A general method to predict the performance of closed pulsating heat pipe by artificial neural network

Abstract

In this paper, a novel predicting model of artificial neural network (ANN), which can be used for the PHP with different working fluids and wide operational conditions, was proposed for the first time to the author’s knowledge. The Kutateladze number (Ku), Bond number (Bo), Morton number (Mo), Prandtl number (Pr), Jacob number (Ja), number of turns (N), and the ratio of the evaporation section length to the diameter (le/D) were selected as the input parameters. The characteristic temperature to calculate the dimensionless number was the coolant temperature, rather than the average temperature of the evaporator and condenser, considering the latter one was still unknown in the early design stage. The predicted results agreed with the experimental data very well. The MSE and the correlation coefficient of the ANN model were 0.0138 and 0.9824, respectively. Meanwhile, the evaluation method for the evaporation section and condensation section temperature was also presented with a lumped parameter method. The calculation flow charts for two typical conditions, with the knowing of coolant temperature and knowing the heat source temperature, were also given. This paper was expected to be a good reference for the potential application of PHP.