一种改进的方差自适应滤波算法

An improved acceleration variance adaptive filtering algorithm

标准的基于"当前"统计模型的自适应卡尔曼滤波算法中机动频率和加速度极限值存在靠经验预先设定的问题,以及在跟踪非机动和弱机动目标时存在精度不高的问题,本文在分析已有的加速度方差自适应算法的基础上,提出了一种改进的加速度方差自适应算法。仿真结果表明本文提出的改进的加速度方差自适应算法是有效性的,较已有算法提高了跟踪非机动或弱机动目标的精度。

The standard adaptive Kalman filter algorithm based on the ＂current＂ statistical model exists the problem of selecting Maneuvering frequency and maximum acceleration based on experience, and the problem of low accuracy in tracking non-maneuvering or weak maneuvering target. By analyzing the existing acceleration variance self-adapting algorithm, an improved acceleration variance self-adapting （IAVS） algorithm is proposed. The contrasting simulation results have showed IAVS＇s validity. IAV algorithm also obtains a better tracking accuracy, especially for non-maneuvering or weak maneuvering target.