Author(s): A. R. Nazemi; S. M. Hosseini; T. M. R. Akbarzadeh; N. H. Poorkhadem
Linked Author(s):
Keywords: Porous Media; Non-Darcy flow; Decision Fusion; Artificial Neural Networks
Abstract: By increasing the velocity of flow in coarse grain materials, local turbulences are often imposed to the flow. As a result, the flow regime through rockfill structures deviates from linear Darcy law; and nonlinear or non-Darcy flow equations will be applicable. Even though the structures of these nonlinear equations have some physical justification, they still need empirical studies based on laboratory conditions, to estimate parameters of these equations. Hence there is a great deal of uncertainty as an inherent part of the estimation process. In this paper we investigate several artificial neural networks architectures to combine three of the most commonly validated and utilized empirical solutions in the current literature. In this way, the results of the three empirical equations serve as inputs, and the combination framework serve as decision fusion algorithm. The results show that neural network methodology provides a powerful solution paradigm with a strong ability to track reality. Specifically, this paper concludes that Cascade Correlation architecture Neural Networks provide the best combination framework with the greatest accuracy among the considered conventional alternatives as well as other neural network structures.
Year: 2003