改进的HHT变换在光纤振动模式识别中的应用
|
摘要
针对双马赫-曾德尔(M-Z)干涉型光纤振动传感系统输出信号非线性、非平稳特点,提出基于互补总体经验模态分解(CEEMD)的希尔伯特-黄变换(HHT)模式识别算法。该算法采用CEEMD将振动信号分解成多个本征模态函数(IMF),利用各阶IMF的归一化自相关函数筛选出噪声分量进行中值滤波;然后对各阶IMF分量做Hilbert变换,基于Hilbert边际能量谱构造特征向量;最后利用概率神经网络(PNN)实现振动信号的模式识别。对四种典型光纤振动信号的实验验证表明,算法的平均正确识别率最低可达85%。
According to the nonlinear and nonstationary characteristics of output signal of dual Mach-Zenhder(M-Z)interferometric fiber-optic vibration sensing system,a modified Hilbert-Huang transform(HHT) pattern recognition algorithm based on complementary ensemble empirical mode decomposition(CEEMD)is proposed. The CEEMD is used in the algorithm to decompose the vibration signals into several intrinsic mode functions(IMFs),and the normalized autocorrelation function of each-order IMFs is adopted to screen out the noise component for median filtering. The Hilbert transform is performed for eachorder IMFs component,and the feature vector is constructed on the basis of Hilbert marginal energy spectrum. The probabilistic neural network(PNN)is utilized to realize the pattern recognition of vibration signal. The experimental results of four typical fiber-optic vibration signals show that the average correct recognition rate of the algorithm can reach up to 85%.
According to the nonlinear and nonstationary characteristics of output signal of dual Mach-Zenhder(M-Z)interferometric fiber-optic vibration sensing system,a modified Hilbert-Huang transform(HHT) pattern recognition algorithm based on complementary ensemble empirical mode decomposition(CEEMD)is proposed. The CEEMD is used in the algorithm to decompose the vibration signals into several intrinsic mode functions(IMFs),and the normalized autocorrelation function of each-order IMFs is adopted to screen out the noise component for median filtering. The Hilbert transform is performed for eachorder IMFs component,and the feature vector is constructed on the basis of Hilbert marginal energy spectrum. The probabilistic neural network(PNN)is utilized to realize the pattern recognition of vibration signal. The experimental results of four typical fiber-optic vibration signals show that the average correct recognition rate of the algorithm can reach up to 85%.
引文
[1]黄翔东,张皓杰,刘琨,等.基于综合特征的光纤周界安防系统高效入侵事件识别[J].物理学报,2017,66(12):164-173.HUANG Xiangdong,ZHANG Haojie,LIU Kun,et al.Highefficiency intrusion recognition by using synthesized features in optical fiber perimeter security system[J].Acta physica Sinica,2017,66(12):164-173.
[2]杨正理,孙书芳.基于小波能量熵的光纤周界安防系统信号识别[J].光电子·激光,2016,27(12):1328-1333.YANG Zhengli,SUN Shufang.The signal identification of optical fiber perimeter security system based on wavelet energy entropy[J].Journal of optoelectronics·laser,2016,27(12):1328-1333.
[3]刘琨,柴天娇,刘铁根,等.多防区光纤周界安防系统及入侵快速判定算法[J].光电子·激光,2015,26(2):288-294.LIU Kun,CHAI Tianjiao,LIU Tiegen,et al.Multi-area optical perimeter security system with quick invasion judgement algorithm[J].Journal of optoelectronics·laser,2015,26(2):288-294.
[4]王思远,娄淑琴,梁生,等.M-Z干涉仪型光纤分布式扰动传感系统模式识别方法[J].红外与激光工程,2014,43(8):2613-2618.WANG Siyuan,LOU Shuqin,LIANG Sheng,et al.Pattern recognition method of fiber distributed disturbance sensing system based on M-Z interferometer[J].Infrared and laser engineering,2014,43(8):2613-2618.
[5]喻骁芒,罗光明,朱珍民,等.分布式光纤传感器周界安防入侵信号的多目标识别[J].光电工程,2014,41(1):36-41.YU Xiaomang,LUO Guangming,ZHU Zhenmin,et al.The multi target recognition of intrusion signal of perimeter security with distributed fiber-optic sensor[J].Opto-electronic engineering,2014,41(1):36-41.
[6]朱程辉,王建平,李奇越,等.基于时频特征的光纤周界入侵振动信号识别与定位[J].中国激光,2016,43(6):309-317.ZHU Chenghui,WANG Jianping,LI Qiyue,et al.Recognition and localization of intrusion vibration signal based on timefrequency characteristics in optical fiber perimeter security[J].Chinese journal of lasers,2016,43(6):309-317.
[7]蒋立辉,盖井艳,王维波,等.基于总体平均经验模态分解的光纤周界预警系统模式识别方法[J].光学学报,2015,35(10):52-58.JIANG Lihui,GAI Jingyan,WANG Weibo,et al.Ensemble empirical mode decomposition based event classification method for the fiber-optic intrusion monitoring system[J].Acta optica Sinica,2015,35(10):52-58.
[8]赵亮,刘海,徐世昌,等.HHT和CWT用于光纤振动信号分析的对比研究[J].激光技术,2017,41(2):260-264.ZHAO Liang,LIU Hai,XU Shichang,et al.Comparison study of optical fiber vibration signals using HHT and CWT[J].Laser technology,2017,41(2):260-264.
[9]熊兴隆,崔雅峰,杨立香,等.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.XIONG Xinglong,CUI Yafeng,YANG Lixiang,et al.A new method for signal recognition of the fiber-optic alarm system around airport[J].Journal of optoelectronics·laser,2017,28(9):985-991.
[10]席旭刚,武昊,罗志增.基于EMD自相关的表面肌电信号消噪方法[J].仪器仪表学报,2014,35(11):2494-2500.XI Xugang,WU Hao,LUO Zhizeng.De-noising method of the EMG based on EMD autocorrelation[J].Chinese journal of scientific instrument,2014,35(11):2494-2500.
[11]邵忍平,曹精明,李永龙.基于EMD小波阈值去噪和时频分析的齿轮故障模式识别与诊断[J].振动与冲击,2012,31(8):96-101.SHAO Renping,CAO Jingming,LI Yonglong.Gear fault pattern identification and diagnosis using time-frequency analysis and wavelet threshold de-noising based on EMD[J].Journal of vibration and shock,2012,31(8):96-101.
[2]杨正理,孙书芳.基于小波能量熵的光纤周界安防系统信号识别[J].光电子·激光,2016,27(12):1328-1333.YANG Zhengli,SUN Shufang.The signal identification of optical fiber perimeter security system based on wavelet energy entropy[J].Journal of optoelectronics·laser,2016,27(12):1328-1333.
[3]刘琨,柴天娇,刘铁根,等.多防区光纤周界安防系统及入侵快速判定算法[J].光电子·激光,2015,26(2):288-294.LIU Kun,CHAI Tianjiao,LIU Tiegen,et al.Multi-area optical perimeter security system with quick invasion judgement algorithm[J].Journal of optoelectronics·laser,2015,26(2):288-294.
[4]王思远,娄淑琴,梁生,等.M-Z干涉仪型光纤分布式扰动传感系统模式识别方法[J].红外与激光工程,2014,43(8):2613-2618.WANG Siyuan,LOU Shuqin,LIANG Sheng,et al.Pattern recognition method of fiber distributed disturbance sensing system based on M-Z interferometer[J].Infrared and laser engineering,2014,43(8):2613-2618.
[5]喻骁芒,罗光明,朱珍民,等.分布式光纤传感器周界安防入侵信号的多目标识别[J].光电工程,2014,41(1):36-41.YU Xiaomang,LUO Guangming,ZHU Zhenmin,et al.The multi target recognition of intrusion signal of perimeter security with distributed fiber-optic sensor[J].Opto-electronic engineering,2014,41(1):36-41.
[6]朱程辉,王建平,李奇越,等.基于时频特征的光纤周界入侵振动信号识别与定位[J].中国激光,2016,43(6):309-317.ZHU Chenghui,WANG Jianping,LI Qiyue,et al.Recognition and localization of intrusion vibration signal based on timefrequency characteristics in optical fiber perimeter security[J].Chinese journal of lasers,2016,43(6):309-317.
[7]蒋立辉,盖井艳,王维波,等.基于总体平均经验模态分解的光纤周界预警系统模式识别方法[J].光学学报,2015,35(10):52-58.JIANG Lihui,GAI Jingyan,WANG Weibo,et al.Ensemble empirical mode decomposition based event classification method for the fiber-optic intrusion monitoring system[J].Acta optica Sinica,2015,35(10):52-58.
[8]赵亮,刘海,徐世昌,等.HHT和CWT用于光纤振动信号分析的对比研究[J].激光技术,2017,41(2):260-264.ZHAO Liang,LIU Hai,XU Shichang,et al.Comparison study of optical fiber vibration signals using HHT and CWT[J].Laser technology,2017,41(2):260-264.
[9]熊兴隆,崔雅峰,杨立香,等.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.XIONG Xinglong,CUI Yafeng,YANG Lixiang,et al.A new method for signal recognition of the fiber-optic alarm system around airport[J].Journal of optoelectronics·laser,2017,28(9):985-991.
[10]席旭刚,武昊,罗志增.基于EMD自相关的表面肌电信号消噪方法[J].仪器仪表学报,2014,35(11):2494-2500.XI Xugang,WU Hao,LUO Zhizeng.De-noising method of the EMG based on EMD autocorrelation[J].Chinese journal of scientific instrument,2014,35(11):2494-2500.
[11]邵忍平,曹精明,李永龙.基于EMD小波阈值去噪和时频分析的齿轮故障模式识别与诊断[J].振动与冲击,2012,31(8):96-101.SHAO Renping,CAO Jingming,LI Yonglong.Gear fault pattern identification and diagnosis using time-frequency analysis and wavelet threshold de-noising based on EMD[J].Journal of vibration and shock,2012,31(8):96-101.