Experimental Thermohydraulic Assessment of Novel Curved Ribs for Heat Exchanger Tubes: A Machine Learning Approach

Abstract

Heat transfer enhancement using curved ribs of different cross sections, viz., square, rectangular, triangular, and circular, is a crucial study for designing heat-exchanging devices for various applications, and their thermohydraulic performance prediction using machine learning technique is a vital part of the modern world. An experimental study on using curved ribs suitable for heat transfer enhancement for the circular tube is presented for turbulent airflow with Reynolds numbers varying from 10,000 to 50,000. The machine learning methodology is used to predict the thermohydraulic performance assessment of curved ribs. The square cross-sectioned curved ribs produce the highest performance factor R3 of 1.5 to 2.65 to the equivalent Reynolds number Rec value of 20,000. It is observed that most of the curved rib configurations show a performance ratio R3 maximum and are suitable at a low Reynolds number value. At moderate and high Reynolds number values, the performance factor values decrease due to a rise in the pressure drop values for a few curved rib configurations. An artificial neural network (ANN) model predicts with an accuracy of 95% with the present study experimental values for the heat transfer performance indicators like average heat transfer enhancement Nua/Nus, average heat transfer enhancement fa/fs, and performance ratio R3, i.e., Nua/Nuc.