稳态条件高斯推理在电磁态势估计中的应用

Stable to Electronic Warfare Situation Assessment Application of Conditional Gaussian Inference

根据电磁态势估计原理,建立含连续结点和离散结点的混合贝叶斯网络模型,对一级融合的输出数据进行二级处理,估计干扰前后单架飞机对单个保护目标的威胁的变化情况。针对传统的连接树推理算法的不足,提出稳态条件高斯推理算法。新算法不仅能实现数值稳定性,还能根据高斯混合模型精确计算查询结点的边缘概率密度。仿真实验表明,稳态条件高斯推理是解决电磁态势估计问题的一种有效方法,且威胁估计的精度高。

In this paper we present a mixed Bayes net based electronic warfare situation assessment algorithm from a tracking and data fusion module.The threat posed by a given intruder on a specified asset is evaluated under no-jamming condition and jamming condition.The stable conditional Gaussian inference scheme is developed to remedy the numerical instability.In addition to the means and variances provided by the previous algorithm,the new propagation scheme yields full local marginal distributions.The experiments indicate that the scheme is practicable and effective.