| 基于结构自整定前馈网络的雷达目标识别研究 |
| |
| 引用本文： | 谢希权,陈大庆.基于结构自整定前馈网络的雷达目标识别研究[J].火力与指挥控制,1998(1). |
| |
| 作者姓名： | 谢希权 陈大庆 |
| |
| 作者单位： | 西安空军工程学院(谢希权)，西安电子科技大学(陈大庆) |
| |
| 摘 要： | 概述了基于雷达成像的目标类型识别技术。阐述了多层前向网络的分类特性，提出一种网络结构自整定算法来训练网络，并构造分类器，对基于转台成像实验的雷达目标类型识别问题进行了仿真研究。研究结果表明，经结构自整定算法训练后的前馈网络对成像雷达目标具有较好的推广识别能力，识别率达到９０％。
|
| 关 键 词： | 雷达目标识别 转台成像 多层前向网络 结构自整定 |
Radar Target Identification Based on Multi layer Feed Forward Neural Networks with Self architechure Algorithm |
| |
| Xie Xiquan,Chen Daqing.Radar Target Identification Based on Multi layer Feed Forward Neural Networks with Self architechure Algorithm[J].Fire Control & Command Control,1998(1). |
| |
| Authors: | Xie Xiquan Chen Daqing |
| |
| Institution: | Xie Xiquan * Chen Daqing ** |
| |
| Abstract: | The technology of radar target identification(RTID)based on radar imaging is reviewed briefly. The Classification characteristics of multilayer feedfoward neural network(MFNN)is investigated, and a self_architechture algorithm is presented in this paper. Then several simulations on RTID have been taken by using MFNN to design a classifier. The results demonstrate that a small scale MFNN has better Classification characteristics after being trained by the algorithm, and the correct recognition rate is up to 90%. |
| |
| Keywords: | radar target identification imaging of rotating object multilayer feedforward neural networks self architecture |
| 本文献已被 CNKI 等数据库收录！ |
