华南理工大学学报(自然科学版)
華南理工大學學報(自然科學版)
화남리공대학학보(자연과학판)
JOURNAL OF SOUTH CHINA UNIVERSITY OF TECHNOLOGY(NATURAL SCIENCE EDITION)
2014年
7期
55-61
,共7页
特征提取%Morlet小波%奇异值分解%频率-能量谱
特徵提取%Morlet小波%奇異值分解%頻率-能量譜
특정제취%Morlet소파%기이치분해%빈솔-능량보
feature extraction%Morlet wavelet%singular value decomposition%frequency-energy spectrum
针对Morlet小波变换结果中的特征提取问题,对连续小波变换得到的小波系数矩阵进行奇异值分解( SVD),分析了所获得的奇异值与Morlet小波变换结果中的特征信号以及噪声的对应关系。基于这种关系,通过选择合适的奇异值进行重构,清晰地提取到Morlet小波分解结果中的有效特征信息;进一步计算得到频率-能量谱,根据峰值位置能够提取冲击特征。将该方法应用于轴承振动信号的故障特征提取,并与其他方法进行了比较。结果表明,文中方法所获得的故障波形非常清晰,在低信噪比时具有较好的故障特征提取效果。
針對Morlet小波變換結果中的特徵提取問題,對連續小波變換得到的小波繫數矩陣進行奇異值分解( SVD),分析瞭所穫得的奇異值與Morlet小波變換結果中的特徵信號以及譟聲的對應關繫。基于這種關繫,通過選擇閤適的奇異值進行重構,清晰地提取到Morlet小波分解結果中的有效特徵信息;進一步計算得到頻率-能量譜,根據峰值位置能夠提取遲擊特徵。將該方法應用于軸承振動信號的故障特徵提取,併與其他方法進行瞭比較。結果錶明,文中方法所穫得的故障波形非常清晰,在低信譟比時具有較好的故障特徵提取效果。
침대Morlet소파변환결과중적특정제취문제,대련속소파변환득도적소파계수구진진행기이치분해( SVD),분석료소획득적기이치여Morlet소파변환결과중적특정신호이급조성적대응관계。기우저충관계,통과선택합괄적기이치진행중구,청석지제취도Morlet소파분해결과중적유효특정신식;진일보계산득도빈솔-능량보,근거봉치위치능구제취충격특정。장해방법응용우축승진동신호적고장특정제취,병여기타방법진행료비교。결과표명,문중방법소획득적고장파형비상청석,재저신조비시구유교호적고장특정제취효과。
Aiming at the feature extraction of Morlet wavelet transform results , the wavelet coefficient matrix obtained by the continuous Morlet wavelet transform is decomposed by singular value decomposition ( SVD ) .The relationship among the singular value , the feature signal and the noise in the Morlet wavelet transform results is analyzed .Based on this relationship , the effective feature information of wavelet transform results can be clearly extracted by selecting appropriate singular values for SVD reconstruction .Further calculation is carried out to obtain the frequency-energy spectrum , and the shock feature can be extracted according to the peak position of this spec -trum.Finally, the proposed method is applied to the fault feature extraction of bearing vibration signals and is com-pared with other methods .The results show that the proposed method can extarct the distinct fault waveforms and achieve a very good effect on fault feature extraction at a low signal-to-noise ratio(SNR).