A fault diagnosis method based on parametric estimation in hydraulic servo system

Hongmei Liu; Pingchao Ouyang; Shaoping Wang

doi:10.1117/12.717595

6 November 2006 A fault diagnosis method based on parametric estimation in hydraulic servo system

Hongmei Liu, Pingchao Ouyang, Shaoping Wang

Proceedings Volume 6357, Sixth International Symposium on Instrumentation and Control Technology: Signal Analysis, Measurement Theory, Photo-Electronic Technology, and Artificial Intelligence; 63575A (2006) https://doi.org/10.1117/12.717595
Event: Sixth International Symposium on Instrumentation and Control Technology, 2006, Beijing, China

Abstract

Due to the fault occurrence could commonly be considered as results of the physical parameters variation of the system and this variation usually is embodied by model coefficients variation of the system, faults can be detected and diagnosed according to the model parameter variation of the system. In this paper, a parametric estimation method, which is extended to extract features existing in input and output data of the monitored system, is employed to realize the FDD for a hydraulic servo system. An Auto-Regressive model with exogenous input (ARX) is selected to approximate the dynamic behavior of the system. Then according to the feature vector constructed by the coefficient of ARX model, faults are classified in feature space using RBF neural network to realize the fault localization. Experiments and simulations results indicate that the proposed method is effective in fault diagnosis for hydraulic servo system.

Citation Download Citation

Hongmei Liu, Pingchao Ouyang, and Shaoping Wang "A fault diagnosis method based on parametric estimation in hydraulic servo system", Proc. SPIE 6357, Sixth International Symposium on Instrumentation and Control Technology: Signal Analysis, Measurement Theory, Photo-Electronic Technology, and Artificial Intelligence, 63575A (6 November 2006); https://doi.org/10.1117/12.717595

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