Investigation of boiling heat transfer coefficients of different refrigerants for low fin, Turbo-B and Thermoexcel-E enhanced tubes using computational smart schemes

摘要: The design and manufacture of highly efficient evaporators heat exchangers in cooling machinery need an accurate estimation the boiling transfer coefficient refrigerants. In present study, coefficients different refrigerants were predicted using machine learning methods compared to existing empirical correlations. For this purpose, four models ANN, ANFIS, ELM SVM developed by MATLAB functions. 320 data collected on plain enhanced (low fin, Turbo-B, Thermo excel-E) tubes. percent deviation from actual value was between − 2.05 1.36% for − 4.97 8.72% − 38.11 83.01% − 17.35 78.37% SVM. results show that proposed ANN ANFIS are reliable predicting coefficient. They have a better performance than models. values RMSE, AARD R2 best model 74 W m−2 K−1, 0.399% 0.99993 306 W m−2 K−1, 1.117% 0.99883 2163 W m−2 K−1, 15.539% 0.94191 2212 W m−2 K−1, 14.905% 0.93921 intelligent algorithms more predictions