Investigation of Heat exchanger performance with delta-wing tape inserts for high Reynolds Number using various machine learning techniques

The present study utilizes the support vector regression (SVR) technique with a cubic kernel to forecast the performance of a double-pipe heat exchanger using T-W tape inserts with wing-width ratios of 0.31, 0.47, and 0.63. The SVR model that is established is applied to predict two key parameters, namely, the thermal performance (η) and the friction factor (f). Various scenarios are examined by considering the Reynolds number (Re) range from 5,500 to 14,500 and the wing-width ratio as inputs. The outcomes indicate that the SVR model accurately predicts the experimental data, as evidenced by the minimal mean square error (MSE) obtained when compared to the experimental values. Furthermore, the proposed SVR-based method predicts the thermal parameters with minimal variance. In addition, multiple regression models are utilized to evaluate the effectiveness of the proposed model, which shows that the recommended SVR technique is useful for predicting thermal parameters with minimal variance. It is noteworthy that the SVR model with the cubic kernel outperforms other modeling approaches in predicting the performance of the T-W double-pipe heat exchanger.