基于不敏Kalman滤波的多传感器数据融合算法  

A Novel Multi-sensor Data Fusion Algorithm Based on Unscented Kalman Filter

作　　者：尚晓星[1] 李俊霞[2] 

机构地区：[1]焦作师范高等专科学校物理系,河南焦作454001 [2]河南理工大学计算机科学与技术学院,河南焦作454000

出　　处：《河南师范大学学报（自然科学版）》2011年第4期66-69,共4页Journal of Henan Normal University(Natural Science Edition)

摘　　要：针对非线性系统状态估计的有效融合问题,给出了一种基于不敏Kalman滤波的多传感器数据融合算法.首先,依据单传感器的量测利用不敏Kalman滤波器得到局部状态估计值;其次,依据模糊集合理论中隶属度的性质构建反映局部状态估计结果的支持度函数和支持度矩阵,进而实现对于各局部状态估计之间蕴含冗余和互补信息的充分提取;最终,通过对支持度矩阵的求解完成对于权重的合理选择.蒙特卡罗仿真验证了算法的有效性.For the effective fusion of nonlinear system state estimation, a novel multi-sensor data fusion algorithm based on unscented Kalman filter is given. Firstly, unscented Kalman filter is used to estimate local state estimation value of nonlinear system by single sensor measurement data. Then, according to the principle of the membership degree in fuzzy set theory, sup- port degree function and support degree matrix are constructed, so that the complementary and redundancy information among local state estimation value can be fully used. Finally, the reasonable choice of weight is realized by means of calculating con- sensus matrix. The Monte Carlo simulation results verify the effectiveness of the method proposed.

关 键 词：数据融合 非线性滤波 支持度函数 支持度矩阵 不敏卡尔曼滤波 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]