithm Based on ANFIS Neural Network

介绍了自适应神经网络模糊推理技术(ANFIS),在此基础上采取新息自适应调整的思想,设计了一种基于滤波器工作参数调整的GPS/INS组合导航神经网络辅助卡尔曼滤波器,利用神经网络的非线性,根据滤波器的实际输出在线实时动态调整滤波器参数,达到对滤波器的调整和控制。与传统卡尔曼滤波器进行计算机仿真比较表明,基于ANFIS神经网络的GPS/INS组合导航信息融合技术具有较强的自适应性,能够在复杂的环境下抑制数据的发散,提高导航精度。

Introduces Adaptive--Network--based Fuzzy Inference System, and based on this use a method of Innovation--Based adap- tive, design a GPS/INS integrated navigation neural network Kalman filter based on filter working parameters adjustment. Comparing the traditional Kalman filter, the simulation result show that the new algorithm prevent divergence effectively. The precision of navigation is im- proved.