<abstract xmlns="http://www.w3.org/1999/xhtml"><p> The main focus of the present study is to utilize the artificial neural network (ANN) in predicting the natural convection from horizontal isothermal cylinders arranged in vertical and inclined arrays. The effects of the vertical separation spacing to the cylinder diameter ratio (<italic>Py</italic>/<italic>d</italic>), horizontal separation spacing to the cylinder diameter ratio (<italic>Px</italic>/<italic>d</italic>) and Rayleigh number (<italic>Ra</italic>) variation on the average heat transfer from the arrays are considered via this prediction. The training data for optimizing the ANN structure is based on available experimental data. The Levenberg-Marquardt back propagation algorithm is used for ANN training. The proposed ANN is developed using MATLAB functions. For the best ANN structure obtained in this investigation, the mean relative errors of 0.027% and 0.482% were reached for the training and test data, respectively. The results show that the predicted values are very close to the experimental ones.</p></abstract>

The main focus of the present study is to utilize the artificial neural network (ANN) in predicting the natural convection from horizontal isothermal cylinders arranged in vertical and inclined arrays. The effects of the vertical separation spacing to the cylinder diameter ratio (Py/d), horizontal separation spacing to the cylinder diameter ratio (Px/d) and Rayleigh number (Ra) variation on the average heat transfer from the arrays are considered via this prediction. The training data for optimizing the ANN structure is based on available experimental data. The Levenberg-Marquardt back propagation algorithm is used for ANN training. The proposed ANN is developed using MATLAB functions. For the best ANN structure obtained in this investigation, the mean relative errors of 0.027% and 0.482% were reached for the training and test data, respectively. The results show that the predicted values are very close to the experimental ones.

Artificial neural network to predict the natural convection from vertical and inclined arrays of horizontal cylinders

Kermanshah University of Technology, Department of Chemical Engineering, Kermanshah, Iran

Kermanshah University of Technology, Department of Mechanical Engineering, Kermanshah, Iran

Razi University, Department of Mechanical Engineering, Kermanshah, Iran

Polish Journal of Chemical Technology

The main focus of the present study is to utilize the artificial neural network (ANN) in predicting the natural convection from horizontal isothermal cylinders...

Artificial neural network to predict the natural convection from vertical and inclined arrays of horizontal cylinders

Publié en ligne: 12 janv. 2013

Pages: 46 - 52

DOI: https://doi.org/10.2478/v10026-012-0101-6

This content is open access.