| 一种机场环境光纤预警系统的信号识别新算法 |
| |
| 引用本文： | 熊兴隆,崔雅峰,杨立香,马愈昭,李猛.一种机场环境光纤预警系统的信号识别新算法[J].光电子．激光,2017,28(9):985-991. |
| |
| 作者姓名： | 熊兴隆 崔雅峰 杨立香 马愈昭 李猛 |
| |
| 作者单位： | 中国民航大学 天津市智能信号与图像处理重点实验室,天津 300300,中国民航大学 天津市智能信号与图像处理重点实验室,天津 300300,中国民航大学 天津市智能信号与图像处理重点实验室,天津 300300,中国民航大学 天津市智能信号与图像处理重点实验室,天津 300300,天津市空管运行规划与安全技术重点实验室,天津 300300 |
| |
| 基金项目： | 国家自然科学基金重点(U1533113)、国家自然科学基金重点项目(U1433202)和中央高 校基本科研业务费中国民航大学专项(3122016B001)资助项目 (1.中国民航大学 天津市智能信号与图像处理重点实验室,天津 300300; 2.天津市空管运行规划与安全技术重点实验室,天津 300300) |
| |
| 摘 要： | 提出了一种基于导数分析与典型特征选取的信 号识别新算法。首先,分析信号导数与频率的关系,得到信号的时频特性；其次,根据时频 分布的特点,选取具有代表性的典型特征,以降低特征维度,减少识别时间；最后,应用概 率神经网络(PNN)对典型特征进行学习和分类。采用4种扰动信号对本文算法进行实验验证 ,平均正确识别率达95.7%,且识别时间小于0.23s。实验结果表明,本文算法能够快速准确 地识别扰动类型,为Mech-Zehnder(M-Z)干涉型周界系统的模式识别提供一种科学可靠的 方法。
|
| 关 键 词： | 光纤光学 Mach-Zehnder(M-Z)干涉 信号识别 概率神经网络(PNN) |
| 收稿时间： | 2017/1/3 0:00:00 |
A new method for signal recognition of the fiber-optic alarm system around airp ort |
| |
| XIONG Xing-long,CUI Ya-feng,YANG Li-xiang,MA Yu -zhao and LI Meng.A new method for signal recognition of the fiber-optic alarm system around airp ort[J].Journal of Optoelectronics·laser,2017,28(9):985-991. |
| |
| Authors: | XIONG Xing-long CUI Ya-feng YANG Li-xiang MA Yu -zhao and LI Meng |
| |
| Affiliation: | Key Laboratory for Advanced Signal Processing,Civil Aviation Universi ty of C hina,Tianjin 300300,China,Key Laboratory for Advanced Signal Processing,Civil Aviation Universi ty of C hina,Tianjin 300300,China,Key Laboratory for Advanced Signal Processing,Civil Aviation Universi ty of C hina,Tianjin 300300,China,Key Laboratory for Advanced Signal Processing,Civil Aviation Universi ty of C hina,Tianjin 300300,China and Tianjin key Laboratory for Act Operation Planning and Safety Technology,Tianjin 300300,China |
| |
| Abstract: | A new signal recognition method is presented based on the derivative analysis and feature extraction.Firstly,the time-frequency characteristics are obtained thought analyzing the relation of derivative and fr equency.Secondly,according to the time-frequency distribution characteristic,several typical features are extracted to reduce fea ture dimensions and recognition time. Finally,probability neural network (PNN) is used to identify and learn.The algor ithm is verified by four disturbance signals, the average accuracy rate reaches 95.7%,and the recognition time is less than 0. 23s.The experimental results show that the method can identify the type of disturbance quickly and accurately,and provide a scientific and reliable method for the pattern recognition of perimeter system based on Mach-Zehnder (M -Z) interferometer. |
| |
| Keywords: | fiber optics Mach-Zehnder (M-Z) interferometer signal recognition probabili ty neural network (PNN) |
|
| 点击此处可从《光电子．激光》浏览原始摘要信息 |
|
点击此处可从《光电子．激光》下载全文 |
|
