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

Fault diagnosis method of control system actuator based on EWT-DKELM
Published:2022-06-16 author:ZHANG Wen-guang, LI Hao-han, LIN Yuan,et al. Browse: 540 Check PDF documents
Fault diagnosis method of control system actuator based on EWT-DKELM


ZHANG Wen-guang1, LI Hao-han1, LIN Yuan2, WANG Wei-jian3, WU Kai-li3, MA Yan-hua4

(1.School of Control and Computer Engineering, North China Electric Power University, Beijing 102206, China;

2.School of New Energy, North China Electric Power University, Beijing 102206, China;

3.Shanghai Xinhua Control Technology Co., Ltd., Shanghai 270062, China;

4.School of Microelectronics, Dalian University of Technology, Dalian 116024, China)


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 EWTDKELM 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; electrohydraulic actuator; empirical wavelet transform (EWT); fuzzy information entropy (FIE); dual kernel extreme learning machine (DKELM)

  • Chinese Core Periodicals
  • Chinese Sci-tech Core Periodicals
  • SA, INSPEC Indexed
  • CSA: T Indexed
  • UPD:Indexed

Copyright 2010 Zhejiang Information Institute of Mechinery Industry All Rights Reserved

Technical Support:Hangzhou Bory science and technology

You are 1895221 visit this site