Analysis of adaptive-network-based fuzzy inference system (ANFIS) to estimate buoyancy-induced flow field in partially heated triangular enclosures

Abstract

Adaptive-network-based Fuzzy Inference System (ANFIS) was used to predict temperature and flow field due to buoyancy-induced heat transfer in a partially heated right-angle triangular enclosure. Results are obtained for two-dimensional, steady and laminar flow. Data were generated from earlier studies which were obtained from a CFD-based computer code writing in Fortran. Equations were analyzed using finite difference method. Effective parameters on flow and temperature fields are Rayleigh number, location of partial heater and height-to-base ratio of triangular enclosures. Both instability and accuracy related results will be discarded by using ANFIS. Thanks to using of ANFIS, computation time, memory space and effort were reduced. (C) 2007 Elsevier Ltd. All rights reserved.