摘要
针对电磁环境越来越复杂的问题,提出了一种基于前馈BP神经网络算法的电磁环境复杂度评估方法。首先建立了靶场电磁环境模型,分析了电磁环境复杂度的评估指标,为定量评估提供理论依据;然后分析了BP神经网络关键参数的选取方法,通过靶场实例验证了神经网络的功能;最后将新方法与传统评估方法进行了对比研究。结果表明了新方法优于传统方法,能够实时、快速、自适应地实现电磁环境的定性和定量分级,拓展了传统方法的应用范围,对研究真实的战场电磁环境问题具有实用价值。
The electromagnetic environment has become increasingly complex. In order to evaluate the complexity properly, a new method based on Back Propagation （BP） neural network is proposed. Firstly, the paper establishes range electromagnetic environment model, analyses the electromagnetic environment complexity evaluation index, in order to provide theoretical basis for quantitative evalua- tion. Secondly, we analyze the selection method of key parameters of BP neural network, and an exam- ple is used to verify the n^ural network function. Finally, the new method and the traditional evaluation methods are compared. Results show that the new method outperforms the traditional methods and real- izes qualitative and quantitative classification of the electromagnetic environment in a real-time, fast and self- adaptive way. It expands the application range of the traditional methods, and has practical value in studying the complex electromagnetic environment in real battlefield.
出处
《计算机工程与科学》
CSCD
北大核心
2014年第1期105-110,共6页
Computer Engineering & Science
基金
国家杰出青年科学基金资助项目(50925727)
国家自然科学基金资助项目(60876022
61102039
51107034)
湖南省科技计划项目(2011J4
2011JK2023)
广东省教育部产学研计划资助项目(2009B090300196)
中央高校基本科研业务费计划资助项目
关键词
靶场
电磁环境
复杂度
BP神经网络
复杂度
收敛速度
range
electromagnetic environment
back propagation （BP） neural network
complexity
convergence speed
