Issue |
JNWPU
Volume 41, Number 6, Decembre 2023
|
|
---|---|---|
Page(s) | 1054 - 1063 | |
DOI | https://doi.org/10.1051/jnwpu/20234161054 | |
Published online | 26 February 2024 |
Threat assessment for air-to-ground combat of UAVs using improved Bayesian networks
基于贝叶斯网络的无人机对地作战威胁评估
1
School of Aeronautics, Northwestern Polytechnical University, Xi'an 710072, China
2
AVIC the First Aircraft Institute, Xi'an 710089, China
Received:
2
February
2023
Aiming at the problems of information uncertainty and real-time faced by ground threat assessment during UAV air-to-ground combat, the limitations of existing threat assessment methods are analyzed, and a new threat assessment method based on improved Bayesian network is proposed in this paper. In this method, a hybrid-driven approach of threat data and expert knowledge is used to improve the rationality of threat assessment model, and a layered threat assessment architecture is constructed. Threat levels are classified based on the relationship between carrier aircraft and threat envelope, threat radiation, etc. In order to improve the rationality of the ground threat assessment model, a calculation model of ground threat intervisibility probability is established, and the intervisibility probability is taken as the input of Bayesian network threat assessment model. Simulation results show that the model has less computation and good real-time performance, and the introduction of threat intervisibility probability improves the rationality of ground threat assessment.
摘要
针对无人机对地作战过程中地面威胁评估面临的信息不确定性和实时性等问题, 分析了现有威胁评估方法的局限性, 提出了一种基于改进贝叶斯网络的威胁评估方法, 采用威胁数据与专家知识混合驱动的方法提高威胁评估模型的合理性。构建了分层威胁评估架构, 基于载机与威胁包线的关系、威胁辐射等划分威胁等级。建立了地面威胁通视概率计算模型, 并将通视概率作为贝叶斯网络威胁评估模型的输入。仿真结果表明, 该模型计算量小, 算法实时性好, 引入威胁通视概率提高了地面威胁评估的合理性。
Key words: air to ground combat / threat assessment / intervisibility / Bayesian networks / parameter learning
关键字 : 对地攻击 / 威胁评估 / 通视性 / 贝叶斯网络 / 参数学习
© 2023 Journal of Northwestern Polytechnical University. All rights reserved.
This is an Open Access article distributed under the terms of the Creative Commons Attribution License (https://creativecommons.org/licenses/by/4.0), which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Current usage metrics show cumulative count of Article Views (full-text article views including HTML views, PDF and ePub downloads, according to the available data) and Abstracts Views on Vision4Press platform.
Data correspond to usage on the plateform after 2015. The current usage metrics is available 48-96 hours after online publication and is updated daily on week days.
Initial download of the metrics may take a while.