基于BN的无人机气象威胁度建模和评估方法研究  

Weather Threat Modeling and Assessment for UAV Based on BN

作　　者：朱国涛[1,2] 周树道[1] 叶松[1] 王彦杰[1] 吴家瑜[1,3] 

机构地区：[1]解放军理工大学气象学院 [2]94195部队 [3]94755部队

出　　处：《计算机测量与控制》2011年第9期2200-2202,2209,共4页Computer Measurement &Control

基　　金：国家自然科学基金(40976062)

摘　　要：在军事和非军事领域,气象威胁与火力威胁一样,严重影响无人机的飞行安全;在进行航迹规划时,气象威胁不容忽视;重点讨论了气象要素对无人机安全飞行的影响,分析总结出八种对飞行安全有严重影响的气象相关因子并进行了量化;应用贝叶斯网络推理方法进行了气象威胁度建模,给出比较直观的层次因果关系,对气象胁度进行了分析评估;仿真结果表明,该评估方法具有较好的效用,能更准确地反映实际的气象威胁度等级。Weather threat like firepowers affects flight of UAVs both in military areas and unmilitary areas seriously. So the weather threat must be paid more attention when route planning. The weather elements are focused in this paper, and eight weather related factors are given and quantified which affect flight of UAVs seriously. The inference method based on Bayesian Networks （BN） is applied to model for weather threat about these eight weather related factors, and hierarchy causality is given directly, then weather threat level is assessed based on the weather threat model. Simulation results show that the modeling and assessment method for weather threat, which is able to re- flect real weather threat level exactly, is effective for actual route planning.

关 键 词：气象 威胁评估 贝叶斯网络 航迹规划 无人机 

分 类 号：TP391.9[自动化与计算机技术—计算机应用技术] TP18[自动化与计算机技术—计算机科学与技术]