基于岭回归的红外协同定位优化算法  

Optimization algorithm of infrared cooperative location based on ridge regression

作　　者：王俊迪 许蕴山[1] 彭芳[1] 肖冰松[1] WANG Jundi;XU Yunshan;PENG Fang;XIAO Bingsong(Aeronautics Engineering College,Air Force Engineering University,Xi’an 710038,China)

机构地区：[1]空军工程大学航空工程学院,西安710038

出　　处：《北京航空航天大学学报》2020年第3期563-570,共8页Journal of Beijing University of Aeronautics and Astronautics

基　　金：空军工程大学校长基金(XZJK2018003,XZJY2018013)。

摘　　要：针对双机协同定位误差较大问题,首先,在球坐标与直角坐标相结合的基础上,建立双机协同定位的数学模型,并通过对数学模型的分析得出双机距离较近时定位误差大的原因。其次,利用岭回归算法求解出定位精度较高的两组测量子集的目标位置估计值和定位误差协方差矩阵。最后,利用加权最小二乘算法对两组测量子集进行融合定位,推导出协同定位优化算法。仿真分析表明,该算法能显著改善了整个探测区域内的定位精度,并且在双机相距较近时也能保持高的定位精度。Aimed at the problem that the infrared sensor has a large error,in this paper,based on the combination of spherical coordinates and Cartesian coordinates,a mathematical model of cooperative location is established,and the reason for the large positioning error when the distance between the two machines is close is obtained by analyzing the mathematical model.Then,the ridge regression algorithm is used to solve the target position estimation value and the positioning error covariance matrix of the two sets of measurement subsets with higher positioning accuracy.Finally,the two sets of measurement subsets are fused and positioned by the weighted least squares algorithm to derive the cooperative location optimization algorithm.The simulation analysis shows that the proposed algorithm can significantly improve the positioning accuracy in the whole detection area,and can maintain high positioning accuracy when the two machines are close.

关 键 词：红外传感器 岭回归 协同定位 定位精度 最小二乘 

分 类 号：TN929.5[电子电信—通信与信息系统]