Novel approach for identifying Z-axis drift of RLG based on GA-SVR model  

作　　者：Guo Wei Xudong Yu Xingwu Long 

机构地区：[1]College of Optoelectric Science and Engineering,National University of Defense Technology

出　　处：《Journal of Systems Engineering and Electronics》2014年第1期115-121,共7页系统工程与电子技术（英文版）

摘　　要：This paper describes a novel approach for identifying the Z-axis drift of the ring laser gyroscope （RLG） based on ge-netic algorithm （GA） and support vector regression （SVR） in the single-axis rotation inertial navigation system （SRINS）. GA is used for selecting the optimal parameters of SVR. The latitude error and the temperature variation during the identification stage are adopted as inputs of GA-SVR. The navigation results show that the proposed GA-SVR model can reach an identification accuracy of 0.000 2 （？）/h for the Z-axis drift of RLG. Compared with the ra-dial basis function-neural network （RBF-NN） model, the GA-SVR model is more effective in identification of the Z-axis drift of RLG.This paper describes a novel approach for identifying the Z-axis drift of the ring laser gyroscope （RLG） based on ge-netic algorithm （GA） and support vector regression （SVR） in the single-axis rotation inertial navigation system （SRINS）. GA is used for selecting the optimal parameters of SVR. The latitude error and the temperature variation during the identification stage are adopted as inputs of GA-SVR. The navigation results show that the proposed GA-SVR model can reach an identification accuracy of 0.000 2 （？）/h for the Z-axis drift of RLG. Compared with the ra-dial basis function-neural network （RBF-NN） model, the GA-SVR model is more effective in identification of the Z-axis drift of RLG.

关 键 词：ring laser gyroscope （RLG） support vector regression （SVR） inertial navigation system （INS） genetic algo-rithm （GA） 

分 类 号：TN966[电子电信—信号与信息处理]