Share Email Print
cover

Proceedings Paper

A fault diagnosis method based on parametric estimation in hydraulic servo system
Author(s): Hongmei Liu; Pingchao Ouyang; Shaoping Wang
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper 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.

Paper Details

Date Published: 6 November 2006
PDF: 6 pages
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); doi: 10.1117/12.717595
Show Author Affiliations
Hongmei Liu, Beihang Univ. (China)
Pingchao Ouyang, Beihang Univ. (China)
Shaoping Wang, Beihang Univ. (China)


Published in SPIE Proceedings Vol. 6357:
Sixth International Symposium on Instrumentation and Control Technology: Signal Analysis, Measurement Theory, Photo-Electronic Technology, and Artificial Intelligence

© SPIE. Terms of Use
Back to Top