International Scientific Journal

Thermal Science - Online First

online first only

Comparison study of CFD and artificial neural networks in predicting temperature fields induced by natural convention in a square enclosure

Natural convection in an enclosure is a classical problem in heat transfer field. In this study, natural convection induced by the heat source in the enclosure is studied with two analysis methods, i.e. Computational Fluid Dynamics (CFD) and Artificial Neural Networks (ANN). The heat transfer in the enclosure is an unsteady process. During this process, the temperature fields in the enclosure are changing with time. The vertical temperature field of y=0 at one moment is picked up for investigation. Firstly, FLUENT software which is a simulation program of CFD is adopted to simulate the temperature fields under different computation conditions. Then part of the simulation condition's temperature data is picked for training an ANN model and the rest of data is used for validating the ANN model. It has been found from the comparison between the CFD simulation and ANN prediction that the two results have a good agreement with each other. In the comparison, the max relative errors (MAEs) are around 12 %, mean relative errors (MREs) are around 0.3 %, mean square errors (MSEs) are around 0.6 %, values of absolute fraction of variance (R2) are all not less than 0.99. The results demonstrated that the ANN prediction have enough accuracy.
PAPER REVISED: 2018-01-16
PAPER ACCEPTED: 2018-02-01
  1. Lage, J. L., Bejan, A., The Ra-Pr domain of laminar natural convection in an enclosure heated from the side, Numerical Heat Transfer Applications, Part A 19 (1991), pp. 21-41
  2. Ntibarufata, E., et al., Natural convection in partitioned enclosures with localized heating, International Journal of Numerical Methods for Heat & Fluid Flow, 3 (1993) , pp. 133-143
  3. Das, D., et al., Studies on natural convection within enclosures of various (non-square) shapes - A review, International Journal of Heat and Mass Transfer, 106 (2017) , pp. 356-406
  4. Mahmoodi, M., et al., Free convection of a nanofluid in a square cavity with a heat source on the bottom wall and partially cooled from sides, Thermal Science, 18 (2014), (suppl.2) :283-300
  5. Jani, S., et al., Numerical investigation of natural convection heat transfer in a symmetrically cooled square cavity with a thin fin on its bottom wall, Thermal Science, 18(2014),4, pp. 1119-1132
  6. Minea, A. A., A review on analytical techniques for natural convection investigation in a heated closed enclosure: Case study, Thermal Science, 19 (2015) ,3, pp. 1077-1095
  7. Oke. S. A., A literature review on artificial intelligence, International Journal of Information and Management Sciences, 19 (2008) , pp. 535-570
  8. Erdemir, D., Ayata, T., Prediction of temperature decreasing on a green roof by using artificial neural network, Applied Thermal Engineering, 112 (2017) , pp. 1317-1325
  9. Mahmoud, M.A., Ben-Nakhi. A.E., Neural networks analysis of free laminar convection heat transfer in a partitioned enclosure, Communications in Nonlinear Science and Numerical Simulation, 12 (2007) , pp. 1265-1276
  10. Ben-Nakhi, A.E., et al., Inter-model comparison of CFD and neural network analysis of natural convection heat transfer in a partitioned enclosure, Applied Mathematical Modelling, 32 (2008) , pp. 1834-1847
  11. Varol, Y., et al., Prediction of flow fields and temperature distributions due to natural convection in a triangular enclosure using Adaptive-Network-Based Fuzzy Inference System (ANFIS) and Artificial Neural Network (ANN), International Communications in Heat and Mass Transfer, 34 (2007) , pp. 887-896
  12. Varol, Y., et al., Analysis of adaptive-network-based fuzzy inference system (ANFIS) to estimate buoyancy-induced flow field in partially heated triangular enclosures, Expert Systems with Applications, 35 (2008) , pp. 1989-1997
  13. Sudhakar, T.V.V., et al., Optimal configuration of discrete heat sources in a vertical duct under conjugate mixed convection using artificial neural networks, International Journal of Thermal Sciences, 48 (2009) , pp. 881-890
  14. Ozsunar, A., et al., The prediction of maximum temperature for single chips' cooling using artificial neural networks, Heat & Mass Transfer, 45 (2009) , pp. 443-450
  15. Atayılmaz, S.O., et al., Application of artificial neural networks for prediction of natural convection from a heated horizontal cylinder, International Communications in Heat and Mass Transfer, 37 (2010) , pp. 68-73
  16. Selimefendigil, F., Oztop, H.F., Fuzzy-based estimation of mixed convection heat transfer in a square cavity in the presence of an adiabatic inclined fin, International Communications in Heat and Mass Transfer, 39 (2012) , pp. 1639-1646
  17. Karami, A., et al., Adaptive neuro-fuzzy inference system (ANFIS) to predict the forced convection heat transfer from a v-shaped plate, Heat & Mass Transfer, 49(2013), pp. 789-798
  18. Yang, X., et al., Optimum design of flow distribution in quenching tank for heat treatment of A357 aluminum alloy large complicated thin-wall workpieces by CFD simulation and ANN approach, Transactions of Nonferrous Metals Society of China, 23(2013) , pp. 1442-1451
  19. Aminossadati, S.M., et al.,Computational analysis of magnetohydrodynamic natural convection in a square cavity with a thin fin, European Journal of Mechanics B/Fluids, 46 (2014) , pp. 154-163
  20. Taghavifar, H, Shabahangnia E., Prediction of thermal gradient in an air channel with presence of electrostatic field using artificial neural network, Heat & Mass Transfer, 50 (2014), pp. 1515-1524
  21. Ahamad, S. I., Balaji, C., Inverse conjugate mixed convection in a vertical substrate with protruding heat sources: a combined experimental and numerical study, Heat & Mass Transfer , 52 (2016) , pp. 1243-1254
  22. Ahmadi, M. H., et al., Prediction of power in solar stirling heat engine by using neural network based on hybrid genetic algorithm and particle swarm optimization, Neural Computing and Applications, 22 (2013),6, pp. 1141-1150
  23. Ahmadi, M. H., et al., Using GMDH neural networks to model the power and torque of a stirling engine, Sustainability, 7 (2015), 2, pp. 2243-2255
  24. Ahmadi, M. H., et al., Artificial neural networks modelling of the performance parameters of the Stirling engine, International Journal of Ambient Energy, 37 (2016),4, pp. 341-347
  25. Toghyani, S., et al., Artificial neural network, ANN-PSO and ANN-ICA for modelling the Stirling engine, International Journal of Ambient Energy ,37 (2016), 5, pp. 456-468
  26. Hamimid, S., et al., Numerical study of natural convection in a square cavity under non-boussinesq conditions, Thermal Science, 20(2016),5, pp. 1509-1517
  27. Calcagni, B., et al., Natural convective heat transfer in square enclosures heated from below, Applied Thermal Engineering, 25 (2005) , pp. 2522-2531
  28. Montana, D. J., Davis. L., Training feed-forward neutral networks using genetic algorithms, Proceeding of the International Joint Conference on Artificial Intelligence. Los Altos, 1989, pp. 762−767
  29. Liu, Q., et al., Research on Initialization AIgorithms of Weights and Biases of BP Neural Netwok, Jourml of Southwest Chim Nornlal University(Natural Science Edition) 35(2010),6, pp. 137-141 (in chinese)