Boiling heat transfer prediction in helical coils under terrestrial gravity with artificial neural network

In the present article, deep learning neural network model has been proposed to predict the boiling heat transfer in helical coils under terrestrial gravity conditions and compare with actual experimental data. A new test rig is set up with the heat flux can be up to 15100 W/m² and the mass velocity range from 40 to 2000 kg m^-2 s^-1. Total 877 data sample have been used in the present neural model. Artificial Neural Network (ANN) model developed in Python environment with Feed-forward Back-propagation (FFBP) Multi-layer Perceptron (MLP) using five parameters (helical coils dimensions, mass flow rate, inlet pressure, heating power, inlet temperature) and three parameters (outlet pressure, outlet temperature, wall temperature) have been used in input layer and output layer respectively. Levenberg-Marquardt (LM) algorithm using L2 Regularization with 6-35 neurons has been used to find out the optimal model. A typical feed-forward neural network model composed of three layers, with 30 numbers of neurons in each hidden layer, has been found as optimal on the basis of statistical error analysis. The 5-30-30-3 neural model predict the helical coils characteristics with accuracy of 97.68% in training stage and 97.52% in testing stage. The result indicated that the proposed ANN model successfully predicts the heat transfer performance in helical coils.