Fault diagnosis approach based on module fuzzy subsystems

Hong Lv; Haiwen Yuan; Haibin Yuan

doi:10.1117/12.717594

6 November 2006 Fault diagnosis approach based on module fuzzy subsystems

Hong Lv, Haiwen Yuan, Haibin Yuan

Proceedings Volume 6357, Sixth International Symposium on Instrumentation and Control Technology: Signal Analysis, Measurement Theory, Photo-Electronic Technology, and Artificial Intelligence; 635759 (2006) https://doi.org/10.1117/12.717594
Event: Sixth International Symposium on Instrumentation and Control Technology, 2006, Beijing, China

Abstract

Module fuzzy subsystems approach is introduced to solve Electrical Apparatus Control System (EACS) fault diagnosis problem in this paper. First, the input vectors are classified into several classifications using Radial Basis Function (RBF) neural network according to the faults occurring part. Then, a module subsystem is designed separately based on Fuzzy Neural Network (FNN) with exponential function fuzzy pattern matching. Finally, SF₆ breaker faults diagnosis application is employed to validate the effectiveness of the proposed method. Simulation result shows that the diagnosis approach for the structure of module fuzzy subsystems can solute the problem of rules quick increasing with the input vector increasing, and the algorithm of fuzzy pattern matching with exponential function can improve the diagnosis precision.

Citation Download Citation

Hong Lv, Haiwen Yuan, and Haibin Yuan "Fault diagnosis approach based on module fuzzy subsystems", Proc. SPIE 6357, Sixth International Symposium on Instrumentation and Control Technology: Signal Analysis, Measurement Theory, Photo-Electronic Technology, and Artificial Intelligence, 635759 (6 November 2006); https://doi.org/10.1117/12.717594

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available