Micro segment analysis and machine learning prediction for thermal-hydraulic parameters of propane condensation flow in a PCHE straight channel

Abstract

In the LNG regasification process, the printed circuit heat exchangers(PCHE) is an ideal choice for vaporizer, with propane as the intermediate working medium in the hot side of PCHE. In this work, numerical simulations of propane condensation flow and heat transfer at different operating parameters was carried out in a semi-circular straight channel of PCHE. The micro-segment analysis method was used to present the local heat transfer coefficient and pressure drop in the channel. The results indicate that the propane condensation process can be divided into three stages: the “constant temperature condensation stage” in the droplet condensation state, the “varying temperature condensation stage” in the film condensation state, and the “subcooled stage” in the liquid phase state. Different operating parameters can affect the start and end position of each stage, as well as the parameter values in the same state. An artificial neural network method was used to predict the local heat transfer coefficient and pressure drop, with the predicting error of less than 5 % and 10 % respectively. This study provides a machine learning method to accurately predict the flow and heat transfer parameters for propane condensation flow in PCHE channel and valuable for future design of LNG vaporizer.