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

摘要

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 RBF-ANN 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 prop-esed adaptive neural network prediction feedback can efficiently provide corrections to the standalone MEMS-SINS predicted navi-gation 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.%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°.