Affordable Access

Access to the full text

Feature extraction of kernel regress reconstruction for fault diagnosis based on self-organizing manifold learning

Authors
  • Chen, Xiaoguang1
  • Liang, Lin1
  • Xu, Guanghua1, 2
  • Liu, Dan1
  • 1 Xi’an Jiaotong University, School of Mechanical Engineering, Xi’an, 710049, China , Xi’an (China)
  • 2 Xi’an Jiaotong University, State Key Laboratory for Manufacturing Systems Engineering, Xi’an, 710049, China , Xi’an (China)
Type
Published Article
Journal
Chinese Journal of Mechanical Engineering
Publisher
Springer Berlin Heidelberg
Publication Date
Sep 28, 2013
Volume
26
Issue
5
Pages
1041–1049
Identifiers
DOI: 10.3901/CJME.2013.05.1041
Source
Springer Nature
Keywords
License
Yellow

Abstract

The feature space extracted from vibration signals with various faults is often nonlinear and of high dimension. Currently, nonlinear dimensionality reduction methods are available for extracting low-dimensional embeddings, such as manifold learning. However, these methods are all based on manual intervention, which have some shortages in stability, and suppressing the disturbance noise. To extract features automatically, a manifold learning method with self-organization mapping is introduced for the first time. Under the non-uniform sample distribution reconstructed by the phase space, the expectation maximization(EM) iteration algorithm is used to divide the local neighborhoods adaptively without manual intervention. After that, the local tangent space alignment(LTSA) algorithm is adopted to compress the high-dimensional phase space into a more truthful low-dimensional representation. Finally, the signal is reconstructed by the kernel regression. Several typical states include the Lorenz system, engine fault with piston pin defect, and bearing fault with outer-race defect are analyzed. Compared with the LTSA and continuous wavelet transform, the results show that the background noise can be fully restrained and the entire periodic repetition of impact components is well separated and identified. A new way to automatically and precisely extract the impulsive components from mechanical signals is proposed.

Report this publication

Statistics

Seen <100 times