摘要
目标识别是指挥自动化系统的一个重要组成部分,针对现代战争对抗手段不断增强的特点,运用BP神经网络和D-S证据理论探索作战飞机机型的识别方法。前端采用3层BP神经网络结构,以传感器接收数据为输入,以神经网络输出作为证据,后端对不同传感器的证据按D-S理论进行融合,得到待识别目标的识别概率。经由M ATLAB编程对国内外几种主要机型的识别进行仿真研究,与现行目标识别方法相比较,能够更快速、准确、可靠地识别飞机目标,较好地满足了空战中作战指挥系统对飞机机型识别的需求。
Target Recognition is important part in C^3I system. According to the peculiarity of continuing promoted counterwork of modern wars ,Target Recognition is base on BP Neural Networks and D-S Evidence Theory to quest for the identification method to the type of aircraft. Firstly,adopt 3 layer neural networks, data of sensor as input of neural networks, output of neural networks as evidence, secondly, according to D-S theory to fuse the evidences of different sensors, finally ,obtaining probability of recognition to aircraft. The recognition models are simulated by the tools of neural networks provided by MATLAB,Compare to present recognition method,this model can further rapidly,precisely and credibly identify the aim of aircraft,and commendably fulfill the demand of aircraft target recognition to C^3I system of air force.
出处
《火力与指挥控制》
CSCD
北大核心
2006年第10期88-90,F0003,共4页
Fire Control & Command Control
