Title :
Gear Intelligent Fault Diagnosis Based on Support Vector Machines
Author :
Peng, Lv ; Yibing, Liu ; Qiang, Ma ; Yufan, Wei
Author_Institution :
North China Electr. Power Univ., Beijing
Abstract :
Support vector machines (SVM) was used in fault intelligent diagnosis of gear. The main research in feature extraction and data preprocess. The feature value of time domain includes peak to peak value, absolute average, square root amplitude, mean square amplitude. The feature value of frequency domain is MSF. The SVM method was used for detecting the gear case. The feature of time and the feature of frequent was be used. Through designed a band-pass filter, the feature of gear case´s signal was extracted, including feature of time and feature of frequent. The results showed that the reference and fault stations of fan can be distinguished clearly in the SVM diagram. The results showed that it was better than that signals which didn´t use filter.
Keywords :
band-pass filters; condition monitoring; fault diagnosis; feature extraction; gears; support vector machines; band-pass filter; data preprocess; feature extraction; gear intelligent fault diagnosis; support vector machines; Band pass filters; Fault diagnosis; Feature extraction; Frequency domain analysis; Gears; Machine intelligence; Mathematics; Physics; Support vector machine classification; Support vector machines; SVM; fault intelligent diagnosis; feature extraction; gear;
Conference_Titel :
Control Conference, 2007. CCC 2007. Chinese
Conference_Location :
Hunan
Print_ISBN :
978-7-81124-055-9
Electronic_ISBN :
978-7-900719-22-5
DOI :
10.1109/CHICC.2006.4347349
