Title :
Systems FDI Using Frequency Techniques Implemented with NN´s
Author :
Ferreiro Garcia, R. ; Perez Castelo, J. ; Pinon Pazos, A. ; Calvo Rolle, Jose Luis
Author_Institution :
Univ. da Coruna, A Coruna
Abstract :
Most of non-linear type 1 and type 2 control systems suffers from lack of detectability when model based techniques are applied on FDI tasks. This research work presents an strategy based on frequency techniques which includes massive neural networks based functional approximation on a parity space approach. As consequence of such technique on non-linear plants of types one and two, useful results were achieved.
Keywords :
fault diagnosis; function approximation; neural nets; nonlinear control systems; detectability; frequency techniques; functional approximation; model based techniques; neural networks; nonlinear control systems; parity space approach; systems FDI; Actuators; Backpropagation; Equations; Fault detection; Filters; Frequency; Neural networks; Observers; Redundancy; Sequential analysis; Backpropagation; Conjugate gradient; Fault detection; Fault isolation; Harmonic balance; Neural Networks;
Conference_Titel :
Automation Congress, 2006. WAC '06. World
Conference_Location :
Budapest
Print_ISBN :
1-889335-33-9
DOI :
10.1109/WAC.2006.376016
