基于BP神经网络的空袭目标识别

Air-raid Target Identification Based on BP Neural Network

通过介绍BP神经网络用于目标识别的基本原理,对目标不完整或不确定数据进行分析、推理。提取空袭目标的速度、高度、机动加速度和雷达反射面积等有用特征,并运用定性、定量相接合的方法,对目标特征进行归一化处理,作为输入层数据。根据目标识别的具体要求确定各层神经元数,建立了BP神经网络目标识别模型。通过对样本数据训练、检验、输出结果的分析,表明在缺乏识别先验知识时,运用该方法识别空中目标简单有效。

Firstly this paper introduces the basic principle of BP neural network use for target identification. Through analyzes and ratiocinate the dis-complete and indeterminate date, the effective character of air-raid target is distilled about the velocity, the altitude, the mobile acceleration and the radar reflect area etc. Secondly, as input date the target character is disposed with the qualitative and quantitative method. A target identification model of BP neural network is built, and the nerve cells are established based on the idiographic need of target identification. Finally, through training and checking up the sample date, the output result proved it is a simple and effective method to identifying aerial target at lack in prescient information.