基于多尺度高阶奇异谱熵的信号特征提取方法

doi:10.3969/j.issn.1000-1158.2019.05.18

摘要
图/表
参考文献(20)
相关文章 (15)

全文: PDF (2096 KB) HTML (1 KB)
输出: BibTeX | EndNote (RIS)

摘要提出了基于变分模态分解(VMD)的高阶奇异谱熵的特征提取方法,并应用在滚动轴承故障诊断中。首先,使用4阶累积量切片代替奇异谱熵分析(SSEA)的协方差矩阵,引入VMD分解实现方法多尺度化,提出信号多分辨高阶奇异谱熵分析(M-HSSEA)方法;通过信号分析,VMD解决了模态混叠的问题,且能够实现信号滤波,同时该方法提取的熵特征向量增强了相空间重构参数鲁棒性;通过和小波奇异谱提取特征的方法对比,结果表明所提出的方法在克服频率混叠现象,提取的特征点总体离散度小等方面更具优势;最后,结合深度信念网络分类器实现了对故障的分类,实验结果验证了所提方法的有效性和可行性。

	服务

	把本文推荐给朋友
	加入我的书架
	加入引用管理器
	E-mail Alert
	RSS
	作者相关文章

关键词 ：计量学, 变分模态分解, 故障诊断, 多尺度, 深度信念网络

Abstract：A feature extraction method based on variational mode decomposition (VMD) for high-order singular spectral entropy is proposed and applied to fault diagnosis of rolling bearings. Firstly, the fourth-order cumulant slice is used to replace the covariance matrix of singular spectrum entropy analysis (SSEA), and the VMD decomposition method is introduced to multi-scale. The multi-resolution high-order singular spectrum entropy analysis of bearing vibration signal is proposed. Through signal analysis, VMD solves the problem of modal aliasing and can realize signal filtering. At the same time, the entropy feature vector extracted by the method enhances the robustness of phase space reconstruction parameters. By comparing with the wavelet singular spectrum extraction feature, the results show that the proposed method is more advantageous in overcoming the frequency aliasing phenomenon and the small overall dispersion of feature points. Finally, the classification of faults is realized by combining the deep belief network classifier. The validity and feasibility of the proposed method are verified by the results.

Key words： metrology variational mode decomposition fault diagnosis multi-scale deep belief network

收稿日期: 2017-09-11 发布日期: 2019-09-01

PACS:	TB936
	TB973

基金资助:国家重点研发项目(2018YFB0905500);国家自然科学基金(51875498);河北省自然科学基金(E2018203439,E2018203339,F2016203496);河北省专业学位研究生教学案例库建设项目(KCJSZ2017022)

通讯作者: 张立国为本文通讯作者。Email: zlgtime@163.com E-mail: zlgtime@163.com

作者简介: 张淑清(1966-),河北秦皇岛人,燕山大学教授,主要研究方向为弱信号检测,智能信号处理及故障诊断。 Email: zhshq-yd@163.com

引用本文:

张淑清,陈荣飞,张立国,姚家琛,穆勇,刘勇,黄毅臣. 基于多尺度高阶奇异谱熵的信号特征提取方法[J]. 计量学报, 2019, 40(5): 848-854.
ZHANG Shu-qing,CHEN Rong-fei,ZHANG Li-guo,YAO Jia-chen,MU Yong2LIU Yong,HUANG Yi-chen. Signal Feature Extraction Method Based on Multi-scale High-order Singular Spectrum Entropy. Acta Metrologica Sinica, 2019, 40(5): 848-854.

链接本文:

http://jlxb.china-csm.org:81/Jwk_jlxb/CN/10.3969/j.issn.1000-1158.2019.05.18 或 http://jlxb.china-csm.org:81/Jwk_jlxb/CN/Y2019/V40/I5/848

［1］Ghafari S H, Golnaraghi F, Ismail F. Effect of localized faults on chaotic vibration of rolling element bearings［J］. Nonlinear Dynamics, 2008, 53(4): 287-301.
［2］Luo S, Cheng J, Zeng M, et al. An intelligent fault diagnosis model for rotating machinery based on multi-scale higher order singular spectrum analysis and GA-VPMCD［J］. Measurement, 2016, 87: 38-50.
［3］Yi C, Lü 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.
［4］杨丰源, 宋辉, 程序, 等. 基于多分辨高阶奇异谱熵分析的局部放电信号特征提取［J］. 电网技术, 2016, 40(10): 3265-3271.
Yang F Y, Song H, Cheng X, et al. Partial Feature Extraction Based on Multi-Resolution Analysis of Higher-Order Singular Spectrum Entropy［J］. Power Systerm Technolog, 2016, 40(10): 3265-3271.
［5］李巧艺, 单奇,陈跃威. 基于HHT边际谱熵-马氏距离的滚动轴承故障诊断［J］. 燕山大学学报,2016,40(6): 493-498.
Li Q Y, Shan Q, Chen Y W. Fault diagnosis of rolling bearing based on HHT marginal spectrum entropy-Mahalanobis distance［J］. Journal of Yanshan University, 2016,40(6): 493-498.
［6］王延东, 张涛, 杨春雷, 等. 基于经验模态分解/高阶统计法实现微机械陀螺降噪［J］. 光学精密工程, 2016, 24(3): 574-581.
Wang Y D, Zhang T, Yang C L, et al. MEMS gyro denoising by EMD-HOS method［J］. Optional and Precision Engineering, 2016, 24(3): 574-581.
［7］张家为. 高阶统计量的应用［J］. 中国科技信息, 2010, (24): 49-50.
Zhang J W. Application of higher order statistics［J］. China Science and Technology Information, 2010, (24): 49-50.

［8］时培明,苏晓,袁丹真,等. 基于VMD和变尺度多稳随机共振的微弱故障信号特征提取方法［J］. 计量学报, 2018,39(4):515-520.
Shi P M,Su X,Yuan D Z,et al. A New Feature Extraction Method of Weak Fault Signal Based on VMD and Re-scaling Multi-stable Stochastic Resonance［J］. Acta Metrologica Sinica,2018,39(4): 515-520.

［9］Dragomiretskiy K, Zosso D. Variational mode decomposition［J］. IEEE transactions on signal processing, 2014, 62(3): 531-544.
［10］付秀伟,高兴泉. 基于傅里叶分解与奇异值差分谱的滚动轴承故障诊断方法［J］. 计量学报, 2018, 39(5): 688-692.
Fu X W,Gao X Q. Rolling Bearing Fault Diagnosis Based on FDM and Singular Value Difference Spectrum［J］. Acta Metrologica Sinica, 2018,39(5):688-692.
［11］孟宗,邢婷婷,张圆圆,等. 基于关联维数和线段聚类的滚动轴承故障诊断［J］. 计量学报, 2019, 40(1): 100-105.
Meng Z,Xing T T,Zhang Y Y,et al. Fault Diagnosis of Rolling Bearing Based on Correlation Dimension and Segment Clustering［J］. Acta Metrologica Sinica, 2019, 40(1): 100-105.

［12］Wang Y, Markert R, Xiang J, et al. Research on variational mode decomposition and its application in detecting rub-impact fault of the rotor system［J］. Mechanical Systems & Signal Processing, 2015, 60-61: 243-251.
［13］张淑清, 邢婷婷, 何红梅, 等. 基于VMD及广义分形维数矩阵的滚动轴承故障诊断［J］. 计量学报, 2017, 38(4): 439-443.
Zhang S Q, Xing T T, He H M, et al. Bearing Fault Diagnosis Method Based on VMD and Grnrealized Fractal Dimension Matrix［J］. Acta Metrologica Sinic, 2017, 38(4): 439-443.
［14］谢平, 江国乾, 武鑫, 等. 本征时间尺度排序熵及其在滚动轴承故障诊断中的应用［J］. 燕山大学学报, 2013, 37(2): 179-183.
Xie P, Jiang G Q, Wu X, et al. Intrinsic time scale sorting entropy and its application to fault diagnosis of rolling bearings［J］. Journal of Yanshan University, 2013, 37(2): 179-183.

［15］刘元峰, 赵玫. 基于奇异谱分析的混沌序列降噪［J］. 上海交通大学学报, 2003, 37(5): 778-780.
Liu Y F, Zhao M. DE-Noising of Chaotic Time Series Based on Singular Spectrum Analysis［J］. Journal of Shang Hai Jiao Tong University, 2003, 37(5): 778-780.
［16］Yang F Y, Song H, Sheng G H, et al. Partial discharge pattern recognition based on adaptive multi-resolution analysis of higher-order Singular Spectrum Entropy［C］//2016 International Conference on Condition Monitoring and Diagnosis (CMD). Xian, China, 2016: 829-832.
［17］杨向锋, 张效民, 李亚安. 一种基于高阶统计量的相空间重构方法［J］. 信号处理, 2006, 22(1): 5-8.
Yang X F, Zhang X M, Li Y A. State Space Reconstruction Based on Highter-Order Statistics［J］. Signal Processing, 2006,22(1): 5-8.
［18］Chen Z Y, Zeng X Q, Li W H, et al. Machine fault classification using deep belief network［C］// 2016 IEEE International. Instrumentation and Measurement Technology Conference Proceedings (I2MTC). Taipei, China, 2016: 1-6.
［19］张淑清, 胡永涛, 姜安琦, 等. 基于双树复小波和深度信念网络的轴承故障诊断［J］. 中国机械工程, 2017, 28(5): 532-536.
Zhang S Q, Hu Y T, Jiang A Q, et al. Bearing Fault Diagnosis Based on DTCWT and DBN［J］. China Mechanical Engineering, 2017, 28(5): 532-536.
［20］张淑清, 李新新, 张立国, 等. 基于符号分析的极大联合熵延迟时间求取方法［J］. 物理学报, 2013, 62(11): 118-123.
Zhang S Q, Li X X, Zhang L G, et al. Maximum joint entropy delay time method based on symbol analysis ［J］. Acta Phys Sin, 2013, 62(11): 118-123.