基于基本尺度熵与GG模糊聚类的轴承性能退化状态识别
|
摘要
针对轴承性能退化状态的识别问题,提出一种基于基本尺度熵与GG聚类的退化状态识别方法。首先分析轴承性能退化过程中的基本尺度熵演化规律,并分析该参数的单调性与敏感性。考虑到轴承退化状态在时间尺度的连续性,构建基本尺度熵、有效值以及退化时间的三维退化特征向量,并采用GG模糊聚类方法对轴承性能退化状态的不同阶段进行划分,实现对性能退化状态的识别。采用来自IEEE PHM 2012的轴承全寿命试验数据进行实例分析,并与FCM、GK算法进行对比,结果表明本文所提出的方法聚类效果更优,同一退化状态内的时间聚集度更高,能够为轴承性能退化状态的识别提供一种有效的途径。
A method based on basic scale entropy and GG clustering was proposed to solve the problem of bearing performance degradation state recognition. The evolution law of the basic scale entropy in bearing performance degradation process was analyzed firstly, and its monotonicity and sensitivity were emphasized. Considering the continuity of bearing degradation state on time scale, a 3 D degradation feature vector was constructed with basic scale entropy, its root mean square and degradation time, and GG fuzzy clustering method was used to divide different stages of bearing performance degradation state to realize bearing performance degradation state recognition. Bearing full lifetime test data of IEEE PHM 2012 was adopted to do example analysis, and the results were compared with those using FCM and GK algorithms. The results showed that the proposed method's clustering effect is better and its time aggregation degree is higher in the same degradation state; the method can provide an effective way for bearing performance degradation state recognition.
A method based on basic scale entropy and GG clustering was proposed to solve the problem of bearing performance degradation state recognition. The evolution law of the basic scale entropy in bearing performance degradation process was analyzed firstly, and its monotonicity and sensitivity were emphasized. Considering the continuity of bearing degradation state on time scale, a 3 D degradation feature vector was constructed with basic scale entropy, its root mean square and degradation time, and GG fuzzy clustering method was used to divide different stages of bearing performance degradation state to realize bearing performance degradation state recognition. Bearing full lifetime test data of IEEE PHM 2012 was adopted to do example analysis, and the results were compared with those using FCM and GK algorithms. The results showed that the proposed method's clustering effect is better and its time aggregation degree is higher in the same degradation state; the method can provide an effective way for bearing performance degradation state recognition.
引文
[1] VOGL G W, WEISS B A, HELU M. A review of diagnostic and prognostic capabilities and best practices for manufacturing[J]. Journal of Intelligent Manufacturing, 2016(6):1-17.
[2] RAI A, UPADHYAY S H. A review on signal processing techniques utilized in the fault diagnosis of rolling element bearings[J]. Tribology International, 2016, 96:289-306.
[3] LóPEZ A J G, MáRQUEZ A C, MACCHI M, et al. Prognostics and health management in advanced maintenance systems[J]. Production Planning & Control, 2018,27(12):991-1004.
[4] YI C, LV Y, GE M, et al. Tensor singular spectrum decomposition algorithm based on permutation entropy for rolling bearing fault diagnosis[J]. Entropy, 2017, 19(4):139-145.
[5] YI C, LV Y, DANG Z, et al. Quaternion singular spectrum analysis using convex optimization and its application to fault diagnosis of rolling bearing[J]. Measurement, 2017, 103:321-332.
[6] ZHENG J, PAN H, CHENG J. Rolling bearing fault detection and diagnosis based on composite multiscale fuzzy entropy and ensemble support vector machines[J]. Mechanical Systems & Signal Processing, 2017, 85:746-759.
[7] ZHOU J, GUO H, ZHANG L, et al. Bearing performance degradation assessment using lifting wavelet packet symbolic entropy and SVDD[J]. Shock and Vibration, 2016(6):1-10.
[8] ZHU K. Performance degradation assessment of rolling element bearings based on hierarchical entropy and general distance[J]. Journal of Vibration & Control, 2017(6):107-114.
[9] YU H, LI H, XU B. Rolling bearing degradation state identification based on LCD relative spectral entropy[J]. Journal of Failure Analysis & Prevention, 2016, 16(4):655-666.
[10] AOUABDI S, TAIBI M, BOURAS S, et al. Using multi-scale entropy and principal component analysis to monitor gears degradation via the motor current signature analysis[J]. Mechanical Systems & Signal Processing, 2017, 90:298-316.
[11] LI Y, XU M, WEI Y, et al. A new rolling bearing fault diagnosis method based on multiscale permutation entropy and improved support vector machine based binary tree[J]. Measurement, 2016, 77:80-94.
[12] 李锦,宁新宝. 短时心率变异性信号的基本尺度熵分析[J]. 科学通报,2005(14):1438-1441. LI Jin, NING Xinbao. Basic scale entropy analysis of short-term heart rate variability signals[J]. Chinese Science Bulletin, 2005(14):1438-1441.
[13] 黄晓林,崔胜忠,宁新宝,等. 心率变异性基本尺度熵的多尺度化研究[J]. 物理学报,2009,58(12):8160-8165. HUANG Xiaolin, CUI Shengzhong, NING Xinbao. Multiscale base-scale entropy analysis of heart rate variability[J]. Acta Phys Sin, 2009,58(12):8160-8165.
[14] 刘大钊,王俊,李锦,等. 颠倒睡眠状态调制心率变异性信号的功率谱和基本尺度熵分析[J]. 物理学报,2014,63(19):434-440. LIU Dazhao, WANG Jun, LI Jin, et al. Analysis on power spectrum and base-scale entropy for heart rate variability signals modulated by reversed[J]. Acta Phys Sin, 2014,63(19): 434-440.
[15] 刘铁兵,姚文坡,宁新宝,等. 功能磁共振成像的基本尺度熵分析[J]. 物理学报,2013,62(21):501-506. LIU Tiebing, YAO Wenpo, NING Xinbao,et al. The base scale entropy analysis of fMRI[J]. Acta Phys Sin,2013, 62(21): 501-506.
[16] 钟先友,赵春华,陈保家,等. 基于改进的本征时间尺度分解和基本尺度熵的齿轮故障诊断方法[J]. 中南大学学报(自然科学版),2015,46(3):870-877. ZHONG Xianyou, ZHAO Chunhua, CHEN Baojia, et al. Gear fault diagnosis method based on IITD and base-scale entropy[J]. Journal of Central South University (Science and Technology), 2015,46(3):870-877.
[17] 许凡,方彦军,张荣,等. 基于LMD基本尺度熵的AP聚类滚动轴承故障诊断[J]. 计算机应用研究,2017,34(6):1732-1736. XU Fan, FANG Yanjun, ZHANG Rong,et al. Roller bearings faults diagnosis method based on LMD,base-scale entropy and AP clustering[J]. Application Research of Computers,2017,34(6):1732-1736.
[18] WANG B, HU X, LI H. Rolling bearing performance degradation condition recognition based on mathematical morphological fractal dimension and fuzzy C-means[J]. Measurement, 2017,109:1-8.
[19] RAI A, UPADHYAY S H. Bearing performance degradation assessment based on a combination of empirical mode decomposition and k-medoids clustering[J]. Mechanical Systems & Signal Processing, 2017, 93:16-29.
[20] 黄友朋,赵山,许凡,等. EEMD排列熵与PCA-GK的滚动轴承聚类故障诊断[J]. 河南科技大学学报(自然科学版),2017(2):17-24. HUANG Youpeng, ZHAO Shan, XU Fan, et al. Rolling bearing clustering faults diagnosis based on EEMD,permutation entropy and PCA-GK[J]. Journal of Henan University of Science and Technology(Natural Science), 2017(2):17-24.
[21] 张立国,李盼,李梅梅,等. 基于ITD模糊熵和GG聚类的滚动轴承故障诊断[J]. 仪器仪表学报,2014,35(11):2624-2632. ZHANG Liguo, LI Pan, LI Meimei,et al. Fault diagnosis of rolling bearing based on ITD fuzzy entropy and GG clustering[J]. Chinese Journal of Scientific Instrument, 2014,35(11): 2624-2632.
[22] LI Yaolong, LI Hongru, WANG Bing, et al. Rolling element bearing performance degradation assessment using variational mode decomposition and Gath-Geva clustering time series segmentation[J]. International Journal of Rotating Machinery, 2017(10):1-12.
[23] YU K, LIN T R, TAN J W. A bearing fault diagnosis technique based on singular values of EEMD spatial condition matrix and Gath-Geva clustering[J]. Applied Acoustics, 2017, 121:33-45.
[24] 张印,李锦,姚沁,等. 不同趋势下两种熵测度的稳定性[J]. 陕西师范大学学报(自然科学版),2017,45(3):29-35. ZHANG Yin,LI Jin, YAO Qin, et al. Stability of entropy analysis for signal with different trends[J]. Journal of Shaanxi Normal University (Natural Science Edition), 2017,45(3):29-35.
[25] 樊春玲,李浩杰,孙迎慧. 基于多尺度化基本尺度熵的两相流流型特性分析[J]. 青岛科技大学学报(自然科学版),2015,36(6):680-684. FAN Chunling, LI Haojie, SUN Yinghui. Characterization of two-phase flow pattern based on multiscale base-scale entropy[J].Journal of Qingdao University of Science and Technology(Natural Science Edition),2015,36(6):680-684.
[26] WANG C, YU J, ZHU J. Analysis of convergence properties for Gath-Geva clustering using Jacobian matrix[J]. Chinese Conference on Pattern Recognition,2016, 662: 650-662.
[27] LI P, ZHAO S L, ZHANG R C.A cluster analysis selection strategy for super saturated designs[J]. Computational Statistics & Data Analysis,2010,54(6):1605-1612.
[28] NECTOUX P, GOURIVEAU R, MEDJAHER K, et al. PRONOSTIA: an experimental platform for bearings accelerated degradation tests[C]//IEEE International Conference on Prognostics and Health Management. Denver, CO, 2012.
[2] RAI A, UPADHYAY S H. A review on signal processing techniques utilized in the fault diagnosis of rolling element bearings[J]. Tribology International, 2016, 96:289-306.
[3] LóPEZ A J G, MáRQUEZ A C, MACCHI M, et al. Prognostics and health management in advanced maintenance systems[J]. Production Planning & Control, 2018,27(12):991-1004.
[4] YI C, LV Y, GE M, et al. Tensor singular spectrum decomposition algorithm based on permutation entropy for rolling bearing fault diagnosis[J]. Entropy, 2017, 19(4):139-145.
[5] YI C, LV Y, DANG Z, et al. Quaternion singular spectrum analysis using convex optimization and its application to fault diagnosis of rolling bearing[J]. Measurement, 2017, 103:321-332.
[6] ZHENG J, PAN H, CHENG J. Rolling bearing fault detection and diagnosis based on composite multiscale fuzzy entropy and ensemble support vector machines[J]. Mechanical Systems & Signal Processing, 2017, 85:746-759.
[7] ZHOU J, GUO H, ZHANG L, et al. Bearing performance degradation assessment using lifting wavelet packet symbolic entropy and SVDD[J]. Shock and Vibration, 2016(6):1-10.
[8] ZHU K. Performance degradation assessment of rolling element bearings based on hierarchical entropy and general distance[J]. Journal of Vibration & Control, 2017(6):107-114.
[9] YU H, LI H, XU B. Rolling bearing degradation state identification based on LCD relative spectral entropy[J]. Journal of Failure Analysis & Prevention, 2016, 16(4):655-666.
[10] AOUABDI S, TAIBI M, BOURAS S, et al. Using multi-scale entropy and principal component analysis to monitor gears degradation via the motor current signature analysis[J]. Mechanical Systems & Signal Processing, 2017, 90:298-316.
[11] LI Y, XU M, WEI Y, et al. A new rolling bearing fault diagnosis method based on multiscale permutation entropy and improved support vector machine based binary tree[J]. Measurement, 2016, 77:80-94.
[12] 李锦,宁新宝. 短时心率变异性信号的基本尺度熵分析[J]. 科学通报,2005(14):1438-1441. LI Jin, NING Xinbao. Basic scale entropy analysis of short-term heart rate variability signals[J]. Chinese Science Bulletin, 2005(14):1438-1441.
[13] 黄晓林,崔胜忠,宁新宝,等. 心率变异性基本尺度熵的多尺度化研究[J]. 物理学报,2009,58(12):8160-8165. HUANG Xiaolin, CUI Shengzhong, NING Xinbao. Multiscale base-scale entropy analysis of heart rate variability[J]. Acta Phys Sin, 2009,58(12):8160-8165.
[14] 刘大钊,王俊,李锦,等. 颠倒睡眠状态调制心率变异性信号的功率谱和基本尺度熵分析[J]. 物理学报,2014,63(19):434-440. LIU Dazhao, WANG Jun, LI Jin, et al. Analysis on power spectrum and base-scale entropy for heart rate variability signals modulated by reversed[J]. Acta Phys Sin, 2014,63(19): 434-440.
[15] 刘铁兵,姚文坡,宁新宝,等. 功能磁共振成像的基本尺度熵分析[J]. 物理学报,2013,62(21):501-506. LIU Tiebing, YAO Wenpo, NING Xinbao,et al. The base scale entropy analysis of fMRI[J]. Acta Phys Sin,2013, 62(21): 501-506.
[16] 钟先友,赵春华,陈保家,等. 基于改进的本征时间尺度分解和基本尺度熵的齿轮故障诊断方法[J]. 中南大学学报(自然科学版),2015,46(3):870-877. ZHONG Xianyou, ZHAO Chunhua, CHEN Baojia, et al. Gear fault diagnosis method based on IITD and base-scale entropy[J]. Journal of Central South University (Science and Technology), 2015,46(3):870-877.
[17] 许凡,方彦军,张荣,等. 基于LMD基本尺度熵的AP聚类滚动轴承故障诊断[J]. 计算机应用研究,2017,34(6):1732-1736. XU Fan, FANG Yanjun, ZHANG Rong,et al. Roller bearings faults diagnosis method based on LMD,base-scale entropy and AP clustering[J]. Application Research of Computers,2017,34(6):1732-1736.
[18] WANG B, HU X, LI H. Rolling bearing performance degradation condition recognition based on mathematical morphological fractal dimension and fuzzy C-means[J]. Measurement, 2017,109:1-8.
[19] RAI A, UPADHYAY S H. Bearing performance degradation assessment based on a combination of empirical mode decomposition and k-medoids clustering[J]. Mechanical Systems & Signal Processing, 2017, 93:16-29.
[20] 黄友朋,赵山,许凡,等. EEMD排列熵与PCA-GK的滚动轴承聚类故障诊断[J]. 河南科技大学学报(自然科学版),2017(2):17-24. HUANG Youpeng, ZHAO Shan, XU Fan, et al. Rolling bearing clustering faults diagnosis based on EEMD,permutation entropy and PCA-GK[J]. Journal of Henan University of Science and Technology(Natural Science), 2017(2):17-24.
[21] 张立国,李盼,李梅梅,等. 基于ITD模糊熵和GG聚类的滚动轴承故障诊断[J]. 仪器仪表学报,2014,35(11):2624-2632. ZHANG Liguo, LI Pan, LI Meimei,et al. Fault diagnosis of rolling bearing based on ITD fuzzy entropy and GG clustering[J]. Chinese Journal of Scientific Instrument, 2014,35(11): 2624-2632.
[22] LI Yaolong, LI Hongru, WANG Bing, et al. Rolling element bearing performance degradation assessment using variational mode decomposition and Gath-Geva clustering time series segmentation[J]. International Journal of Rotating Machinery, 2017(10):1-12.
[23] YU K, LIN T R, TAN J W. A bearing fault diagnosis technique based on singular values of EEMD spatial condition matrix and Gath-Geva clustering[J]. Applied Acoustics, 2017, 121:33-45.
[24] 张印,李锦,姚沁,等. 不同趋势下两种熵测度的稳定性[J]. 陕西师范大学学报(自然科学版),2017,45(3):29-35. ZHANG Yin,LI Jin, YAO Qin, et al. Stability of entropy analysis for signal with different trends[J]. Journal of Shaanxi Normal University (Natural Science Edition), 2017,45(3):29-35.
[25] 樊春玲,李浩杰,孙迎慧. 基于多尺度化基本尺度熵的两相流流型特性分析[J]. 青岛科技大学学报(自然科学版),2015,36(6):680-684. FAN Chunling, LI Haojie, SUN Yinghui. Characterization of two-phase flow pattern based on multiscale base-scale entropy[J].Journal of Qingdao University of Science and Technology(Natural Science Edition),2015,36(6):680-684.
[26] WANG C, YU J, ZHU J. Analysis of convergence properties for Gath-Geva clustering using Jacobian matrix[J]. Chinese Conference on Pattern Recognition,2016, 662: 650-662.
[27] LI P, ZHAO S L, ZHANG R C.A cluster analysis selection strategy for super saturated designs[J]. Computational Statistics & Data Analysis,2010,54(6):1605-1612.
[28] NECTOUX P, GOURIVEAU R, MEDJAHER K, et al. PRONOSTIA: an experimental platform for bearings accelerated degradation tests[C]//IEEE International Conference on Prognostics and Health Management. Denver, CO, 2012.