ANN‐Based Correlation for Heat Transfer Coefficient of Gas‐Liquid Flow for Different Flow Patterns in Horizontal Pipes

Abstract

Flow patterns and local heat transfer coefficients were measured for air–water flow in a horizontal pipe. A technique based upon a cascade neural network was developed for simultaneously recognition of the flow pattern (FP) and the corresponding heat transfer coefficient (hTP) for each FP. The results show good agreement between the estimated and the experimental values with 98.35% accuracy for FP and 95.6% accuracy for hTP. The results were compared with the Kim and Ghajar heat transfer correlation. The findings revealed that the proposed model is efficient and predicts flow more accurately than the Kim and Ghajar correlation.

Heat exchanger design considering variable overall heat transfer coefficient: An artificial neural network approach

“…Steady‐state and dynamic results were worked and validated, this demonstrating the precision of the proposed methodology. A neural network model was used by Hajor and Sobhanifar 21 to predict convective heat transfer coefficients in two‐phase flow (air‐water) using estimates of the flow pattern. For the model, the superficial Reynolds numbers for the liquid and gas phases are used as input variables, while the output of the cascade‐ANN model was the flow pattern type.…”