基于递归模糊小波神经网络的INS-GNSS组合导航算法  

INS-GNSS integrated navigation algorithm based on recurrent fuzzy wavelet neural network

作　　者：于仁海[1] 曹春燕 张闯[1] 房美含 YU Renhai;CAO Chunyan;ZHANG Chuang;FANG Meihan(Navigation College,Dalian Maritime University,Dalian 116026,Liaoning,China)

机构地区：[1]大连海事大学航海学院,辽宁大连116026

出　　处：《上海海事大学学报》2021年第2期8-14,共7页Journal of Shanghai Maritime University

基　　金：国家自然科学基金(51939001,61976033);大连市重点学科重大课题科技创新基金(2018J11CY022)。

摘　　要：为提高惯性导航系统(inertial navigation system,INS)与全球卫星导航系统(global navigation satellite system,GNSS)相结合的组合导航系统在GNSS中断期间的精度,提出一种基于递归模糊小波神经网络(recurrent fuzzy wavelet neural network,RFWNN)的启发式神经网络结构,用于INS的速度和位置误差补偿。在GNSS正常工作时,利用INS-GNSS数据将RFWNN训练成一个高精度的预测模型;在GNSS中断期间,利用被训练好的RFWNN模型补偿INS的速度和位置误差。为对所提出的RFWNN辅助INS-GNSS的性能进行评估,进行实船试验,结果表明利用RFWNN能够有效地对GNSS中断时的速度和位置信息进行高精度修正。To improve the precision of the integrated navigation system that combines the inertial navigation system(INS)and the global navigation satellite system(GNSS)during GNSS interruption,a heuristic neural network structure based on the recurrent fuzzy wavelet neural network(RFWNN)is proposed to compensate the speed and position errors of INS.The RFWNN is trained into a high-accuracy prediction model by the INS-GNSS data when GNSS works normally,and the speed and position errors of INS are compensated by the trained RFWNN during GNSS interruption.To evaluate the performance of the proposed RFWNN in INS-GNSS integrated navigation,the real ship tests were executed,and the results show that RFWNN can effectively correct the speed and position information during GNSS interruption.

关 键 词：惯性导航系统(INS) 全球卫星导航系统(GNSS) 递归模糊小波神经网络(RFWNN) 

分 类 号：U666.11[交通运输工程—船舶及航道工程]