正在加载图片...
·76· 工程科学学报,第37卷,增刊1 2005回 参考文献 t [Xu Y J,Yu D J,Sun Y S,et al.Roller bearing fault diagnosis using order multi-scale morphology demodulation.Journal of Vi- 尺度 300而 bration Engineering,2013,26(2):252 200 (徐亚军,于德介,孙云嵩,等.滚动轴承故障诊断的阶比多 尺度形态学解调方法.振动工程学报,2013,26(2):252) 0 Huang NE,Shen Z,Long S R,et al.The empirical mode de- 尺度 composition and the Hilbert spectrum for nonlinear and non-sta- 100 (c) tionary time series analysis.Proceedings of the Royal Society of 50 London.Series A:Mathematical,Physical and Engineering Sci- ;g1;。9gg品 ences,1998,454(1971):903 B] Wu ZH,Huang N E.A study of the characteristics of white noise 尺度 using the empirical mode decomposition method.Proceedings of 图5不同故障类型形态谱图.()内图故障:(b)外圈故障: the Royal Society of London.Series A:Mathematical,Physical and (c)滚动体故障 Engineering Sciences,2004,460(2046):1597 Fig.5 Morphological pattern figures of fault signals:(a)inner Serra J.Image Analysis and Mathematical Morphology.Vol.1. fault:(b)outer fault;(c)rolling element fault New York:Academic Press,1982 5 Serra J.Image Analysis and Mathematical Morphology.Vol.2. 对这20组样本进行识别,识别结果如表2所示. New York:Academic Press,1988 表23类故障诊断结果 Matagos P,Schafer R W.Morphological filters-Part I:Their set- theoretic analysis and relations to liner shift-invariant filters.IEEE Table 2 Diagnosis result of 3 faults Transactions on Acoustics,Speech,and Signal Processing ASSP, SVM KFCM FCM K-means 2008,22(3):597 信号类型 识别结果识别结果 识别结果识别结果率 ] Matagos P,Schafer R W.Morphological filters-Part Il:Their rela- 内圈 100% 100% 100% 100% tions to median,order-statistic,and stack filters.IEEE Transac- tions on Acoustics,Speech,and Signal Processing ASSP,2008,22 外圈 100% 100% 100% 100% (3):1170 滚动体 100% 100% 100% 100% 8] Maragos P.Pattern spectrum of images and morphological shape- size complexity /IEEE International Conference on ICASSP87. 通过对表2的轴承内圈、外圈和滚动体三种故障 Dallas,1987:241 类型的诊断结果发现,20组测试样本可以被这四种方 9] Maragos P.Pattem spectrum and multiscale shape representation. 法进行有效的识别,每种故障的识别正确率都达到了 IEEE Transactions on Pattern Analysis and Machine Intelligence 1989,11(7):701 100%.可以得出:基于集总经验模态分解、形态谱特 0o] Hao R J,Lu WX,Chu F L.Multiscale morphological analysis 征提取和支持向量机识别的方法可以成功地实现对轴 on fault signals of rolling element bearings.Journal of Mechanical 承三种故障的诊断;形态谱可以有效地表征信号的形 Engineering,2008,44(11):160 态特征,利用其作为特征向量可以有效地对滚动轴承 (郝如江,卢文秀,褚福磊.滚动轴承故障信号的多尺度形 故障进行诊断. 态学分析.机械工程学报,2008,44(11):160) [11]Jiang W L,Wu S Q.Multi-ata fusion fault diagnosis method 6结论 based on SVM and evidence theory.Chinese Journal of Scientific Instrument,2010,31(8):1738 针对滚动轴承的内圈、外圈和滚动体的三种故障 (姜万录,吴胜强.基于SVM和证据理论的多数据融合故障 类型的诊断问题,本文提出了一种基于集总经验模态 诊断方法.仪器仪表学报,2010,31(8):1738) [12]Zhou Z,Zhang YY,Zhu Y S,et al.Adaptive fault diagnosis of 分解、形态谱特征提取和支持向量机识别的复合方法, rolling bearings based on EEMD and demodulated resonance. 并得出如下结论: Journal of Shock and Vibration,2013,32(2):76 (1)该方法可以有效地对滚动轴承的内圈、外圈 (周智,张优云,朱永生,等.基于EEMD和共振解调的滚 和滚动体三种故障进行诊断,为轴承的故障诊断提供 动轴承自适应故障诊断.振动与冲击,2013,32(2):76) 了一种有效的方法: 13] Zhang L J,Xu J W,Yang J H,et al.Adaptive multiscale mor- (2)形态谱可以有效地表征信号的形态特征,利 phology analysis and its application in fault diagnosis of bearings Journal of University of Science and Technology Beijing,2008,30 用其作为特征向量,可以高效、准确地实现滚动轴承的 (4):441 故障诊断 (章立军,徐金梧,阳建宏,等。自适应多尺度形态学分析及工程科学学报,第 37 卷,增刊 1 图 5 不同故障类型形态谱图. ( a) 内圈故障; ( b) 外圈故障; ( c) 滚动体故障 Fig. 5 Morphological pattern figures of fault signals: ( a ) inner fault; ( b) outer fault; ( c) rolling element fault 对这 20 组样本进行识别,识别结果如表 2 所示. 表 2 3 类故障诊断结果 Table 2 Diagnosis result of 3 faults 信号类型 SVM 识别结果 KFCM 识别结果 FCM 识别结果 K-means 识别结果率 内圈 100% 100% 100% 100% 外圈 100% 100% 100% 100% 滚动体 100% 100% 100% 100% 通过对表 2 的轴承内圈、外圈和滚动体三种故障 类型的诊断结果发现,20 组测试样本可以被这四种方 法进行有效的识别,每种故障的识别正确率都达到了 100% . 可以得出: 基于集总经验模态分解、形态谱特 征提取和支持向量机识别的方法可以成功地实现对轴 承三种故障的诊断; 形态谱可以有效地表征信号的形 态特征,利用其作为特征向量可以有效地对滚动轴承 故障进行诊断. 6 结论 针对滚动轴承的内圈、外圈和滚动体的三种故障 类型的诊断问题,本文提出了一种基于集总经验模态 分解、形态谱特征提取和支持向量机识别的复合方法, 并得出如下结论: ( 1) 该方法可以有效地对滚动轴承的内圈、外圈 和滚动体三种故障进行诊断,为轴承的故障诊断提供 了一种有效的方法; ( 2) 形态谱可以有效地表征信号的形态特征,利 用其作为特征向量,可以高效、准确地实现滚动轴承的 故障诊断. 参 考 文 献 [1] Xu Y J,Yu D J,Sun Y S,et al. Roller bearing fault diagnosis using order multi-scale morphology demodulation. Journal of Vi￾bration Engineering,2013,26( 2) : 252 ( 徐亚军,于德介,孙云嵩,等. 滚动轴承故障诊断的阶比多 尺度形态学解调方法. 振动工程学报,2013,26( 2) : 252) [2] Huang N E,Shen Z,Long S R,et al. The empirical mode de￾composition and the Hilbert spectrum for nonlinear and non-sta￾tionary time series analysis. Proceedings of the Royal Society of London. Series A: Mathematical,Physical and Engineering Sci￾ences,1998,454( 1971) : 903 [3] Wu Z H,Huang N E. A study of the characteristics of white noise using the empirical mode decomposition method. Proceedings of the Royal Society of London. Series A: Mathematical,Physical and Engineering Sciences,2004,460( 2046) : 1597 [4] Serra J. Image Analysis and Mathematical Morphology. Vol. 1. New York: Academic Press,1982 [5] Serra J. Image Analysis and Mathematical Morphology. Vol. 2. New York: Academic Press,1988 [6] Matagos P,Schafer R W. Morphological filters-Part I: Their set￾theoretic analysis and relations to liner shift-invariant filters. IEEE Transactions on Acoustics,Speech,and Signal Processing ASSP, 2008,22( 3) : 597 [7] Matagos P,Schafer R W. Morphological filters-Part II: Their rela￾tions to median,order-statistic,and stack filters. IEEE Transac￾tions on Acoustics,Speech,and Signal Processing ASSP,2008,22 ( 3) : 1170 [8] Maragos P. Pattern spectrum of images and morphological shape￾size complexity / / IEEE International Conference on ICASSP'87. Dallas,1987: 241 [9] Maragos P. Pattern spectrum and multiscale shape representation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1989,11( 7) : 701 [10] Hao R J,Lu W X,Chu F L. Multiscale morphological analysis on fault signals of rolling element bearings. Journal of Mechanical Engineering,2008,44( 11) : 160 ( 郝如江,卢文秀,褚福磊. 滚动轴承故障信号的多尺度形 态学分析. 机械工程学报,2008,44( 11) : 160) [11] Jiang W L,Wu S Q. Multi-data fusion fault diagnosis method based on SVM and evidence theory. Chinese Journal of Scientific Instrument,2010,31( 8) : 1738 ( 姜万录,吴胜强. 基于 SVM 和证据理论的多数据融合故障 诊断方法. 仪器仪表学报,2010,31( 8) : 1738) [12] Zhou Z,Zhang Y Y,Zhu Y S,et al. Adaptive fault diagnosis of rolling bearings based on EEMD and demodulated resonance. Journal of Shock and Vibration,2013,32( 2) : 76 ( 周智,张优云,朱永生,等. 基于 EEMD 和共振解调的滚 动轴承自适应故障诊断. 振动与冲击,2013,32( 2) : 76) [13] Zhang L J,Xu J W,Yang J H,et al. Adaptive multiscale mor￾phology analysis and its application in fault diagnosis of bearings. Journal of University of Science and Technology Beijing,2008,30 ( 4) : 441 ( 章立军,徐金梧,阳建宏,等. 自适应多尺度形态学分析及 ·76·
<<向上翻页向下翻页>>
©2008-现在 cucdc.com 高等教育资讯网 版权所有