Neural networks analysis of free laminar convection heat transfer in a partitioned enclosure

Abstract The feasibility of using neural networks (NNs) to predict the complete thermal and flow variables throughout a complicated domain, due to free convection, is demonstrated. Attention is focused on steady, laminar, two-dimensional, natural convective flow within a partitioned cavity. The objective is to use NN (trained on a database generated by a CFD analysis of the problem of a partitioned enclosure) to predict new cases; thus saving effort and computation time. Three types of NN are evaluated, namely General Regression NNs, Polynomial NNs, and a versatile design of Backpropagation neural networks. An important aspect of the study was optimizing network architecture in order to achieve best performance. For each of the three different NN architectures evaluated, parametric studies were performed to determine network parameters that best predict the flow variables. A CFD simulation software was used to generate a database that covered the range of Rayleigh number Ra = 104–5 × 106. The software was used to calculate the temperature, the pressure, and the horizontal and vertical components of flow speed. The results of the CFD were used for training and testing the neural networks (NN). The robustness of the trained NNs was tested by applying them to a “production” data set (1500 patterns for Ra = 8 × 104 and 1500 patterns for Ra = 3 × 106), which the networks have never been “seen” before. The results of applying the technique on the “production” data set show excellent prediction when the NNs are properly designed. The success of the NN in accurately predicting free convection in partitioned enclosures should help reduce analysis-time and effort. Neural networks could potentially help solve some cases in which CFD fails to solve because of numerical instability.

[1]  Tianqing Liu,et al.  Neural network analysis of boiling heat transfer enhancement using additives , 2002 .

[2]  Abdullatif Ben-Nakhi,et al.  Architecture and performance of neural networks for efficient A/C control in buildings , 2003 .

[3]  G. Smith,et al.  Numerical Solution of Partial Differential Equations: Finite Difference Methods , 1978 .

[4]  Yasar Islamoglu,et al.  Performance prediction for non-adiabatic capillary tube suction line heat exchanger: an artificial neural network approach , 2005 .

[5]  Mihir Sen,et al.  Dynamic prediction and control of heat exchangers using artificial neural networks , 2001 .

[6]  Nuri Yucel,et al.  Natural convection in partially divided square enclosures , 2003 .

[7]  Pawan P. Singh,et al.  PRESSURE DROP ESTIMATION IN TUBE FLOW of NON‐NEWTONIAN FLUID FOODS BY NEURAL NETWORKS , 1997 .

[8]  F. W. Kellaway,et al.  Advanced Engineering Mathematics , 1969, The Mathematical Gazette.

[9]  R. Benning,et al.  Initial studies of predicting flow fields with an ANN hybrid , 2001 .

[10]  Ihsan Dagtekin,et al.  Natural convection heat transfer by heated partitions within enclosure , 2001 .

[11]  Donald F. Specht,et al.  A general regression neural network , 1991, IEEE Trans. Neural Networks.

[12]  M. Hasnaoui,et al.  Natural convection in interacting cavities heated from below , 1997 .

[13]  Rajkumar Thirumalainambi,et al.  Training data requirement for a neural network to predict aerodynamic coefficients , 2003, SPIE Defense + Commercial Sensing.

[14]  F. Ampofo,et al.  Turbulent natural convection in an air filled partitioned square cavity , 2004 .

[15]  Mohamed A. Mahmoud,et al.  Neural network solution of the inverse vibration problem , 1999 .

[16]  Rafael Delgado-Buscalioni,et al.  Flow and heat transfer regimes in inclined differentially heated cavities , 2001 .

[17]  L. Piazza,et al.  Convective cooling of supercritical carbon dioxide inside tubes: heat transfer analysis through neural networks , 2003 .

[18]  Mihir Sen,et al.  Prediction of Turbulence Statistics Behind a Square Cylinder Using Neural Networks and Fuzzy Logic , 2003 .

[19]  Soteris A. Kalogirou,et al.  Artificial neural networks for predicting air flow in a naturally ventilated test room , 2001 .

[20]  Abdullatif Ben-Nakhi,et al.  Energy conservation in buildings through efficient A/C control using neural networks , 2002 .

[21]  Abdullatif Ben-Nakhi,et al.  Cooling load prediction for buildings using general regression neural networks , 2004 .

[22]  Antonio Delgado,et al.  Principal Feasability Studies Using Neuro – Numerics for Prediction of Flow Fields , 2004, Neural Processing Letters.