Search

Heat transfer deterioration of supercritical fluids is difficult to predict accurately due to the numerous influencing factors. Traditional correlations failed to fit the relationships between many parameters over a wide range of experimental conditions. To this end, we developed a general artificial neural network model for simultaneously predicting the T w and Nu of supercritical H 2 O and CO 2 , which is the first model currently available for multi-fluid prediction. To maintain the compactness of the model feature space, redundant features are eliminated by feature selection. This model was trained with circle tube data but still maintained high accuracy on the non-circle tube data, demonstrating its strong generalization and independence of channel shape. High accuracy, applicability, and convenience over a wide range of applications are embraced in the ANN model, which lays a solid foundation for engineering application of the ANN model. The generalizability of the ANN model could be further improved by incorporating other fluid data. • A general artificial neural network has been used to predict T w and Nu for CO 2 and H 2 O. • Feature selection was adopted to remove the redundant features and keep a compact feature space. • A strong independent for the channel shape of the model was demonstrated. • The model outperforms the correlations. [ABSTRACT FROM AUTHOR]

The aim of this paper is to achieve an accurate prediction of heat transfer deterioration and Nu of supercritical CO 2 upward flowing in vertical channels using the artificial neural network method. Firstly, based on extensive experiments of round tubes and the square annular channel, a database with 11,589 data in 431 sets of experimental conditions was established. Then ANN models were trained with the training set which only contains the round tube data, and the optimal model structures were determined. The effects of input features on the prediction performance, including the experimental parameters, the dimensionless parameters, and the thermophysical property ratios, were compared, and the results showed that the model with all features in the input parameters performed best. The test set contains the experimental data of the round tubes and the square annular channel, the prediction results of the models on the test set showed that the model for HTD only has high precision on the round tube data, while the model for Nu has precise prediction performance both on the data of round tubes and the square annular channel. Simultaneously, the model for Nu shows a higher prediction performance than the correlations. • Effects of mass flux, heat flux, inlet temperature, and tube diameter on the heat transfer characteristics are evaluated. • Two models for the prediction of HTD and Nu were proposed based on the artificial neural network. • The effects of different input features on the ANN model performance are compared. • The model for predicting Nu outperforms the correlations. [ABSTRACT FROM AUTHOR]

The effects of gravity on the heat transfer performance of supercritical CO2 flowing within a vertical tube with a diameter of 4.75 mm are numerically studied in this paper. The main objectives are to comprehensively investigate the action of gravity and buoyancy on the supercritical heat transfer. An effective numerical method, which employs a modified Shear Stress Transfer k-ω model (SST k-ω), is applied at various gravity conditions. It is found that, for both upward and downward flows, the heat transfer of supercritical CO2 is improved with increased gravity magnitude. The effect of gravity on heat transfer are more pronounced under a low mass flux condition than that under a high mass flux condition and it is closely related to the variations of thermal properties. For the upward flow, the increased gravity magnitude accelerates the near wall fluid and creates a classic "M-shaped" radial velocity distribution. For the downward flow, the increased gravity magnitude decelerates the near wall fluid and creates a parabola-like radial velocity distribution. On one hand, the turbulent kinetic energies of both the upward and downward flows are enhanced as the gravity magnitude increases, which benefits heat transfer dominated by turbulent eddy diffusion. On the other hand, high-density fluid with high thermal conductivity occupies the near wall region as the gravity magnitude increases, which benefits heat transfer dominated by molecular diffusion. The results might provide some instructive advice to improve the design and operation safety of heat exchanger at various gravity conditions. [ABSTRACT FROM AUTHOR]