Gearbox fault diagnosis based on multi-fractal

Author

Wang Tian-Hong ; Yuan Gui-Li ; Lan Zhong-Fu

Author_Institution

Chinese Power Complete Equip. Co., Ltd., Beijing, China

fYear

2014

fDate

28-30 July 2014

Firstpage

3292

Lastpage

3296

Abstract

The multi-fractal analysis methods of nonlinear theory was adopted to extract multi-fractal characteristics of nonstationary vibration signals of the gear box under a variety of complex fault states, and training a variety of neural network to the classification of the composite fault signal. The experimental results show that the multi-fractal characteristics of extraction has a good degree of differentiation, combined with a neural network is an effective method of gearbox vibration signal analysis.

Keywords

differentiation; fault diagnosis; fractals; gears; mechanical engineering computing; neural nets; signal classification; vibrations; complex fault state; composite fault signal classification; differentiation; gearbox fault diagnosis; gearbox vibration signal analysis; multifractal analysis method; neural network; nonlinear theory; nonstationary vibration signals; Educational institutions; Electronic mail; Fault diagnosis; Fluctuations; Fractals; Gears; Principal component analysis; Eliminate Trend Analysis; Fault Diagnosis; Feature Extraction; Multi-fractal; Vibration;

fLanguage

English

Publisher

ieee

Conference_Titel

Control Conference (CCC), 2014 33rd Chinese

Conference_Location

Nanjing

Type

conf

DOI

10.1109/ChiCC.2014.6895483

Filename

6895483