Yazar "Mercan, Hatice" seçeneğine göre listele
Listeleniyor 1 - 2 / 2
Sayfa Başına Sonuç
Sıralama seçenekleri
Öğe Determination of heat transfer rates of heavy-duty radiators for trucks having flattened and double-U grooved pipes with louvered fins by ANN method: an experimental study(Springer Heidelberg, 2022) Mercan, Hatice; Sonmez, Furkan; Colak, Andac Batur; Dalkilic, Ahmet SelimIn this study, radiators equipped with conventional pipes and newly proposed double-U grooved and brazed pipes are compared with each other under similar operating conditions. The radiators' heat transfer performances have been evaluated experimentally and validation is done using the analytical Number of Transfer Unit Method. The cooling fluid has a fixed composition with 50% water and 50% ethylene glycol. Coolant flow rate changed between 2.5 and 7 kg/s, air velocity changed between 1.5 and 12 m/s and both inlet pressure and temperature values have been kept constant for air and coolant fluid sides throughout the experiments. Heat transfer rate, exit coolant temperature, friction coefficient, pressure drop inside the radiator and the total heat transfer coefficient have been assessed experimentally and compared under changing operation conditions. Using the obtained experimental data, an Artificial Neural Network model has been generated to determine the heat transfer rate for each radiator. The data taken from the numerical model have been compared with the practical one and analyzed extensively. It is observed that heat transfer rate and pressure drop are the highest for the Double U-grooved pipe radiator. The prediction values acquired from the reformed neural network are in good compatibility with the practical data.Öğe Prediction of heat transfer coefficient, pressure drop, and overall cost of double-pipe heat exchangers using the artificial neural network(Elsevier, 2022) Colak, Andac Batur; Acikgoz, Ozgen; Mercan, Hatice; Dalkilic, Ahmet Selim; Wongwises, SomchaiTypically, success in the estimation of machine learning is expected to rise with increasing input parameters, whereas the noise issue may rarely arise owing to redundant input factors undesirably influencing the learning algorithm. The parameters such as overall heat transfer coefficient, pressure drop, and overall cost have been determined by two different artificial neural networks evaluated by a multi-layer perceptron model. Using the Levenberg-Marquardt training algorithm, in the first model input layer, a total of 10 input parameters rho, n(p), k(1), Re-1, f(i), Re-2, f(o), n(s), P-1 and P-2 have been defined, while the second involves 8 input parameters by subtracting pumping powers from the first one, thus the noise issue has been investigated using unnecessary input parameters. Overall heat transfer coefficient, tube/annulus sides pressure drops, and overall cost have been estimated with deviations of 0.16%, 0.23%, 0.02%, and 0.003% via Model 1, 0.02%, 0.18%, 0.16%, and 0.15% via Model 2, respectively. Moreover, Model 1 results in the best mean squared errors for annulus side pressure drop and overall cost with the values of 2.54E-04 and 1.93E-04, correspondingly, whereas Model 2 yields the best values of 1.11E-04 and 1.90E-04 for overall heat transfer coefficient and tube side pressure drop, sequentially.