Title :
Diagnosis of AC motors with parity equations and neural networks
Author :
Pacheco, M.A. ; Arnanz, R. ; Mendoza, A. ; Miguel, L.J. ; Peran, J.R.
Author_Institution :
C.A.R.T.I.F. Parque Tecnol. de Boecillo, Valladolid, Spain
Abstract :
This paper presents a diagnosis method for AC motors using a linear residual generator and neural networks. The residual generator is obtained from an identified model of the motor. The residuals are classified with a SOM neural network that allows an easy representation of the state of the motor and the evolution of the faults. Finally, this system is validated with an experimental work on a real AC motor and a real-time implementation.
Keywords :
AC generators; AC motors; fault diagnosis; neural nets; power engineering computing; reliability; AC motor fault diagnosis method; SOM neural network; linear residual generator; parity equation; self organizing map; AC motors; Biological neural networks; Circuit faults; Mathematical model; Neurons; Vectors; AC motors; Fault detection; identification; model-based diagnosis; neural networks;
Conference_Titel :
Control Conference (ECC), 2001 European
Conference_Location :
Porto
Print_ISBN :
978-3-9524173-6-2
