Artículos de revistas
Recurrent neurofuzzy network in thermal modeling of power transformers
Registro en:
Ieee Transactions On Power Delivery. Ieee-inst Electrical Electronics Engineers Inc, v. 22, n. 2, n. 904, n. 910, 2007.
0885-8977
WOS:000245599900020
10.1109/TPWRD.2006.874613
Autor
Hell, M
Costa, P
Gomide, F
Institución
Resumen
This work suggests recurrent neurofuzzy networks as a means to model the thermal condition of power transformers. Experimental results with actual data reported in the literature show that neurofuzzy modeling requires less computational effort, and is more robust and efficient than multilayer feedforward networks, a radial basis function network, and classic deterministic modeling approaches. 22 2 904 910