Application of Neural Networks to Predict Changing the Diameters of Bubbles in Pool Boiling Distilled Water

In this research, the capability of neural networks in 
modeling and learning complicated and nonlinear relations has been 
used to develop a model for the prediction of changes in the diameter 
of bubbles in pool boiling distilled water. The input parameters used 
in the development of this network include element temperature, heat 
flux, and retention time of bubbles. The test data obtained from the 
experiment of the pool boiling of distilled water, and the 
measurement of the bubbles form on the cylindrical element. The 
model was developed based on training algorithm, which is 
typologically of back-propagation type. Considering the correlation 
coefficient obtained from this model is 0.9633. This shows that this 
model can be trusted for the simulation and modeling of the size of 
bubble and thermal transfer of boiling.

• V. Nikkhah Rashidabad
• M. Manteghian
• M. Masoumi
• S. Mousavian
• D. Ashouri

• Bubble Diameter
• Heat Flux
• Neural Network
• Training Algorithm.

[1] Nukiyama,S., 1934, "The maximum and minimum values of heat
transmitted from metal to boiling water under atmospheric pressure",
J.Japan Soc. Mech. Eng., 37, 367
[2] Kutateladze, S. S., Gogonin, I. I., 1979, "Growth velocity and
detachment diameter of vapor bubbles of various fluids under free
convection conditions", Teplofizika Visokikh(in Russian), 4, PP.792-
797
[3] Mukherejee, A., Kandlikar, S.G., 2006. "Numerical study of single
bubbles with dynamic contact angle during nucleate pool boiling", Int. J.
Heat and Mass Transfer, 5.
[4] Jamialahmadi, M., Blochl,R., Muller-Steinhagen, H., 1991 "Pool boiling
heat transfer to saturated water and refrigerant 113", The Can. J. of
Chemical Eng., 69, PP.746-754
[5] Ng., G.W. "Application of Neural Networks to Adaptive Control of
Nonlinear Systems.” Willey & Sons Inc., NY 198. (1997) .
[6] McCulloch, W. W. and Pitts, W. "A Logical Calculus of Ideas Imminent
in Nervous Activity.” Bull. Math. Biophys. 5: 115 -133. (1943).
[7] Bellos, G. D., Kallinikos, L. E., Gounaris, C. E., and Papayannakos, N.
G. "Modeling of the performance of industrial HDS reactors using a
hybrid neural network approach.” Chem. Eng. and Proc. (2005). 44:505–
515.
[8] Rumelhart, D., and J. McClelland. "Parallel Distributed Processing.”
MIT Press, Cambridge, Mass. (1986).
[9] Moral, H., Aksoy, A., and Gokcay, C. F. "Modeling of the activated
sludge process by using artificial neural networks with automated
architecture screening.” Comp. and Chem. Eng. 32: 2471–2478. (2007).
[10] Hornik, K., Stinchombe, J., and White, H. "Multilayer feed forward
networks are universal approximators.” Neural Networks 2: 359–366.
(1989).
[11] Stuart Russell, Peter Norvig, Artificial Intelligence A Modern Approach,
Published by Pearson Education, Inc., New Jersey 2nd ed,1-100,2003.