基于VMD-ICMSE和半监督判别SOINN L-Isomap的滚动轴承故障诊断

摘要
图/表
参考文献(21)
相关文章 (15)

全文: PDF (2199 KB) HTML (1 KB)
输出: BibTeX | EndNote (RIS)

摘要

针对从滚动轴承非线性、非平稳振动信号中提取故障特征困难的问题，提出一种基于半监督判别自组织增量学习神经网络界标点的等度规映射(SSDSL-Isomap)的滚动轴承故障诊断方法。利用基于变分模态分解的改进复合多尺度样本熵(VMD-ICMSE)从复杂域提取振动信号的故障特征，构建高维故障特征集；采用SSDSL-Isomap方法对高维故障特征集进行维数约简，提取出利于识别的低维、敏感故障特征子集；应用粒子群优化极限学习机(PSO-ELM)分类器对低维故障特征进行故障识别，判别故障类型。VMD-ICMSE方法集成了VMD自适应分解非线性信号与ICMSE衡量时间序列复杂性程度的优势，提高故障特征提取能力；SSDSL-Isomap方法综合了全局流形结构、半监督型双约束图构建以及SOINN界标点选取的优点，增强故障分类能力。调心球轴承故障诊断实验分析结果表明，该方法对实验数据的故障识别率达到100%。

	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
	戚晓利
	王振亚
	吴保林
	叶绪丹
	潘紫微

关键词 ：故障诊断, 滚动轴承, SSDSL-Isomap, 变分模态分解(VMD), 改进复合多尺度熵(ICMSE), 粒子群优化极限学习机(PSO-ELM)

Abstract：For the difficulty that extracting fault features from the nonlinear and non-stationary vibration signals of rolling bearings, a fault diagnosis method of rolling bearing based on semi-supervised discriminant self-organizing incremental neural network landmark Isomap (SSDSL-Isomap) was proposed.Firstly, the fault features of vibration signals were extracted from the complex domain by using the improved composite multiscale sample entropy based on variational mode decomposition (VMD-ICMSE), and the high-dimensional fault feature set was constructed.Secondly, the SSDSL-Isomap method was used to reduce the dimension of the high-dimensional fault feature set, and the low-dimensional and sensitive feature subset was extracted.Finally, low-dimensional features were input into a particle swarm optimization extreme learning machine (PSO-ELM) classifier to recognize fault types.The VMD-ICMSE method integrates the advantages of VMD in adaptive nonlinear signals decomposition and ICMSE to measure the complexity of time series, and improves the ability of fault feature extraction.The SSDSL-Isomap method considers global manifold structure information, semi-supervised double-constraint graph construction and SOINN landmark selection; therefore, it enhances the ability of fault classification.Experimental results of fault diagnosis on self-aligning ball bearings show that the identifying rate of the proposed method is 100%.

Key words： feature diagnosis rolling bearing SSDSL-Isomap variational mode decomposition（VMD） improved composite multiscale sample entropy(ICMSE) particle swarm optimization extreme learning machine(PSO-ELM)

收稿日期: 2018-07-05 出版日期: 2020-02-15

引用本文:

戚晓利，王振亚，吴保林，叶绪丹，潘紫微. 基于VMD-ICMSE和半监督判别SOINN L-Isomap的滚动轴承故障诊断[J]. 振动与冲击, 2020, 39(4): 252-260.
QI Xiaoli, WANG Zhenya, WU Baolin, YE Xudan, PAN Ziwei. A rolling bearing fault diagnosis method based on VMD-ICMSE and semi-supervised discriminant SOINN L-Isomap. JOURNAL OF VIBRATION AND SHOCK, 2020, 39(4): 252-260.

链接本文:

http://jvs.sjtu.edu.cn/CN/ 或 http://jvs.sjtu.edu.cn/CN/Y2020/V39/I4/252

[1] 戚晓利, 叶绪丹, 蔡江林,等. 基于变分模态分解与流形学习的滚动轴承故障特征提取方法[J]. 振动与冲击, 2018, 37(23):133-140.
QI Xiao-li, YE Xu-dan, CAI Jiang-lin, et al. Fault feature extraction method of rolling bearings based on VMD and manifold learning[J]. Journal of Vibration and Shock, 2018, 37(23): 133-140.
[2] OU Lu, YU De-jie, YANG Han-jian. A new rolling bearing fault diagnosis method based on GFT impulse component extraction[J]. Mechanical Systems and Signal Processing, 2016, 81:162-182.
[3] 胥永刚, 李凌均, 何正嘉. 近似熵及其在机械设备故障诊断中的应用[J]. 信息与控制, 2002, 31(6):547-551.
XU Yong-gang, LI Ling-jun, HE Zheng-jia. Approximate entropy and its applications in mechanical fault diagnosis[J]. Information and Control, 2002, 31(6):547-551.
[4] WANG Feng-tao, ZHANG Yang-yang, ZHANG Bin, et al. Application of wavelet packet sample entropy in the forecast of rolling element bearing fault trend[C]// International Conference on Multimedia and Signal Processing. IEEE, 2011:12-16.
[5] 冯辅周, 司爱威, 饶国强,等. 基于小波相关排列熵的轴承早期故障诊断技术[J]. 机械工程学报, 2012, 48(13):73-79.
FENG Fu-zhou, SI Ai-wei, RAO Guo-qiang. Early fault diagnosis technology for bearing based on wavelet correlation permutation entropy[J]. Journal of Mechanical Engineering, 2012, 48(13):73-79.
[6] 郑近德, 程军圣, 胡思宇. 多尺度熵在转子故障诊断中的应用[J]. 振动.测试与诊断, 2013, 33(2):294-297.
ZHENG Jin-de, CHEN Jun-sheng, HU Si-yu. Rotor fault diagnosis based on multiscale entropy[J]. Journal of Vibration Measurement and Diagnosis, 2013, 33(2):294-297.
[7] WU S D, WU C W, LIN S G, et al. Feature extraction for bearing fault diagnosis using composite multiscale entropy [C]// IEEE/ASME International Conference on Advanced Intelligent Mechatronics. IEEE, 2013:1615-1618.
[8] ZHENG Jin-de, JIANG Zhan-wei, PAN Zi-wei, et al. VMD based adaptive multiscale fuzzy entropy and its application to rolling bearing fault diagnosis[C]// International Conference on Sensing Technology. IEEE, 2016:1-4.
[9] TANG Bao-ping, SONG Tao, LI Feng, et al. Fault diagnosis for a wind turbine transmission system based on manifold learning and shannon wavelet support vector machine[J]. Renewable Energy, 2014, 62(3):1-9.
[10] 潘海洋, 杨宇, 李永国,等. 基于流形学习和改进VPMCD的滚动轴承故障诊断方法[J]. 振动工程学报, 2014, 27(6):934-941.
PAN Hai-yang, YANG Yu, LI Yong-guo, et al. The rolling bearings fault diagnosis method based on manifold learning and improved VPMCD[J]. Journal of Vibration Engineering, 2014, 27(6):934-941.
[11] 马萍, 张宏立, 范文慧. 基于局部与全局结构保持算法的滚动轴承故障诊断[J]. 机械工程学报, 2017, 53(2):20-25.
MA Ping, ZHANG Hong-li, FAN Wen-hui. Fault diagnosis of rolling bearings based on local and global preserving embedding algorithm[J]. Journal of Mechanical Engineering, 2017, 53(2):20-25.
[12] 姜战伟, 郑近德, 潘海洋,等. 基于多尺度时不可逆与t-SNE流形学习的滚动轴承故障诊断[J]. 振动与冲击, 2017, 36(17):61-68,84.
JIANG Zhan-wei, ZHENG Jin-de, PAN Hai-yang, et al. Rolling bearing fault diagnosis method based on multi-scale time irreversibility and t-SNE manifold learning[J]. Journal of Vibration and Shock, 2017, 36(17):61-68,84.
[13] SILVA V D, TENENBAUM J B. Sparse multidimensional scaling using landmark points[R]. Technical Report, Stanford University, 2004.
[14] 李锋, 汤宝平, 王家序,等. 基于图嵌入概率半监督判别分析的故障辨识[J]. 机械工程学报, 2017, 53(9):92-100.
LI Feng, TANG Bao-ping, WANG Jia-xu, et al. Fault identification method based on graph-implanted probability-based semi-supervised discriminant analysis [J]. Journal of Mechanical Engineering, 2017, 53(9):92-100.
[15] GENG Xing, ZHAN De-chuan, ZHOU Zhi-hua. Supervised nonlinear dimensionality reduction for visualization and classification[J]. IEEE Transactions on Systems Man and Cybernetics Part B Cybernetics a Publication of the IEEE Systems Man and Cybernetics Society, 2005, 35(6):1098-107.
[16] 张赟, 杨栋, 斯彦刚,等. 基于监督流形学习的航空发动机振动故障诊断方法[J]. 推进技术, 2017, 38(5):1147-1154.
ZHANG Yun, YANG Dong, SI Yan-gang, et al. Aero-engine vibration fault diagnosis based on supervised manifold learning[J].Journal of Propulsion Technology, 2017, 38(5): 1147 -1154.
[17] SU Zu-qiang, TANG Bao-ping, DENG Lei, et al. Fault diagnosis method using supervised extended local tangent space alignment for dimension reduction[J]. Measurement, 2015, 62:1-14.
[18] NAKAMURA Y, HASEGAWA O. Nonparametric density estimation based on self-organizing incremental neural network for large noisy data.[J]. IEEE Transactions on Neural Networks and Learning Systems, 2017, 28(1):8-17.
[19] 王杰, 毕浩洋. 一种基于粒子群优化的极限学习机[J]. 郑州大学学报(理学版), 2013, 45(1):100-104.
WANG Jie, BI Hao-yang. A new extreme learning machine optimized by PSO[J]. Journal of Zhengzhou University (Natural Science Edition), 2013, 45(1):100-104.
[20] SHI Hao, YIN Bao-qun, BAO Yi-zhao, et al. A novel landmark point selection method for L-ISOMAP[C]// IEEE International Conference on Control and Automation. IEEE, 2016: 621-625.
[21] YANG Xin, FU Hao-ying, ZHA Hong-yuan, et al. Semi-supervised nonlinear dimensionality reduction[C]// Internati-onal Conference on Machine Learning. ACM, 2006:1065-1072.