Participatory learning in power transformers thermal modeling

Autor(es)

Hell, Michel ^[1] ; Costa, Jr., Pyramo ^[2] ; Gomide, Fernando ^[1]

Afiliação do(s) autor(es)

^[1] State Univ Campinas UNICAMP, Fac Elect & Comp Engn, Dept Comp Engn & Automat DCA, BR-13083960 Campinas, SP - Brazil

^[2] Pontificia Univ Catolica Minas Gerais, PPGEE PUC MG, Grad Program Elect Engn, BR-30535610 Belo Horizonte, MG - Brazil

• Tipo de documento: Artigo Científico
• Fonte: IEEE Transactions on Power Delivery; v. 23, n. 4, p. 2058-2067, OCT 2008.
• Citações Web of Science: 9

Resumo

In this paper, we introduce a new approach based on the participatory learning paradigm to train a class of hybrid neurofuzzy networks whose aim is to model the thermal behavior of power transformers. The participatory learning paradigm is a training procedure that tends to emulate the human learning mechanism. An acceptance mechanism determines which observation is used for learning based upon their compatibility with the current beliefs. The proposed model is compared with actual data obtained from an experimental power transformer equipped with fiber-optic probes. Comparisons with alternative approaches suggested in the literature are included to show the effectiveness of participatory learning to model the thermal behavior of power transformers. (AU)

• Processo FAPESP: 03/05042-1 - Abordagem neurofuzzy para modelagem de sistemas dinamicos nao lineares.
• Beneficiário: Michel Bortolini Hell
• Modalidade de apoio: Bolsas no Brasil - Doutorado