Research on Fault Diagnosis Method of Rotating Machinery Based on Extreme Learning Machine

DOI

10.2991/mbdasm-19.2019.13How to use a DOI?

Keywords

information entropy; intrinsic mode function; extreme learning machine

Abstract

The space station has gradually entered the world. It is equipped with centrifuges for variable gravity experiments. The stagnation of centrifuge may lead to the increase of motor current, which may lead to fire. Vibration signal of centrifuge is unstable and asymmetric. Secondly, the first order modal functions are used to obtain the spectrum by Fourier transform, and the information entropy intrinsic mode function of the spectrum is calculated. At the same time, information entropy is used as a fault feature and dimensionality reduction. Finally, the fault features are trained by the extreme learning machine method, and the actual data acquisition training method is used.

Copyright

© 2019, 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  - Dequan Yu
AU  - Yang Wang
AU  - Wenbo Wu
AU  - Hongyong Fu
AU  - Ke Wang
PY  - 2019/10
DA  - 2019/10
TI  - Research on Fault Diagnosis Method of Rotating Machinery Based on Extreme Learning Machine
BT  - Proceedings of the 2019 International Conference on Mathematics, Big Data Analysis and Simulation and Modelling (MBDASM 2019)
PB  - Atlantis Press
SP  - 56
EP  - 59
SN  - 2352-538X
UR  - https://doi.org/10.2991/mbdasm-19.2019.13
DO  - 10.2991/mbdasm-19.2019.13
ID  - Yu2019/10
ER  -