基于小波包能量谱与主成分分析的轴承故障特征增强诊断方法

doi:10.3969/j.issn.1000-1093.2019.11.022

摘要/Abstract

摘要： 滚动轴承出现损伤时，采集的振动信号呈非平稳性，采用一般的时域和频域分析方法不能准确提取出振动信号的故障特征。根据小波包多分辨、精细化的分解特性，提出一种基于小波包能量谱与主成分分析（PCA）方法的滚动轴承故障诊断算法。将振动信号进行小波包分解，得到重点频率段信息的能量谱，提取能量谱作为特征向量；利用PCA方法对特征向量降维并减小噪声信号的干扰，获得增强的故障特征；利用层次聚类方法和改进的模糊c均值聚类算法对不同类型的滚动轴承故障进行识别，两种聚类方法都准确地识别出了不同的故障类型。实例验证结果表明，所提方法能够有效地提取振动信号中的有用故障特征，实现轴承故障类型的精确诊断。

关键词: 轴承, 故障诊断, 特征增强, 小波包分解, 能量谱, 主成分分析

Abstract: The acquired vibration signal is usually unstable once rolling bearing damage occurs, which results in inaccurately detecting the fault features of rolling bearing by time-domain or frequency-domain analysis. A fault diagnosis method which uses the wavelet packet energy spectrum and principal component analysis (PCA) to diagnose the faults of rolling bearing is presented. The wavelet packet decomposition algorithm is used to decompose and refine the vibration signals in different frequency ranges. The energy spectra in the focused frequency ranges are calculated after the vibration signal is decomposed by wavelet packet decomposition. PCA is performed to decrease the dimension of the energy spectrum and reduce the noise interference, thus enhancing the extracted fault feature without the noise interference. And then the different fault types of rolling bearing are classified by two types of clustering algorithms, i.e., hierarchical clustering analysis (HCA) and fuzzy c-means (FCM). The results show that the fault types can be correctly identified by both cluster algorithms. The example verification indicates that the proposed method can be used to effectively extract the useful fault features in the vibration signal and identify the fault types exactly. This provides a feasible method for diagnosing a machine with some similar faults. Key

Key words: bearing, faultdiagnosis, featureenhancement, waveletpacketdecomposition, energyspectrum, principalcomponentanalysis

中图分类号:

TH133.33⁺1

郭伟超，赵怀山，李成，李言，汤奥斐. 基于小波包能量谱与主成分分析的轴承故障特征增强诊断方法[J]. 兵工学报, 2019, 40(11): 2370-2377.

GUO Weichao, ZHAO Huaishan, LI Cheng, LI Yan, TANG Aofei. Fault Feature Enhancement Method for Rolling Bearing Fault Diagnosis Based on Wavelet Packet Energy Spectrum and Principal Component Analysis[J]. Acta Armamentarii, 2019, 40(11): 2370-2377.

参考文献

［1］邱明, 周大威, 周占生. 基于加速寿命试验的自润滑关节轴承可靠性分析[J]. 兵工学报, 2018, 39(7): 1429-1435.
QIU M, ZHOU D W, ZHOU Z S. Reliability analysis of life-lubricating spherical plain bearings based on accelerated tests[J]. Acta Armamentarii, 2018, 39(7): 1429-1435. (in Chinese)
[2］高文君, 刘振侠, 朱鹏飞, 等. 基于多节点热网络法的航空发动机主轴轴承温度场分析[J]. 推进技术,2019,40(2): 382-388.
GAO W J, LIU Z X, ZHU P F,et al. Steady thermal analysis of main-shaft roller bearing for aero-engine based on multi-nodes thermal network methods[J]. Journal of Propulsion Technology, 2019, 40(2): 382-388. (in Chinese)
[3］程卫东, 赵德尊, 刘东东. 基于故障特征系数模板的变转速滚动轴承故障诊断[J]. 振动与冲击, 2017, 36(7): 123-129.
CHENG W D, ZHAO D Z, LIU D D. Rolling element bearing fault diagnosis based on fault characteristic coefficient template under time-varying rotating speed[J]. Journal of Vibration and Shock, 2017, 36(7): 123-129. (in Chinese)
[4］鄢小安, 贾民平. 基于改进奇异谱分解的形态学解调方法及其在滚动轴承故障诊断中的应用[J]. 机械工程学报, 2017, 53(7): 104-112.
YAN X A, JIA M P. Morphological demodulation method based on improved singular spectrum decomposition and its application in rolling bearing fault diagnosis[J]. Journal of Mechanical Engineering, 2017, 53(7): 104-112. (in Chinese)
[5］薛红涛, 殷苏群, 李仲兴, 等. 基于AHN的轮毂电机轴承故障特征提取方法[J]. 华中科技大学学报(自然科学版),2019, 47(1): 27-31.
XUE H T, YIN S Q, LI Z X, et al. Feature extraction method for mechanical faults of bearings in in-wheel motor based on AHN[J].Journal of Huazhong University of Science and Technology (Natural Science Edition), 2019, 47(1): 27-31. (in Chinese)
[6］张淑清, 胡永涛, 姜安琦, 等. 基于双树复小波和自适应权重和时间因子的粒子群优化支持向量机的轴承故障诊断[J]. 中国机械工程, 2017, 28(3): 327-333.
ZHANG S Q, HU Y T, JIANG A Q, et al. Bearing fault diagnosis based on DTCWT and AWTFPSO-optimized SVM[J].China Mechanical Engineering, 2017, 28(3): 327-333. (in Chinese)
[7］ SHAO H D, JIANG H K, WANG F A, et al. Rolling bearing fault diagnosis using adaptive deep belief network with dual-tree complex wavelet packet[J]. ISA Transactions,2017, 69: 187-201.
[8］孙鲜明, 刘欢, 赵新光, 等. 基于瞬时包络尺度谱熵的滚动轴承早期故障奇异点识别及特征提取[J]. 机械工程学报,2017, 53(3): 73-80.
SUN X M, LIU H, ZHAO X G, et al. Singular point recognition and feature extraction for incipient bearing fault based on instantaneous envelope scalogram entropy[J]. Journal of Mechanical Engineering, 2017, 53(3): 73-80. (in Chinese)
[9］段晨东, 高鹏, 徐先峰, 等. 一种基于时频峭度谱的滚动轴承损伤诊断方法[J]. 机械工程学报, 2015, 51(11): 78-83.
DUAN C D, GAO P, XU X F, et al. A ball bearing defect diagnosis method using time-frequency kurtosis spectrum[J]. Journal of Mechanical Engineering, 2015, 51(11): 78-83. (in Chinese)

[10］姚成玉, 来博文, 陈东宁, 等. 基于最小熵解卷积-变分模态分解和优化支持向量机的滚动轴承故障诊断方法[J]. 中国机械工程，2017, 28(24): 3001-3012.
YAO C Y, LAI B W, CHEN D N, et al. Fault diagnosis method based on MED-VMD and optimized SVM for rolling bearing[J]. China Mechanical Engineering， 2017, 28(24): 3001-3012. (in Chinese)
[11］贾峰, 武兵, 熊晓燕, 等. 基于多维度排列熵与支持向量机的轴承早期故障诊断方法[J]. 计算机集成制造系统,2014, 20(9): 2275-2282.
JIA F, WU B, XIONG X Y, et al. Early fault diagnosis of bearing based on multi-dimension permutation entropy and SVM[J]. Computer Integrated Manufacturing Systems, 2014, 20(9): 2275-2282. (in Chinese)
[12］ ZHANG X, LIU Z W, MIAO Q, et al. Bearing fault diagnosis using a whale optimization algorithm-optimized orthogonal matching pursuit with a combined time-frequency atom dictionary[J]. Mechanical Systems and Signal Processing,2018, 107: 29-42.
[13］ TENG W, DING X, ZHANG Y Y, et al. Application of cyclic coherence function to bearing fault detection in a wind turbine generator under electromagnetic vibration[J]. Mechanical Systems and Signal Processing, 2017, 87: 279-293.
[14］田福庆, 罗荣, 李万, 等. 改进的卷积型小波包分解及在故障诊断中的应用[J]. 西安交通大学学报, 2014, 48(3): 89-95.
TIAN F Q, LUO R, LI W, et al. Improved convolution-type wavelet packet decomposition with applications to fault diagnosis[J]. Journal of Xi'an Jiaotong University, 2014, 48(3): 89-95. (in Chinese)
[15］ ZHAO X Z, YE B Y. Singular value decomposition packet and its application to extraction of weak fault feature[J]. Mechanical Systems and Signal Processing, 2016, 70/71: 73-86.
[16］陈安华, 周博, 张会福, 等. 基于PCA与蚁群算法的机械故障聚类诊断方法[J]. 中国机械工程, 2013, 24(24): 3333-3337,3344.
CHEN A H, ZHOU B, ZHONG H F, et al. Clustering method of mechanical fault diagnosis based on PCA and ant colony algorithm[J]. China Mechanical Engineering, 2013, 24(24): 3333-3337, 3344. (in Chinese)
[17］ GUO W C, ZHAO H S, GAO X Q, et al. An efficient represen-tative for object recognition in structural health monitoring[J]. The International Journal of Advanced Manufacturing Technology, 2018，94:3239-3250
[18］张西宁, 雷威, 李兵. 主分量分析和隐马尔科夫模型结合的轴承监测诊断方法[J]. 西安交通大学学报， 2017, 51(6): 1-7， 109.
ZHANG X N, LEI W, LI B. Bearing fault detection and diagnosis method based on principal component analysis and hidden markov model[J]. Journal of Xi'an Jiaotong University， 2017, 51(6): 1-7，109. (in Chinese)
[19］ YEN G G, LIN K C. Wavelet packet feature extraction for vibration monitoring[J]. IEEE Transactions on Industrial Electronics， 2000, 47(3): 650-667.
[20］刘涛, 李爱群, 丁幼亮,等. 基于小波包能量谱的结构损伤预警方法试验研究[J]. 振动与冲击，2009, 28(4): 4-9，199.
LIU T，LI A Q, DING Y L, et al. Experimental study on structural damage alarm method based on wavelet packet energy spectrum [J]. Journal of Vibration and Shock, 2009, 28(4): 4-9,199. (in Chinese)
[21］雷亚国. 混合智能技术及其在故障诊断中的应用研究[D]. 西安：西安交通大学, 2017.
LEI Y G. Research on hybrid intelligent technique and its applications in fault diagnosis[D]. Xi'an：Xi'an Jiaotong University, 2017. (in Chinese)
[22］ Case Western Reserve University.Bearing Data Center (seeded fault test data) [EB/OL]. ［2019-01-10］. http://csegroups.case.edu/bearingdatacenter/home.

第40卷
第11期2019 年11月兵工学报ACTA
ARMAMENTARIIVol.40No.11Nov.2019

[1]	李良钰，苏铁熊，马富康，吴小军，徐春龙. 基于集合经验模态分解-支持向量机的高压共轨系统故障诊断方法[J]. 兵工学报, 2022, 43(5): 992-1001.
[2]	胡晶，翟九童，张心明，李海龙，荀博. 基于响应面法的双级串联轴承结构优化设计[J]. 兵工学报, 2022, 43(3): 694-703.
[3]	张文虎，胡余生，邓四二，徐嘉，李峰. 摆动球轴承球与保持架碰撞行为[J]. 兵工学报, 2022, 43(1): 207-217.
[4]	常丽萍，常亚南，杨雷雷. 内圈倾斜角对高速角接触球轴承动态特性的影响[J]. 兵工学报, 2021, 42(6): 1138-1147.
[5]	李志农, 胡志峰, 毛清华, 张旭辉, 陶俊勇. 非线性调频模态分解-同步提取变换方法及其在滚动轴承故障诊断中的应用[J]. 兵工学报, 2021, 42(6): 1324-1330.
[6]	朱敏，许爱强，许晴，李睿峰. 基于改进多层核超限学习机的模拟电路故障诊断[J]. 兵工学报, 2021, 42(2): 356-369.
[7]	高嘉明，佘冲冲，陈军，李敏，侯云辉，陈丽珍，王建龙. 基于近红外光谱的梯恩梯凝固点温度检测方法研究[J]. 兵工学报, 2020, 41(5): 1034-1040.
[8]	于军，刘可，郭帅，于广滨，郭振宇. 基于条件深度循环生成对抗网络和动作探索的行星轮轴承剩余寿命预测[J]. 兵工学报, 2020, 41(11): 2170-2178.
[9]	洪晓文，李伟兵，李文彬，徐赫阳，李军宝. 多层复合装药爆炸冲击波信号能量谱[J]. 兵工学报, 2020, 41(11): 2243-2251.
[10]	杨振祥，郭智威，袁成清. 石墨微胶囊改性超高分子量聚乙烯舰船水润滑尾轴承复合材料的摩擦学性能[J]. 兵工学报, 2020, 41(11): 2281-2291.
[11]	邓四二，胡余生，孙玉飞，徐嘉，牛荣军，崔永存. 空调滑片式压缩机用圆柱滚子轴承摩擦功耗特性分析[J]. 兵工学报, 2019, 40(9): 1943-1952.
[12]	李佳蔚，崔涛，刘宇航，师帅楠，孙强. 基于排气温度动态模型的在线观测器研究[J]. 兵工学报, 2019, 40(8): 1562-1571.
[13]	张占立，周鹏举，李文博，王恒迪. YRT转台轴承摩擦力矩特性研究[J]. 兵工学报, 2019, 40(7): 1495-1502.
[14]	赵尧，虞钢，何秀丽，李海明，李少霞. 基于主成分分析法与逼近理想解法的38MnVS6激光熔覆工艺研究[J]. 兵工学报, 2019, 40(12): 2537-2544.
[15]	翟禹尧，史贤俊，吕佳朋. 基于广义随机Petri网的导弹系统测试性建模与指标评估方法研究[J]. 兵工学报, 2019, 40(10): 2070-2079.