Title :
A Neural-Network Based Model of the Magnetic Nonlinearity of a DC Electromagnet
Author :
Díaz-Chacón, J.M. ; Ovando-Martínez, R. B B ; Hernández, C. ; Arjona, M.A.
Author_Institution :
Div. de Estudios de Posgrado e Investig., Inst. Tecnol. de la Laguna, Torreón, Mexico
fDate :
Sept. 28 2010-Oct. 1 2010
Abstract :
This paper shows how an Artificial Neural Network model (ANN) can be used to fit the nonlinear magnetic behavior of a DC electromagnet. An ANN model is trained to obtain a generalized function of the B2-vr curve, which is commonly used in an electromagnetic model. Once the generalized function and its derivative are obtained, they are used to solve a magnetostatic nonlinear problem of a DC device using the finite element method and the Newton-Raphson algorithm.
Keywords :
Newton-Raphson method; electromagnets; electronic engineering computing; finite element analysis; magnetic materials; magnetostatics; neural nets; ANN model; DC device; DC electromagnet; Newton-Raphson algorithm; artificial neural network model; electromagnetic model; finite element method; generalized function; magnetostatic nonlinear problem; nonlinear magnetic behavior; Artificial neural networks; Finite element methods; Magnetic flux; Magnetostatics; Neurons; Numerical models; Training; Artificial neural networks; electromagnetic model; finite element method; magnetization curve;
Conference_Titel :
Electronics, Robotics and Automotive Mechanics Conference (CERMA), 2010
Conference_Location :
Morelos
Print_ISBN :
978-1-4244-8149-1
DOI :
10.1109/CERMA.2010.142
