Numerical analysis and artificial neural network-based prediction of two-phase flow pressure drop of refrigerants in T-junction

The two-phase flow behaviors in T-junction are quite complex in energy transport systems. In this paper, the two-phase flow pressure drop of refrigerants in a horizontal branching T-junction was analyzed numerically and predicted using artificial neural network. Firstly, the distribution of static and total pressure was obtained based on Eulerian method, and the parametric studies on the local pressure drop were conducted. It is observed that the vortexes in the entrance of branch pipe lead to the pressure fluctuation and irreversible pressure losses, and the descend-ascend of static and total pressure happens under high mass flow split ratio in run pipe. Then, the ANN predicting model of local pressure drop coefficients was established. It shows that GA-BPNN and PSO-BPNN has the best predicting ability for K-12J and K-13J respectively, and the relative errors are within 10% for most cases. Finally, the sensitivity analysis was conducted, indicating that the effect of mass flow split ratio (F) and inlet quality (x(1)) is the most significant for K-12J and K-13J respectively.

Automated summary

The study analyzed the two-phase flow pressure drop of refrigerants in a horizontal branching T-junction through numerical simulation and artificial neural network, establishing a predicting model for the local pressure drop coefficients. The results showed that vortexes in the entrance of branch pipe and high mass flow split ratio led to pressure fluctuations and descending-ascending static and total pressure, with the best predicting abilities found in GA-BPNN and PSO-BPNN models. Sensitivity analysis revealed mass flow split ratio and inlet quality as significant factors for pressure drop coefficients in different T-junction configurations.