基于SVD的机动目标自适应滤波研究与仿真

由于计算误差等因素的影响,致使滤波协方差阵不对称或负定,从而导致滤波器发散,影响滤波算法的收敛速度和稳定性.该研究在机动加速度"当前"统计自适应卡尔曼滤波算法的基础上,引入了基于奇异值分解(SVD)的协方差平方根滤波的自适应卡尔曼滤波算法.仿真结果表明,该算法可以较好地跟踪机动目标,具有精度高、稳定好、收敛快等特点.

Simulation and study of the maneuvering target adaptive filtering algorithm based on SVD

The convergence rate and stability of the filter is influenced and its divergence exists, because the filtering covariance matrix becomes nonsymmetrical or negative elements appear in the filtering covariance matrix . on the basis of current statistical adaptive filtering algorithm of maneuvering acceleration, the adaptive Kalman filtering algorithm based on singular value decomposition(SVD) is presented. The simulation results show that the adaptive Kalman filtering algorithm can track the maneuvering target, and it is characterized by high accuracy, good stability and quick convergence.