Turboprop Engine Fault Diagnosis Based on Hilbert Spectrum and Singular Value Decomposition

DOI

10.2991/mcei-16.2016.265How to use a DOI?

Keywords

Fault diagnosis; Feature extraction; Hilbert spectrum; Singular value decomposition; RBF network

Abstract

In order to solve the time-frequency feature extraction problem of the vibration signal, a fault diagnosis method based on Hilbert spectrum and singular value decomposition is proposed and applied to engine fault diagnosis. Firstly, the vibration signals are decomposed into a series of intrinsic mode functions by using empirical mode decomposition method. Secondly, Hilbert transform is applied to each intrinsic mode function and Hilbert spectrum of the vibration signal is got. Then the singular value method is applied to the Hilbert spectrum and the singular value vector is acquired. Finally, as feature vectors, singular value vectors are input into RBF network for identifying the different fault. Experimental simulation shows that this method can extract effectively the engine fault vibration signal characteristics.

Copyright

© 2017, 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  - Feng Ding
AU  - Zhi Qi
PY  - 2016/12
DA  - 2016/12
TI  - Turboprop Engine Fault Diagnosis Based on Hilbert Spectrum and Singular Value Decomposition
BT  - Proceedings of the 2016 6th International Conference on Mechatronics, Computer and Education Informationization (MCEI 2016)
PB  - Atlantis Press
SP  - 1300
EP  - 1304
SN  - 1951-6851
UR  - https://doi.org/10.2991/mcei-16.2016.265
DO  - 10.2991/mcei-16.2016.265
ID  - Ding2016/12
ER  -