Modeling of Closed Loop Pulsating Heat Pipes by Neural Networks

Pulsating heat pipes (PHPs) are devices that their performance strongly depends on many factors such as filling ratio, working fluid, internal diameter, and etc. Therefore, variety of such parameters must be considered in experimental data or an accurate model must be used to characterize the behaviors of PHPs. In this study, a two layers neural network model is used to predict the behaviors of the PHPs. The effects of filling ratio and heat power input and working fluid on thermal resistance of PHPs are considered. The obtained results are in good agreement with available data and can be appropriate for predicting the trend of effective parameters on PHPs performance.