基于多特征提取和改进马田系统的滚动轴承故障分类方法研究

PDF(1220 KB)

振动与冲击 ›› 2020, Vol. 39 ›› Issue (6) : 249-256.

论文

彭宅铭，程龙生，詹君，姚启峰

作者信息 +

Fault classification method for rolling bearings based on the multi-featureextraction and modified Mahalanobis-Taguchi system

PENG Zhaiming, CHENG Longsheng, ZHAN Jun, YAO Qifeng

Author information +

文章历史 +

摘要

为提高旋转机械的使用效率，及时识别滚动轴承的潜在故障，提出一种基于多特征提取和改进马田系统(MTS)的故障分类方法。通过时域、频域和自适应白噪声的完备经验模态分解（CEEMDAN）提取多维特征，构建初始特征集。结合马田系统和有向非循环图（DAG）的特点，构建DAG-MTS多分类模型，并将其运用到轴承故障诊断中。利用滚动轴承故障数据测试该模型的有效性和实用性，结果表明，该模型能够准确识别出滚动轴承的故障。

Abstract

In order to improve the running efficiency of rotating machinery and to identify its potential failure, a fault classification method based on the multi-feature extraction and improved Mahalanobis Taguchi system (MTS) was proposed.The methods of time domain, frequency domain and the complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) were combinedly used to obtain a multi-dimensional feature set.Integrating the advantages of the MTS and the directed acyclic graph (DAG), a DAG-MTS multi-class classification model was constructed and applied to bearing fault diagnosis.The effectiveness and applicability of the model was verified by using experimental data.The results show that the model can quickly and accurately identify the fault of rolling bearings.

导出引用

彭宅铭，程龙生，詹君，姚启峰. 基于多特征提取和改进马田系统的滚动轴承故障分类方法研究[J]. 振动与冲击, 2020, 39(6): 249-256

PENG Zhaiming, CHENG Longsheng, ZHAN Jun, YAO Qifeng. Fault classification method for rolling bearings based on the multi-featureextraction and modified Mahalanobis-Taguchi system[J]. Journal of Vibration and Shock, 2020, 39(6): 249-256

参考文献

[1] LEI Y. Intelligent Fault Diagnosis and Remaining Useful Life Prediction of Rotating Machinery [M]. Butterworth-Heinemann, 2017.
[2] 万海波, 杨世锡. 基于HHT的数控机床主轴振动监测系统的研制[J]. 振动与冲击, 2014, 33(6): 48-52.
WAN Haibo, YANG Shixi. Development of HHT-based vibration monitoring system for NC spindle [J]. Journal of Vibration and Shock, 2014, 33(6): 48–52.
[3] ZHAO XM, PATEL TH，ZUO MJ. Multivariate EMD and full spectrum based condition monitoring for rotating machinery [J]. Mechanical Systems and Signal Processing, 2012, 27(1): 712-728.
[4] LIU HH, HAN MH. A fault diagnosis method based on local mean decomposition and multi-scale entropy for roller bearings [J]. Mechanism and Machine Theory, 2014, 75: 67-78.
[5] RONG RW, MING TF. Research on rolling element bearing fault diagnosis based on genetic algorithm matching pursuit [J]. 6th Global Conference on Materials Science and Engineering, 2017, 012009.
[6] ISLAM MM, KIM JM. Reliable multiple combined fault diagnosis of bearings using heterogeneous feature models and multiclass support vector Machines [J]. Reliability Engineering and System Safety, 2018, 000: 1-12.
[7] PATIL AB, GAIKWAD JA, KULKARNI JV. Bearing fault diagnosis using discrete wavelet transform and artificial neural network [J]. International Conference on Applied and Theoretical Computing and Communication Technology, 2016: 399-405.
[8] QIN Y. A new family of model-based impulsive wavelets and their sparse representation for rolling bearing fault diagnosis [J]. IEEE Transactions on Industrial Electronics, 2018, 65(3): 2716-2726.
[9] DUONG DP, KIM JM. Non-Mutually Exclusive Deep Neural Network Classifier for Combined Modes of Bearing Fault Diagnosis [J]. Sensors, 2018, 18(4): 1129.
[10] SUN JD, YAN CH, WEN JT. Intelligent bearing fault diagnosis method combining compressed data acquisition and deep learning [J]. IEEE transaction on instrumentation and measurement, 2018, 67(1): 185-195.
[11] TAGUCHI G, RAJESH J. New trends in multivariate diagnosis [J]. The Indian Journal of Statistics, 2000, Series B: 233-248.
[12] SOYLEMEZOGLU A, JAGANNATHAN S, SAYGIN C. Mahalnobis Taguchi System (MTS) as a prognostic tool for rolling element bearing failures [J]. Journal of Manufacturing Science and Engineering, 2010, 132(5): 635-645.
[13] HU JQ, ZHANG LB, LIANG W. Dynamic degradation observer for bearing fault by MTS–SOM system [J]. Mechanical Systems and Signal Processing, 2013; 36: 385-400.
[14] WANG Z, LU C, WANG ZL, et al. Fault diagnosis and health assessment for bearings using the Mahalanobis-Taguchi system based on EMD-SVD [J]. Transactions of the Institute of Measurement and Control, 2013, 35(6): 798-807.
[15] SHAKYA P, KULKARNI MS, DARPE AK. Bearing diagnosis based on Mahalanobis-Taguchi-Gram-Schmidt method [J]. Journal of Sound and Vibration，2015，337: 342-362．
[16] 剡昌锋, 朱涛, 吴黎晓, 等. 基于马田系统的滚动轴承初始故障检测和状态监测[J]. 振动与冲击, 2017, 36(12): 155-162.
YAN Changfeng, ZHU Tao, WU Lixiao, et al. Incipient fault detection and condition monitoring of rolling bearings by using the Mahalanobis-Taguchi System [J]. Journal of Vibration and Shock, 2017, 36(12): 155-162.
[17] 陈俊洵, 程龙生, 胡绍林, 等. 基于EMD的改进马田系统的滚动轴承故障诊断[J]. 振动与冲击, 2017, 36(5): 151-156.
CHEN Junxun, CHENG Longsheng, HU Shaolin, et al. Fault diagnosis of rolling bearing using modified Mahalanobis-Taguchi system based on EMD [J]. Journal of Vibration and Shock, 2017, 36(5): 151-156.
[18] CHEN JX, CHENG LS, YU H, et al. Rolling bearing fault diagnosis and health assessment using EEMD and the adjustment Mahalanobis-Taguchi system [J]. International Journal of Systems Science, 2018, 49(1): 147-159.
[19] YEH JR, SHIEH JS, HUANG NE. Complementary ensemble empirical mode decomposition: A novel noise enhanced data analysis method [J]. Advance in Adaptive Data Analysis, 2010, 2(2): 135-156.
[20] TORRES ME, COLOMINAS MA, SCHLOTTHAUER G, et al. A complete ensemble empirical mode decomposition with adaptive noise [J]. In Proceedings of the 36th International Conference on Acoustic, Speech, and Signal Processing (ICASSP), 2011: 4144-4147.
[21] COLOMINAS MA, SCHLOTTHAUER G, TORRES ME, et al. Noise-assisted EMD methods in action [J]. Advance in Adaptive Data Analysis, 2012, 4(4): 1250025.
[22] LOPARO KA. Bearings vibration data set, Case Western Reserve University. http://www.eecs.cwru.edu/laboratory/Bearing /download.htm.