首页 | 本学科首页   官方微博 | 高级检索  
     

基于神经网络和功率谱的水中目标信号检测方法
引用本文:李军,姜礼平,张志宏. 基于神经网络和功率谱的水中目标信号检测方法[J]. 海军工程大学学报, 2005, 17(2): 108-111
作者姓名:李军  姜礼平  张志宏
作者单位:海军工程大学,理学院,湖北,武汉,430033
基金项目:海军工程大学科研基金资助项目(HGDJJ02020)
摘    要:将功率谱和神经网络相结合,应用于高海况、低信噪比条件下,水中目标信号的特征提取中.文中首先对信号进行功率谱估计,利用目标信号功率主要集中在低频部分的特点,提取低频信号的能量作为特征,然后利用人工神经网络对目标信号进行检测.利用不同浪级情况下海洋水压场的仿真信号数据,对某型目标舰船的水压信号进行了检测计算,验证了该方法的有效性,尤其是达到了在高海况、低信噪比条件下,对目标信号检测率比较高、虚警率比较低的效果.

关 键 词:目标检测  功率谱  神经网络
文章编号:1009-3486(2005)02-0108-04
修稿时间:2004-10-13

A method of underwater target signal detection based on neural networks and power spectrum
LI Jun,JIANG Li-ping,ZHANG Zhi-hong. A method of underwater target signal detection based on neural networks and power spectrum[J]. Journal of Naval University of Engineering, 2005, 17(2): 108-111
Authors:LI Jun  JIANG Li-ping  ZHANG Zhi-hong
Abstract:This paper combines power spectrum estimation with neural networks for target signal detection under the condition of low SNR. On the basis of power spectrum estimation, some energy parameters can be extracted by frequency-domain analysis. By means of BP network, it is possible to recognize whether target signal is involved in received signals or not. The validity of the method is verified by a real target signal with additive simulated noise signal, especially under the condition of low SNR.
Keywords:target detection  power spectrum  neural networks
本文献已被 CNKI 万方数据 等数据库收录!
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号