局部费歇尔判别分值在滚动轴承故障诊断中的应用

王雪冬; 赵荣珍; 邓林峰; 张亚龙

doi:10.13433/j.cnki.1003-8728.2017.0219

局部费歇尔判别分值在滚动轴承故障诊断中的应用

doi: 10.13433/j.cnki.1003-8728.2017.0219

1.
兰州理工大学机电工程学院, 兰州 730050

基金项目:

国家自然科学基金项目（51675253）与教育部高等学校博士学科点专项科研基金项目（20136201110004）资助

详细信息

作者简介:
王雪冬(1988-),硕士,研究方向为旋转机械故障诊断,wang6493@126.com

通讯作者:
赵荣珍(联系人),教授,博士生导师,zhaorongzhen@lut.cn

计量
- 文章访问数: 153
- HTML全文浏览量: 32
- PDF下载量: 7
- 被引次数: 0
出版历程
- 收稿日期: 2015-06-15
- 刊出日期: 2017-02-05

Application of Localized Fisher Discriminant Score in Fault Diagnosis of Rolling Bearing

1.
School of Mechanical and Electronical Engineering, Lanzhou University of Technology, Lanzhou 730050, China

摘要

摘要: 为精确、高效地识别出滚动轴承不同程度、不同类型的故障，提出一种基于局部费歇尔判别分值（Localized fisher discriminant score，LFDS）的故障诊断方法。该方法首先从时域、频域及时频域构造原始故障特征集；然后运用LFDS选择出其中最能反映故障本质的敏感特征子集；最后将选择出的特征子集输入到最小二乘支持向量机进行模式识别。用滚动轴承一组故障特征数据集进行验证。结果表明，经LFDS选择出的特征能显著表现出不同故障类别间的差异。
- 故障诊断 /
- 局部费歇尔判别分值 /
- 特征选择 /
- 最小二乘支持向量机
Abstract: In order to precisely and efficiently identify different types with different degree of fault rolling bearing. An intelligent fault diagnosis method based on localized fisher discriminant score (LFDS) is put forward. At first, the feature extractions of time domain, frequency domain and time-frequency from vibration signal are prepared; then use LFDS to select the most sensitive feature subset from the original feature set; finally, the sensitive low dimension feature data set is fed into least squares support vector machine algorithm to recognize the fault type. The proposed method was verified by the typical fault vibration signal of rolling bearing. According to the example result, the feature subset selected by LFDS can reveal the differences among the different types with different degree.
- fault diagnosis /
- localized fisher discriminant score /
- feature selection /
- least squares support vector machine

HTML全文

参考文献(16)

[1]	张龙,张磊,熊国良,等.基于多尺度熵的滚动轴承Elman神经网络故障诊断方法[J].机械科学与技术,2014,33(12):1854-1858 Zhang L, Zhang L, Xiong G L, et al. Rolling bearing fault diagnosis based on multiscale entropy and Elman neural network[J]. Mechanical Science and Technology for Aerospace Engineering, 2014,33(12):1854-1858 (in Chinese)
[2]	欧璐,于德介.基于监督拉普拉斯分值和主元分析的滚动轴承故障诊断[J].机械工程学报,2014,50(5):88-94 Ou L, Yu D J. Rolling bearing fault diagnosis based on supervised Laplaian score and principal component analysis[J]. Journal of Mechanical Engineering, 2014,50(5):88-94 (in Chinese)
[3]	Liu H, Yu L. Toward integrating feature selection algorithms for classification and clustering[J]. IEEE Transactions on Knowledge and Data Engineering, 2005,17(4):491-502
[4]	Dy J G, Brodley C E. Feature selection for unsupervised learning[J]. Journal of Machine Learning Research, 2004,5:845-889
[5]	Kohavi R, John G H. Wrappers for feature subset selection[J]. Artificial Intelligence, 1997,97(1-2):273-324
[6]	He X F, Cai D, Niyogi P. Laplacian score for feature selection[M]. Cambridge, MA:MIT Press, 2005:249-256
[7]	Liao B, Jiang Y, Liang W, et al. Gene selection using locality sensitive Laplacian score[J]. IEEE/ACM Transactions on Computational Biology and Bioinformatics, 2014,11(6):1146-1156
[8]	Yilmaz E. An expert system based on fisher score and LS-SVM for cardiac arrhythmia diagnosis[J]. Computational and Mathematical Methods in Medicine, 2013,2013:849674
[9]	欧璐,于德介.基于拉普拉斯分值和模糊C均值聚类的滚动轴承故障诊断[J].中国机械工程,2014,25(10):1352-1357 Ou L, Yu D J. Rolling bearing fault diagnosis based on Laplacian score and fuzzy C-means clustering[J]. China Mechanical Engineering, 2014,25(10):1352-1357 (in Chinese)
[10]	Huang H, Feng H L, Peng C Y. Complete local Fisher discriminant analysis with Laplacian score ranking for face recognition[J]. Neurocomputing, 2012,89:64-77
[11]	Sugiyama M. Dimensionality reduction of multimodal labeled data by local Fisher discriminant analysis[J]. Journal of Machine Learning Research, 2007,8:1027-1061
[12]	万书亭,佟海侠,董炳辉.基于最小二乘支持向量机的滚动轴承故障诊断[J].振动、测试与诊断,2009,30(2):149-152 Wan S T, Tong H X, Dong B H. Bearing fault diagnosis using wavelet packet transform and least square support vector machines[J]. Journal of Vibration, Measurement & Diagnosis, 2009,30(2):149-152 (in Chinese)
[13]	郭金玉,刘玉芹,苑玮琦.基于核局部Fisher判别分析的掌纹识别[J].光电子·激光,2012,23(2):354-358 Guo J Y, Liu Y Q, Yuan W Q. Palmprint recognition based on kernel localized Fisher discriminant analysis[J]. Journal of Optoelectronics·Laser, 2012,23(2):354-358 (in Chinese)
[14]	Suykens J A K, Vandewalle J. Least squares support vector machine classifiers[J]. Neural Processing Letters, 1999,9(3):293-300
[15]	张进,冯志鹏,褚福磊.滚动轴承故障特征的时间-小波能量谱提取方法[J].机械工程学报,2011,47(17):44-49 Zhang J, Feng Z P, Chu F L. Extraction of rolling bearing fault feature based on time-wavelet energy spectrum[J]. Journal of Mechanical Engineering, 2011,47(17):44-49 (in Chinese)
[16]	王德明,王莉,张广明.基于遗传BP神经网络的短期风速预测模型[J].浙江大学学报(工学版),2012,46(5):837-841 Wang D M, Wang L, Zhang G M. Short-term wind speed forecast model for wind farms based on genetic BP neural network[J]. Journal of Zhejiang University (Engineering Science), 2012,46(5):837-841 (in Chinese)