Predicting the cooling heat transfer coefficient of supercritical CO2 with a small amount of entrained lubricating oil by using the neural network method

A neural network method is presented to construct a semi-empirical prediction model of the heat transfer performance of supercritical carbon dioxide with a small amount of entrained PAG-type lubricating oil. The proposed approach involves a feedforward three-layer neural network, with the tube diameter, Prandtl number, Reynolds number, heat flux, thermal conductivity, and oil concentration as the input parameters, and the heat transfer coefficient as the output parameter. The experimental data used to construct the neural network correspond to a large number of experimental conditions, with the following variations: tube diameter from 1 to 6 mm, oil concentration from 0% to 5%, pressure from 8 to 10 MPa, mass flux from 200 to 1200 kg/m2 s, and heat flux from 12 to 24 kW/m2. The proposed model is found to agree well with the experimental results, with a deviation of ±20% for 87.3% of the valid data.