GPS失锁时基于神经网络预测的MEMS-SINS误差反馈校正方法研究  

Adaptive Neural Network Prediction Feedback for MEMS-SINS During GPS Outage

作　　者：曹娟娟[1] 房建成[1] 盛蔚[1] 白焕旭[2] 

机构地区：[1]新型惯性仪表与导航系统技术国防重点学科实验室,北京航空航天大学仪器科学与光电工程学院,北京100191 [2]北京航天发射技术研究所,北京100076

出　　处：《宇航学报》2009年第6期2231-2236,2264,共7页Journal of Astronautics

基　　金：国家自然科学基金重点项目(60736025);国防基础科研重大项目(D2120060013)

摘　　要：GPS信号失锁时,MEMS-SINS组合GPS导航误差会随着时间迅速积聚而无法导航。提出一种基于RBF神经网络预测的MEMS-SINS误差反馈校正方法,GPS有信号时对神经网络进行训练,GPS信号中断时用训练好的RBF神经网络预测MEMS-SINS的导航误差。地面车载跑车试验,证实了训练后的RBF神经网络能很高精度地逼近MEMS-SINS/GPS组合导航系统输入与输出间的关系,在4个50s以内的GPS人为失锁过程中,该方法导航结果与参考系统比较,平均位置误差为3.8m,平均速度误差为0.6m/s,平均姿态误差为0.5°。The overall performance of standalone MEMS-SINS is dramatically degraded during GPS signal outages due to the highly nonlinear drift of the inertial sensors＇ measurements. A method of RBFoANN prediction feedback for MEMS-SINS during GPS outage is presented in this paper. The RBF-ANN module is then trained to predict the MEMS-SINS error during GPS avail- ability and provide accurate navigation data of the moving platform during GPS outage. The car test results indicate that the proposed adaptive neural network prediction feedback can efficiendy provide corrections to the standalone MEMS-SINS predicted navigation error. During the car experiment, a total of 4 outages were intentionally introduced with intervals of less than 50 seconds. The average position errors are 3.8 m, average velocity errors are 0.6m/s and average attitude angle errors are 0.5° during GPS signal outages.

关 键 词：捷联惯性导航系统 组合导航 微机电系统 卫星定位系统 神经网络 

分 类 号：V249.32[航空宇航科学与技术—飞行器设计]