Neural Representation of a Solar Collector with Statistical Optimization of the Training Set
Alternative ways of energy producing are essential in a reality where natural resources have been scarce and solar collectors are one of these ways. However the mathematical modeling of solar collectors involves parameters that may lead to nonlinear equations. Due to their facility of solving nonlinear problems, ANN (i.e. Artificial Neural Networks) are presented here, as an alternative to represent these solar collectors with several advantages on other techniques of modeling, like linear regression. Techniques for selecting representative training sets are also discussed and presented in this paper.
Unable to display preview. Download preview PDF.
- 3.Kudish, A.I., Santaura, P., Beaufort, P.: Direct measurement and analysis of thermosiphon flow. Solar Energy 35(2), 167–173Google Scholar
- 6.Duffie, J.A., Beckman, W.A.: Solar Engineering of Thermal Processes, 2a edn. John Wiley & Sons, Inc., USA (1999)Google Scholar
- 7.Kovács, Z.L.: Redes Neurais Artificiais. Edição acadêmica São Paulo, Cap 5, São Paulo. Brasil, pp. 75–76 (1996)Google Scholar
- 8.Bittencout, F.R., Zárate, L.E.: Controle da Laminação em Redes Neurais, com Capacidade de Generalização, e Lógica Nebulosa via Fatores de Sensibilidade, CBA, Natal, RN (2002)Google Scholar
- 9.Ashrae 93-86 Ra 91. Methods of Testing to Determine the Thermal Performance of Solar Collectors, American Society of Heating, Refrigeration, and Air-Conditioning Engineers, Inc., Atlanta (1986)Google Scholar
- 10.Zárate, L.E., Pereira, E.M., Silva, J.P., Vimieiro, R., Diniz, A.S., Pires, S.: Representation of a solar collector via artificial neural networks. In: Hamza, M.H. (ed.) International Conference On Artificial Intelligence And Applications, Benalmádena, Spain, September 8-11, pp. 517–522. ACTA Press, IASTED (2003a)Google Scholar