Title :
Improving Neural Networks Sensitivity Extraction of Electromagnetic Devices
Author :
Vieira, D.A.G. ; Vasconcelos, J.A. ; Caminhas, W.M.
Author_Institution :
Dept. of Electr. Eng., Fed. Univ. of Minas Gerais
Abstract :
This paper applies the parallel layer perceptron network trained with the minimum gradient method (PLP-MGM) to the problem of sensitivity extraction of electromagnetic devices. The networks trained with the MGM are less dependent of user´s defined parameters, as, for instance, the number of neurons. Some results are presented considering the sensitivity extraction of a loudspeaker magnet assembly, and they show the effectiveness of the proposed approach
Keywords :
electrical engineering computing; electromagnetic devices; gradient methods; loudspeakers; magnets; multilayer perceptrons; sensitivity; electromagnetic devices; loudspeaker magnet; minimum gradient method; neural networks sensitivity extraction; parallel layer perceptron network; Assembly; Data mining; Design optimization; Electromagnetic devices; Electromagnetic modeling; Fuzzy neural networks; Gradient methods; Loudspeakers; Neural networks; Neurons;
Conference_Titel :
Electromagnetic Field Computation, 2006 12th Biennial IEEE Conference on
Conference_Location :
Miami, FL
Print_ISBN :
1-4244-0320-0
DOI :
10.1109/CEFC-06.2006.1633090
