检索规则说明:AND代表“并且”;OR代表“或者”;NOT代表“不包含”;(注意必须大写,运算符两边需空一格)
检 索 范 例 :范例一: (K=图书馆学 OR K=情报学) AND A=范并思 范例二:J=计算机应用与软件 AND (U=C++ OR U=Basic) NOT M=Visual
机构地区:[1]北方工业大学电子信息工程学院,北京100144
出 处:《北方工业大学学报》2015年第3期20-24,共5页Journal of North China University of Technology
摘 要:本文主要研究光纤安全预警系统振动信号特征提取及振源识别问题.采用小波多分辨分析技术,从多尺度分解的角度出发,依据小波变换的分层分解关系和时频特性提取振动信号的细节信息,用来反应不同频带上振动信号的能量分布特征,在此基础上采用支持向量机对振动信号进行分类识别.测试结果表明,与现有方法对比,本方法具有准确率高的优点,为光纤振动信号的识别提供一种高性能的实用方法.This paper conducted a research on the feature extraction of the fiber optic vibration signal and vibration signal identification based on optical fiber security warning system. It used the multiresolution of wavelet from the perspective of wavelet multi scale decomposition to extract the details of vibration signal according to the relationship between time-frequency characteristics of wavelet transform and hierarchical decomposition, so that the features of vibration signals of different frequency band energy distribution can be reflected, on the basis of which, support vector machine was used to classify the vibration signals. The test result shows that compared with the existing methods, this method has the advantage of high accuracy. It provides a practical method with high performance for the identification of the fiber optic vibration signal.
分 类 号:TN911.6[电子电信—通信与信息系统]
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在链接到云南高校图书馆文献保障联盟下载...
云南高校图书馆联盟文献共享服务平台 版权所有©
您的IP:216.73.216.28