Title :
Fault detection and isolation by using multiple model method
Author_Institution :
Univ. of Sci. & Technol. Beijing, Beijing
Abstract :
The system in different faulty state can be represented by different model. The multi-model approach based on Bayesian decision is used for fault detection and isolation. The system with different time delay of input, which is regarded as different level of fault, will be detected by this method. The effectiveness of the proposed method will be tested by the Monte Carlo simulations even in the presence of significant measurement noise.
Keywords :
Monte Carlo methods; belief networks; delays; fault diagnosis; Bayesian decision; Monte Carlo simulations; fault detection; isolation; multiple model method; time delay; Automatic control; Bayesian methods; Control systems; Fault detection; Fault diagnosis; Notice of Violation; Pattern analysis; Pattern recognition; Probability density function; Wavelet analysis; Multi-model; bayesian decision; fault detection;
Conference_Titel :
Wavelet Analysis and Pattern Recognition, 2007. ICWAPR '07. International Conference on
Conference_Location :
Beijing
Print_ISBN :
978-1-4244-1065-1
Electronic_ISBN :
978-1-4244-1066-8
DOI :
10.1109/ICWAPR.2007.4420635
