Founded in 1971 >
Chinese Sci-tech Core Periodicals >
British Science Abstracts (SA, INSPEC) Indexed Journals >
United States, Cambridge Scientific Abstract: Technology (CSA: T) Indexed Journals >
United States, Ulrich's Periodicals Directory(UPD)Indexed Journals >
United States, Cambridge Scientific Abstract: Natural Science (CSA: NS) Indexed Journals >
Poland ,Index of Copernicus(IC) Indexed Journals >
International Standard Serial Number:
ISSN 1001-4551
Sponsor:
Zhejiang University;
Zhejiang Machinery and Electrical Group
Edited by:
Editorial of Journal of Mechanical & Electrical Engineering
Chief Editor:
ZHAO Qun
Vice Chief Editor:
TANG ren-zhong,
LUO Xiang-yang
Tel:
86-571-87041360,87239525
Fax:
86-571-87239571
Add:
No.9 Gaoguannong,Daxue Road,Hangzhou,China
P.C:
310009
E-mail:
meem_contribute@163.com
Abstract: Aiming at the problem that the existing methods of control system actuator(pneumatic actuator/electro-hydraulic actuator) fault diagnosis could not meet the accuracy and rapidity at the same time, a fault diagnosis method of control system actuator based on empirical wavelet transform (EWT) and dual kernel extreme learning machine (DKELM) was proposed. Firstly, the empirical wavelet transform was used to decompose the actuator fault signal to obtain several empirical wavelet functions, the functions were filtered according to the information entropy (IE), and the fuzzy information entropy (FIE) of the reserved functions was calculated to form the fault feature vector. Secondly, wavelet kernel function and RBF kernel function were introduced into the extreme learning machine (ELM) to construct the dual kernel extreme learning machine, and the fault feature vectors were used as input for training and classification test of the dual kernel extreme learning machine model. Finally, the method based on EWTDKELM was tested repeatedly on the actuator fault semi physical test platform to verify the effectiveness of the method. The results show that the empirical wavelet transform can effectively separate each independent mode of actuator fault signal, the extracted fuzzy information entropy features have high distinction, the dual kernel extreme learning machine model has fast training speed, small error and high classification accuracy.
Key words: control system actuator; pneumatic actuator; electrohydraulic actuator; empirical wavelet transform (EWT); fuzzy information entropy (FIE); dual kernel extreme learning machine (DKELM)