Research on planetary gearboxes feature selection and fault diagnosis based on EDT and FDA

Author

Haiping Li ; Jianmin Zhao ; Ruifeng Yang ; Jinsong Zhao ; Hongzhi Teng

Author_Institution

Mech. Eng. Coll., Shijiazhuang, China

fYear

2014

fDate

24-27 Aug. 2014

Firstpage

178

Lastpage

181

Abstract

This paper developed an automatical and accurate method in diagnosing the wear fault of planetary gearboxes. In this method, 19 features are extracted to characterize the gear health statuses. Then, select features which are sensitive to the changed health status and unrelated to the varied work condition. The process of feature selection is based on Euclidean distance technique (EDT). Finally, the Fisher discriminant analysis (FDA) is utilized to diagnose the wear fault. The effectiveness of this methodology is demonstrated using vibration data which obtained from a planetary gearbox test rig.

Keywords

condition monitoring; fault diagnosis; feature extraction; feature selection; gears; mechanical testing; statistical analysis; vibrations; wear; EDT; Euclidean distance technique; FDA; Fisher discriminant analysis; feature selection; features extraction; gear health statuses; planetary gearbox test rig; planetary gearboxes; vibration data; wear fault diagnosis; work condition; Accelerometers; Fault diagnosis; Feature extraction; Gears; Mechanical systems; Sun; Vectors; euclidean distance technique; fault diagnosis; feature selection; fisher discriminant analysis; planetary gearbox;

fLanguage

English

Publisher

ieee

Conference_Titel

Prognostics and System Health Management Conference (PHM-2014 Hunan), 2014

Conference_Location

Zhangiiaijie

Print_ISBN

978-1-4799-7957-8

Type

conf

DOI

10.1109/PHM.2014.6988158

Filename

6988158