A Decoupled Parameters Estimators for in Nonlinear Systems Fault diagnosis by ANFIS

Bellali Badre, A. Hazzab, I. K. Bousserhane, Dimitri lefebvre


This paper presents a new and efficient Adaptive Neural Fuzzy Inference Systems approach for satellite’s attitude control systems (ACSs) fault diagnosis. The proposed approach formulates the fault modelling problem of system component into an on-line parameters estimation The learning  ability of the adaptive neural fuzzy inference system allow as to decoupling the effect of each fault from the estimation of the others.  Our solution provides a method to detect, isolate, and estimate various faults in system components, using Adaptive Fuzzy Inference Systems Parameter Estimators (ANFISPEs) that are designed and based on parameterizations related to each class of fault. Each ANFISPE estimates the corresponding unknown Fault Parameter (FP) that is further used for fault detection, isolation and identification purposes. Simulation results reveal the effectiveness of the developed FDI scheme of an ACSs actuators of a 3-axis stabilized satellite.


Full Text:


Creative Commons License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.

International Journal of Electrical and Computer Engineering (IJECE)
p-ISSN 2088-8708, e-ISSN 2722-2578