Feature Extraction Method for Fault Diagnosis of Rotating Machinery Based on Wavelet and LLE

DOI

10.2991/emim-16.2016.241How to use a DOI?

Keywords

Feature extraction; Rotating machinery; Fault diagnosis; Wavelet; LLE

Abstract

Feature extraction is an important procedure in the process of fault diagnosis for rotating machinery. Based on wavelet and local linear embedding (LLE), a method is proposed in this paper to extract features from vibration signals of rotating machinery. Firstly, multiple features were extracted from the original vibration signals and their wavelet decomposition coefficients to construct a high feature set. Then, to reduce the dimension of the high feature set initially, detection index (DI) was taken as an index to select several features from the extracted features. After that, LLE was employed to conduct feature fusion on the initial obtained feature set and obtain low dimension fault features for fault diagnosis of rotating machinery. To validate the proposed method, fault extraction experiment was conducted, and the result shows that the proposed method can extract better features for fault classification of rotating machinery.

Copyright

© 2016, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Guangtao Zhang
AU  - Yuanchu Cheng
AU  - Xingfang Wang
AU  - Na Lu
PY  - 2016/04
DA  - 2016/04
TI  - Feature Extraction Method for Fault Diagnosis of Rotating Machinery Based on Wavelet and LLE
BT  - Proceedings of the 6th International Conference on Electronic, Mechanical, Information and Management Society
PB  - Atlantis Press
SP  - 1181
EP  - 1185
SN  - 2352-538X
UR  - https://doi.org/10.2991/emim-16.2016.241
DO  - 10.2991/emim-16.2016.241
ID  - Zhang2016/04
ER  -