基于小波模极大值模糊熵的遥测振动信号异常检测

刘学,梁红,玄志武

振动与冲击 ›› 2016, Vol. 35 ›› Issue (9) : 147-151.

PDF(2288 KB)
PDF(2288 KB)
振动与冲击 ›› 2016, Vol. 35 ›› Issue (9) : 147-151.
论文

基于小波模极大值模糊熵的遥测振动信号异常检测

  • 刘学,梁红,玄志武
作者信息 +

Telemetry vibration signal anomaly detection method based on the fuzzy entropy of wavelet modulus maxima

  •   LIU Xue   LIANG Hong  XUAN Zhi-wu
Author information +
文章历史 +

摘要

针对遥测振动信号频域成份复杂、非平稳非线性和强噪声特性,提出一种基于小波模极大值模糊熵的遥测振动信号异常检测方法。首先对采集到的遥测振动信号进行零漂修正和趋势项消除;然后对经预处理后的振动信号进行一维连续小波变换,计算所有尺度空间中的小波模极大值序列;最后将原信号及其小波模极大值序列的模糊熵构成的特征向量输入到SVM分类器,根据模糊熵的变化情况对遥测振动信号进行异常检测。实测数据验证了该方法的有效性。

Abstract

For telemetry vibration signal in the frequency domain has characteristics of complex composition, nonlinear and non-stationary, as well as strong noise, a telemetry vibration signal anomaly detection method based on fuzzy entropy of wavelet modulus maxima is proposed. Firstly, the collected telemetry vibration signal is zero drift amended and eliminated the trend term. Secondly, the one-dimensional continuous wavelet transform is used to convert the preprocessed vibration signal, and then calculate all scales space wavelet modulus maxima sequence; Finally, the feature vector constituted by the fuzzy entropy of original signal and its wavelet modulus maxima sequence is input to SVM classifier, then the abnormal telemetry vibration signal is detected through the changes of fuzzy entropy. Measured data demonstrate the effectiveness of this method.

关键词

遥测振动信号 / 小波模极大值 / 模糊熵 / 支持向量机 / 异常检测

Key words

Telemetry vibration signal / Wavelet modulus maxima / Fuzzy Entropy / SVM / Anomaly detection

引用本文

导出引用
刘学,梁红,玄志武. 基于小波模极大值模糊熵的遥测振动信号异常检测[J]. 振动与冲击, 2016, 35(9): 147-151
LIU Xue LIANG Hong XUAN Zhi-wu . Telemetry vibration signal anomaly detection method based on the fuzzy entropy of wavelet modulus maxima[J]. Journal of Vibration and Shock, 2016, 35(9): 147-151

参考文献

[1] 程军圣,张亢,杨宇,等.局部均值分解与经验模式分解的对比研究[J]. 振动与冲击,2009,28( 5) : 13 -16.
CHENG Jun-sheng, ZHANG Kang, YANG Yu, etal. Comparison between the methods of local mean decomposition and empirical mode decomposition [J]. Journal of Vibration and Shock,2009,28( 5) : 13 -16.
[2] 杨德昌,唐巍,屈瑞谦,等.基于改进局部均值分解的低频振荡参数提取[J].中国电机工程学报,2013,33(4):135-140.
YANG De-chang,TANG Wei,QU Rui-qian,etal. Extraction of the Oscillatory Parameters of Low Frequency Oscillation Based on Improved Local Mean Decomposition [J].Proceedings of the CSEE,2013,33(4):135-140.
[3] 黄林洲,郭兴明,丁晓蓉.EMD近似熵结合支持向量机的心音信号识别研究[J].振动与冲击,2012,31(19): 21-25.
HUANG Lin-zhou, GUO Xing-ming, DING Xiao-rong. Heart sound recognition based on EMD approximate entropy and SVM [J].Journal of Vibration and Shock,2012,31(19): 21-25.
[4] 张学清,梁军.基于EEMD一近似熵和储备池的风电功率混沌时间序列预测模型[J]. 物理学报, 2013,62 (5) :050505-1-9.
ZHANG Xue-qing, LIANG Jun. Chaotic time series prediction model of wind power based on ensemble empirical mode decomposition-approximate entropy and reservoir [J]. Acta Physica Sinica, 2013,62 (5) :050505-1-9.
[5] Chen W T, Wang Z Z, Xie H B,etal. Characterization of Surface EMG Signal Based on Fuzzy Entropy [J]. IEEE Transactions on Neural Systems and Rehabilitation Engineering 2007,15:266 - 272
[6] Costa M,Goldberger A L, Peng C K . Multiscale entropy analysis of  biological signals[J].Physical Review F,2005,71:021906.
[7] 孙克辉,贺少波,尹林子,等.模糊熵算法在混沌序列复杂度分析中的应用[J]. 物理学报, 2012,61(13) :130507-1-7.
SUN Ke-hui, HE Shao-bo, YIN Lin-zi, etal. Application of FuzzyEn algorithm to the analysis of complexity of chaotic sequence[J]. Acta Physica Sinica, 2012,61(13) :130507-1-7.
[8] GAO X T, BACRY E, SATTAR F, et al. Multiscale contour corner detection based on local natural scale and wavelet transform[J]. Image and Vision Computing, 2007, 25 ( 6) :890-898.
[9] 李峰,汤宝平,章国稳.基于舍一交叉验证优化最小二乘支持向量机的故障诊断模型[J].振动与冲击,2010,29(9):170-174.
LI Feng,TANG Bao-ping, ZHANG Guo-wen. Fault diagnosis model based on least square support vector machine optimized by leave-one-out cross-validation[J].Journal of Vibration and Shock, 2010,29(9):170-174.

PDF(2288 KB)

Accesses

Citation

Detail

段落导航
相关文章

/