Prediction of pool boiling heat transfer coefficient for various nano-refrigerants utilizing artificial neural networks

In the present research, an artificial neural network model was developed to predict the pool boiling heat transfer coefficient (HTC) of refrigerant-based nanofluids based on a large number of experimental data (1342) extracted from the literature. Diverse training algorithms, e.g., Bayesian regulation backpropagation, Levenberg–Marquardt (LM), Resilient backpropagation and scaled conjugate gradient were utilized. Besides, several transfer functions like log-sigmoid (logsig), radial basis (radbas), soft max transfer function (softmax), hard-limit (hardlim), tan-sigmoid (tansig) and triangular basis (tribas) were applied for the hidden layer, and their influences on model correctness were surveyed. The effects of heat flux, saturation pressure, nanoparticle thermal conductivity, base fluid thermal conductivity, nanoparticle concentration (mass%), nanoparticles size and lubricant concentration (mass%) on the pool boiling HTC of refrigerant-based nanofluids were determined over wide ranges of operating conditions. A network possessing one hidden layer with 19 neurons using tansig and purelin as transfer functions in hidden and output layers in a row was introduced as a model having the best performance. In addition, LM was known as a much more efficient train algorithm in comparison with others resulting in extremely precise prediction. The outcomes indicated the present model could accurately estimate the pool boiling HTC of refrigerant-based nanofluids with a correlation coefficient (R2) of 0.9948 and overall mean square error of 0.01529.