兵工自动化 自动控制技术 O. I. Automation 2002年第21卷第5期 Auto-Control 2002, Vol. 21, No. 5
文章编号
2002
朱道光
中国兵器工业集团第
206研究所
摘要
采用改进的进化规划算法优化
径向基函数网络该算法将进化规划算法和神经网络结合起
来
Radial Basis Function
Multilayer Feedforward
Neural
Nerworks
用改进进化规划取代反向传播算法
BP
í¨1y??13位巴克码和31位M 编码的仿真实验都有较大的提高
旁瓣抑
制进化规划
中图分类号A
RBF Neural Network Based on Improved Evolutionary
Planning Used in Binary-coded Side-lobe Optimization
WANG Wei, ZHU Dao-guang, HUANG Jin-jie
(No. 206 Institute of China Arms Industry Group Corporation, Xi’an 710100, China)
Abstract: Based on researching binary-coded range side-lobe suppression problem for radar pulse
compressed signal, the radial basis function (RBF) neural network was optimize d with the improved evolutionary planning algorithm (IEPA), a new algorithm based on the improved evolutionary planning algorithm was presented. IEPA was combined with neural network by the new algorithm, multi-layer feed-forward neural network structure was replaced with RBF neural network structure, and back propagation (BP) algorithm was replaced with IEPA, then, expected side -lobe suppression quota was rapidly waisted. The emulation experiments for the 13-elements baker code and 31-elements M code show that side -lobe suppression ability and operating speed was improved with the new method.
Key Words: Side-lobe suppression; Pulse compression; Evolutionary planning
1 引言
脉冲压缩技术在现代雷达中得到了广泛的应用
其中二相编码信号就是
一种比较常用的脉冲压缩信号
信号的主旁瓣比较低
所以常常需要进一步抑制副
瓣
即时域加权[1, 2, 3]和频域加权[4]
?ùò???ó|ó?êüμ?
á?ò??¨μ??T??
ê±óò?óè¨μ?·?·¨óD?±?óê§??ò???
[1, 2]
文献[5]研究了采用13位巴克码和63
位M 编码时脉冲雷达检测的神经网络方法
为二相编码旁瓣
抑制问题的处理提供了一个新的途径
不同的信号差异较大
而
且容易陷入局部最小值
Evolutionary Programming
2001-08-31
2001-10-17
作者简介
1973
-
男
1996年毕业于西北工业大学
从事雷达信号处理
万方数据