Bearing fault diagnosis based on generalized s-transform and two-directional 2DPCA

被引：0
|
作者：
Li, Weihua [1 ]
Lin, Long [1 ]
Shan, Waiping [1 ]
机构：
[1] School of Mechanical Automotive Engineering, South China University of Technology, Guangzhou
来源：
Zhendong Ceshi Yu Zhenduan/Journal of Vibration, Measurement and Diagnosis | 2015年 / 35卷 / 03期
关键词：
Fault diagnosis; Feature extraction; Generalized S-transform; Image recognition; Two-dimensional principle component analysis (2DPCA);
D O I：
10.16450/j.cnki.issn.1004-6801.2015.03.016
中图分类号：
学科分类号：
摘要：
The problem of bearing fault diagnosis can be solved by time-frequency image recognition. A two-directional, two-dimensional principal component analysis (TD-2DPCA) method is proposed to extract features from a time-frequency image matrix. First, features are extracted with TD-2DPCA using the generalized S-transform to transform fault signals into images in the time-frequency domain. The bearing fault experiments are carried out on a bearing test-bed, and vibration signals are collected under the normal condition, inner ring fault condition and outer ring fault condition. The proposed method is adopted to extract image features of three bearings from time-frequency spectrums, and the assembled matrix distance (AMD) is calculated for image classification. Experimental results show that TD-2DPCA combined with the generalized S-transform has good diagnostic performance and can effectively improve the computational speed. ©, 2015, Nanjing University of Aeronautics an Astronautics. All right reserved.
引用
收藏
页码：499 / 506
页数：7
相关论文
共 17 条
  • [1] Yang Y., He Y., Cheng J., Et al., Time-frequency analysis of hilbert spectrum based on maximal overlap discrete wavelet packet transform, Journal of Vibration, Measurement & Diagnosis, 29, 1, pp. 10-13, (2009)
  • [2] Zhao F., Yang R., Voltage sag disturbance detection based on short time fourier transform, Proceedings of the Chinese Society for Electrical Engineering, 27, 10, (2007)
  • [3] Stockwell R.G., Mansinha L., Lowe R.P., Localization of the complex spectrum: the S-transform, IEEE Transactions on Signal Processing, 17, pp. 998-1001, (1996)
  • [4] Zhai J., Zhao W., Wang X., Et al., Research on the image feature extraction, Journal of Hebei University, 29, 1, pp. 106-112, (2009)
  • [5] Yang J., Zhang D., Yang J., Two-dimensional PCA: a new approach to appearance-based face representation and recognition, IEEE Transactions on Pattern Analysis and Machine Intelligence, 26, 1, pp. 131-137, (2004)
  • [6] Li M., Yuan B., 2D-LDA: a statistical linear discriminant analysis for image matrix, Pattern Recognition Letters, 26, 5, pp. 527-532, (2005)
  • [7] Chen F., Chen X., Gao X., Et al., Generalization of 2DPCA and its application in face recognition, Journal of Computer Applications, 25, 8, pp. 1767-1770, (2005)
  • [8] Li B., Zhang P., Liu D., Et al., Classification of time-frequency representations based on two-direction 2DLDA for gear fault diagnosis, Applied Soft Computing, 11, 8, pp. 5299-5305, (2011)
  • [9] Li H., Chen Y., Zhang Z., Et al., Time-frequency image identification using non-negative matrix factorization and principal component analysis, Journal of Vibration and Shock, 18, pp. 169-172, (2012)
  • [10] Li B., Zhang P., Tian H., Et al., A new feature extraction and selection scheme for hybrid fault diagnosis of gearbox, Expert Systems with Applications, 38, 8, pp. 10000-10009, (2011)
12