一类组合神经网络在协同空战分析中的应用  

Application of a Type of Associated Neural Network in Cooperative Air-to-Air Combat Analysis

作　　者：李林森[1] 于海勋[1] 韩志刚[1] 佟明安[1] 

机构地区：[1]西北工业大学电子工程系,西安710072

出　　处：《飞行力学》2000年第1期81-84,共4页Flight Dynamics

基　　金：航空科学基金! ( 97D53 0 3 7)

摘　　要：为了在恶劣、复杂的协同空战环境里帮助飞行员进行更有效的决策 ,在其指挥级 ,提出了一类有 /无教师组合神经网络—— BP-SOFM网络 ,并用它来完成目标分配和攻击排序。对于典型的 2 :4空战 ,给出了 BP-SOFM网络的结构 ,并探讨了各个子网的训练和测试方法 ,及该组合神经网络的使用方法。设计并实现了一个基于 BP-SOFM网络的多机协同空战仿真系统。仿真结果表明 。In order to help pilots make more effective decisions in the adverse and complicated environment in the cooperative air to air combat, in its command hierarchy, we presented a type of associated neural network with/without teachers——BP SOFM network, and used it to complete the target distribution and the attacking sequence. Then, for typical 2 via 4 air to air combat, the subsection 1.1 gives the structure of the BP SOFM network, and studies the training and testing methods of each sub network. The subsection 1 2 discusses its using method. A multi fighter cooperative air to air combat simulation system based on BP SOFM network has been implemented, and simulation result given in section 2 shows that our system is effective.

关 键 词：组合神经网络 多目标攻击 协同空战 战术决策 

分 类 号：V271.41[航空宇航科学与技术—飞行器设计] O157.5[理学—数学]