Damage sensitivity evaluation algorithm for rolling bearing features based on PCCDET

PDF(1226 KB)

Journal of Vibration and Shock ›› 2019, Vol. 38 ›› Issue (1) : 65-72.

WANG Zhihai,WU Xing,LIU Xiaoqin

Author information +

History +

Abstract

Aiming at the problem of not sufficiently considering identification precision’s interference factors affecting distance estimation’s evaluation performance, and the problem of damage level information of rolling bearing not able to be acquired effectively due to irrelevance or redundancy among multiple indicators, a feature evaluation method based on position compensation coefficient distance estimation technique (PCCDET) was proposed.Based on the traditional distance estimation technique, the median approach was introduced to improve the algorithm’s robustness.The position coefficient was used to screen out features to better suppress the overlap ratio among different states.Furthermore, the sensitivity of each feature was comprehensively investigated according to feature samples’ polymeriability, divisibility and position distribution relation.Finally, the acoustic emission data in different damage stages of rolling bearings tested on a self-made rolling bearing fatigue test platform were used to verify the effectiveness of the proposed algorithm.Through comparing it with the other distance estimation techniques, it was shown that the proposed method can better indicate rolling bearings’ damage sensitive features, and the screened sensitive feature set has higher and more stable identification accuracy.

Key words

estimation technology / rolling bearing / acoustic emission / damage sensibility assessment

Cite this article

EndNote

Ris (Procite)

Bibtex

Download Citations

WANG Zhihai,WU Xing,LIU Xiaoqin. Damage sensitivity evaluation algorithm for rolling bearing features based on PCCDET[J]. Journal of Vibration and Shock, 2019, 38(1): 65-72

References

[1] 陈进. 机械设备振动监测与故障诊断[M]. 上海交通大学出版社, 1999.
[2] Al-Ghamd A M, Mba D. A comparative experimental study on the use of acoustic emission and vibration analysis for bearing defect identification and estimation of defect size[J]. Mechanical Systems & Signal Processing, 2006, 20(7):1537-1571.
[3] 伍星. 基于数据挖掘的设备远程监测和故障诊断系统的研究[D]. 上海交通大学, 2005.
[4] 姚旭, 王晓丹, 张玉玺,等. 特征选择方法综述[J]. 控制与决策, 2012, 27(2):161-166.
YAO Xu,WANG Xiao-dan,ZHANG Yu-xi,QUAN Wen. Summary of feature selection algorithms [J]. Control and Decision, 2012, 27(2):161-166.
[5] Kira K, Rendell L A. The feature selection problem: traditional methods and a new algorithm[C]// National Conference on Artificial Intelligence. San Jose, Ca, July. DBLP, 1992:129-134.
[6] Kononenko I. Estimating attributes: Analysis and extensions of RELIEF[M]// Machine Learning: ECML-94. Springer Berlin Heidelberg, 1994:356-361.
[7] Xu L, Yan P, Chang T. Best first strategy for feature selection[C]// International Conference on Pattern Recognition, Nov. IEEE Xplore, 1988:706-708 vol.2.
[8] 蔡哲元, 余建国, 李先鹏,等. 基于核空间距离测度的特征选择[J]. 模式识别与人工智能, 2010, 23(2):235-240.
CAI Zhe-Yuan, YU Jian-Guo , LI Xian-Peng, JIN Zhen-Dong. Feature Selection Algorithm Based on Kernel Distance Measure [J]. Pattern Recognition and Artificial Intelligence, 2010, 23(2):235-240.
[9] 张宏莉, 鲁刚. 分类不平衡协议流的机器学习算法评估与比较[J]. 软件学报, 2012, 23(6):1500-1516.
ZHANG Hong-Li, LU Gang. Machine Learning Algorithms for Classifying the Imbalanced Protocol Flows： Evaluation and Comparison [J]. Journal of Software, 2012, 23(6):1500-1516.
[10] 王皓, 孙宏斌, 张伯明,等. 基于混合互信息的特征选择方法及其在静态电压稳定评估中的应用[J]. 中国电机工程学报, 2006, 26(7):77-81.
WANG Hao, SUN Hong-bin, ZHANG Bo-ming, GUO Qing-lai. Hybrid Mutual Information Based Feature Selection Method as Appied To Static Voltage Stability Assessment in Power Systems [J]. Proceedings of the CSEE, 2006, 26(7):77-81.
[11] 王玫, 孙奇慧, 付先武. 基于蚁群算法的铣削力信号特征选择方法[J]. 振动、测试与诊断, 2014, 34(2):372-378.
[12] 王宏超, 陈进, 董广明. 基于补偿距离评估-小波核PCA的滚动轴承故障诊断[J]. 振动与冲击, 2013, 32(18):87-90.
WANG Hong-chao, CHEN Jin, DONG Guang-ming. Fault diagnosis of rolling bearing based on compensation distance evaluation technique-wavelet kernel principal component analysis [J]. Journal of Vibration and Shock, 2013, 32(18):87-90.
[13] Yang Y, Pan H, Li M, et al. A roller bearing fault diagnosis method based on the improved ITD and RRVPMCD[J]. Measurement, 2014, 55(55):255–264.
[14] Xu Z, Xuan J, Shi T, et al. Application of a modified fuzzy ARTMAP with feature-weight learning for the fault diagnosis of bearing[J]. Expert Systems with Applications, 2009, 36(6):9961-9968.
[15] Chen X, Zhou J, Xiao J, et al. Fault diagnosis based on dependent feature vector and probability neural network for rolling element bearings[J]. Applied Mathematics & Computation, 2014, 247(C):835-847.
[16] Fatima S, Guduri B, Mohanty A R, et al. Transducer invariant multi-class fault classification in a rotor-bearing system using support vector machines[J]. Measurement, 2014, 58:363-374.
[17] Xu Z, Xuan J, Shi T, et al. Application of a modified fuzzy ARTMAP with feature-weight learning for the fault diagnosis of bearing[J]. Expert Systems with Applications, 2009, 36(6):9961-9968.
[18] Zeng M, Yang Y, Zheng J, et al. Maximum margin classification based on flexible convex hulls for fault diagnosis of roller bearings[J]. Mechanical Systems & Signal Processing, 2015, 66:533-545.
[19] Yang B S, Han T, An J L. Art-Kohonen neural network for fault diagnosis of rotating machinery [J]. Mechanical Systems and Signal Processing, 2004, 18(3): 645-657.
[20] Lei Y, He Z, Zi Y, et al. New clustering algorithm-based fault diagnosis using compensation distance evaluation technique[J]. Mechanical Systems & Signal Processing, 2008, 22(2):419-435.
[21] 吴瑕, 周焰, 杨龙坡,等. 基于聚类分析与几何的目标特征敏感性评估算法[J]. 控制与决策, 2012, 27(6):914-918.
WU Xia a,ZHOU Yan b,YANG Long-po b,CUI Jian b. Target feature sensitivity evaluation method based on clustering analysis and geometry [J]. Control and Decision, 2012, 27(6):914-918.
[22] 李孟源. 声发射检测及信号处理[M]. 科学出版社, 2010.
[23] 何正嘉, 陈进, 王太勇,等. 机械故障诊断理论及应用[M]. 高等教育出版社, 2010.
[24] 隋文涛. 滚动轴承表面损伤故障的特征提取与诊断方法研究[D]. 山东大学, 2011.