复合多尺度反向散布熵在轴承故障诊断中的应用

陈焱,郑近德,潘海洋,童靳于

振动与冲击 ›› 2022, Vol. 41 ›› Issue (19) : 55-63.

PDF(3083 KB)
PDF(3083 KB)
振动与冲击 ›› 2022, Vol. 41 ›› Issue (19) : 55-63.
论文

复合多尺度反向散布熵在轴承故障诊断中的应用

  • 陈焱,郑近德,潘海洋,童靳于
作者信息 +

Application of CMRDE in bearing fault diagnosis

  • CHEN Yan, ZHENG Jinde, PAN Haiyang, TONG Jinyu
Author information +
文章历史 +

摘要

滚动轴承发生故障时,其振动信号往往表现出非线性和非平稳特征。反向散布熵(Reverse Dispersion Entropy,RDE)能够有效衡量振动信号的复杂性变化和非线性动力学突变行为,但是单一尺度的RDE值并不能完全反映振动信号的复杂性和非线性特征。对此,受多尺度熵启发,同时针对传统多尺度粗粒化方式的不足,提出了复合多尺度反向散布熵(Composite Multi-scale Reverse Dispersion Entropy,CMRDE)。通过仿真信号分析,将CMRDE与多尺度反向散布熵(Multi-scale Reverse Dispersion Entropy,MRDE)和RDE进行了对比,结果表明:CMRDE不仅能反映不同尺度下信号复杂度的差异,且变化更平缓、波动更小。在此基础上,将CMRDE应用于滚动轴承故障特征提取,提出了一种基于CMRDE、集合经验模态分解和布谷鸟搜索算法优化支持向量机的滚动轴承故障诊断方法。将所提方法应用于滚动轴承实验数据分析,并通过与现有方法进行对比,结果表明:相较所对比的方法,所提方法能有效识别轴承故障类型,提取的故障特征误差更小、故障识别率更高。
关键词:反向散布熵;复合多尺度反向散布熵;滚动轴承;故障诊断

Abstract

The vibration signals are often nonlinear and non-stationary when the fault occurs. Reverse dispersion entropy (RDE) can effectively extract nonlinear dynamic fault features from vibration signals. However, the RDE value at a single scale cannot fully reflect the complexity and nonlinear characteristics of vibration signals. Inspired by multi-scale entropy (MSE) and aiming at the problem of coarse-graining in MSE, composite multi-scale reverse dispersion entropy (CMRDE) was proposed. CMRDE is compared with multi-scale reverse dispersion entropy (MRDE) and RDE through simulation signal analysis and the results show that it can reflect the difference of signal complexity at different scales and its varying trend is much smoother and the fluctuation is much smaller. Based on this, CMRDE was applied to the fault feature extraction of rolling bearings and a new rolling bearing fault diagnosis method was proposed based on CMRDE, ensemble empirical mode decomposition and cuckoo search support vector machine. The proposed fault diagnosis method was applied to analyze experimental data of rolling bearing with comparing with the existing methods and the analysis results indicate that the proposed method can effectively identify the fault location of rolling bearing and the errors of extracted fault feature is smaller and the fault recognition rate is higher than the compared methods.
Key words: reverse dispersion entropy; composite multi-scale reverse dispersion entropy; rolling bearing; fault diagnosis

关键词

反向散布熵 / 复合多尺度反向散布熵 / 滚动轴承 / 故障诊断

Key words

reverse dispersion entropy / composite multi-scale reverse dispersion entropy / rolling bearing / fault diagnosis

引用本文

导出引用
陈焱,郑近德,潘海洋,童靳于. 复合多尺度反向散布熵在轴承故障诊断中的应用[J]. 振动与冲击, 2022, 41(19): 55-63
CHEN Yan, ZHENG Jinde, PAN Haiyang, TONG Jinyu. Application of CMRDE in bearing fault diagnosis[J]. Journal of Vibration and Shock, 2022, 41(19): 55-63

参考文献

[1] 王靖岳, 王浩天, 郭立新. 齿轮传动系统故障诊断技术的研究进展[J]. 机械传动, 2016, 40(08): 185-192.
WANG Jingyue, Wang Haotian, Guo Lixing. Research progress of fault diagnosis technology for gear transmission system[J]. Mechanical Transmission, 2016, 40(08): 185-192.
[2] 周汝胜, 焦宗夏, 王少萍. 液压系统故障诊断技术的研究现状与发展趋势[J]. 机械工程学报, 2006(09): 6-14.
ZHOU Rusheng, JIAO Zongxia, WANG Shaoping. Current research and developing trends on fault diagnosis of hydraulic systems[J]. Chinese Journal of Mechanical Engineering, 2006(09): 6-14.
[3] 孟宗, 胡猛, 谷伟明, 等. 基于LMD多尺度熵和概率神经网络的滚动轴承故障诊断方法[J]. 中国机械工程, 2016, 27(04): 433-437.
MENG Zong, HU Meng, GU Weiming, et al. Rolling bearing fault diagnosis method based on LMD multi-scale entropy and probabilistic neural network[J]. China Mechanical Engineering, 2016, 27(04): 433-437.
[4] 刘中磊, 于德介, 刘坚. 基于故障特征频率的阶比双谱方法及其在滚动轴承故障诊断中的应用[J]. 中国电机工程学报, 2013, 33(33): 123-129+15.
LIU Zhonglei, YU Dejie, LIU Jian. Order bispectrum analysis based on fault characteristic frequency and its application to the fault diagnosis of rolling bearings[J]. Proceedings of the CSEF, 2013, 33(33): 123-129+15.
[5] 梁瑜, 贾利民, 蔡国强, 等. 滚动轴承的非线性动力学故障模型研究[J]. 中国铁道科学, 2014, 35(01): 98-104.
LIANG Yu, JIA Liming, CAI Guoqiang, et al. Research on nonlinear dynamics fault model of rolling bearing[J]. China Railway Science, 2014, 35(01): 98-104.
[6] Yan R, Gao R X. Approximate Entropy as a diagnostic tool for machine health monitoring[J]. Mechanical Systems & Signal Processing, 2007, 21(2): 824-839.
[7] YAN R Q, LIU Y B, GAO R X. Permutati-on entropy: A nonlinear statistical measure for status characterization of rotary machines[J]. Mechanical Systems and Signal Processing, 2012, 29(5): 474-484.
[8] Bilal F, Chen B D, Andreas K, et al. Weighted-permutation entropy: a complexity measure for time series incorporating amplitude information[J]. Physical review. E, Statistical, nonlinear, and soft matter physics, 2013, 87(2): 1-7.
[9] Rostaghi M, Azami H. Dispersion entropy: a measure for time series analysis[J]. IEEE Signal Processing Letters, 2016, 23(5): 610-614.
[10] Bandt C. A New Kind of Permutation Entropy Used to Classify Sleep Stages from Invisible EEG Microstructure[J]. Entropy, 2017, 19(5): 197.
[11] Li Y, Gao X, Wang L. Reverse Dispersion Entropy: A New Complexity Measure for Sensor Signal[J]. Sensors, 2019, 19(23):1-14.
[12] Li Y, Jiao S, Geng B, et al. Research on feature extraction of ship-radiated noise based on multi-scale reverse dispersion entropy[J]. Applied Acoustics, 2021, 173(1):107737.
[13] Zheng J D, Pan H Y, Tong J Y, et al. Generalized refined composite multiscale fuzzy entropy and multi-cluster feature selection based intelligent fault diagnosis of rolling bearing[J]. ISA Transactions, 2021, 1-16.
[14] Billah K, Shinozuka M. Numerical method for colored-noise generation and its application to a bistable system[J]. Physical Review A, 1992, 46(12):7492-7495.
[15] Costa M, Goldberger A L, Peng C K. Multiscale entropy analysis of biological signals[J]. Physical Review E Statistical Nonlinear & Soft Matter Physics, 2005, 71(2): 021906.
[16] Costa M, Goldberger A, Peng C. Multiscale entropy analysis of physiologic time series[J]. Phys Rev Lett, 2002, 89: 062102.
[17] 郑近德, 刘涛, 孟瑞, 等. 基于广义复合多尺度排列熵与PCA的滚动轴承故障诊断方法[J]. 振动与冲击, 2018, 37(20): 61-66.
ZHENG Jinde, LIU Tao, MENG Rui, et al. Generalized composite multi-scale permutation entropy and PCA based fault diagnosis of rolling bearings[J]. Journal of Vibration and Shock, 2018, 37(20): 61-66.
[18] 郑近德, 李从志, 潘海洋. 复合多尺度散布熵在滚动轴承故障诊断中的应用[J]. 噪声与振动控制, 2018, 38(S2): 653-656.
ZHENG Jinde, LI Congzhi, PAN Haiyang. Application of composite multi-scale dispersion entropy in rolling bearing fault diagnosis[J]. Noise and Vibration Control, 2018, 38(S2): 653-656.
[19] 董超. 机械诊断现代信号处理及故障识别关键技术研究[J]. 中国机械, 2014(8): 101-102.
DONG Chao. Research on Key Technologies of modern signal processing and fault identification in mechanical diagnosis[J]. China machinery, 2014(8): 101-102.
[20] Wu Z, Huang N E. Ensemble empirical mode decomposition: a noise assisted data analysis method[J]. Advances in Adaptive Data Analysis, 2009, 1(1): 1-41.
[21] 王婷. EMD算法研究及其在信号去噪中的应用[D]. 哈尔滨工程大学, 2010: 1-128.
WANG Ting. Research on EMD algorithm and its application in signal denoising[D]. Harbin Engineering University, 2010: 1-128.
[22] 胡爱军, 孙敬敬, 向玲. 经验模态分解中的模态混叠问题[J]. 振动、测试与诊断, 2011,31(04): 429-434+532-533.
HU Aijun, SUN Jingjing, XIANG Ling. Mode mixing in empirical mode decomposition[J]. Journal of Vibration Measurement & Diagnosis, 2011,31(04): 429-434+532-533.
[23] Chang C C, Lin C J. LIBSVM[J]. ACM Transactions on Intelligent Systems and Technology (TIST), 2011, 2(3):1-27.
[24] 梁治华, 曹江涛, 姬晓飞. 基于EEMD和CS-SVM的滚动轴承故障诊断研究[J]. 机电工程, 2019, 36(06): 622-627.
LIANG Zhihua, CAO Jiangtao, JI Xiaofei. Fault diagnosis of rolling bearing based on EEMD and CS-SVM[J]. Journal of Mechanical & Electrical Engineering, 2019, 36(06): 622-627.
[25] 李从志, 郑近德, 潘海洋, 等. 基于精细复合多尺度散布熵与支持向量机的滚动轴承故障诊断方法[J]. 中国机械工程, 2019, 30(14): 1713-1719+1726.
LI Congzhi, ZHENG Jinde, PAN Haiyang, et al. Fault diagnosis method of rolling bearings based on refined composite multi-scale dispersion entropy and support vector machine[J]. China Mechanical Engineering, 2019, 30(14): 1713-1719+1726.

PDF(3083 KB)

Accesses

Citation

Detail

段落导航
相关文章

/