Niğde Ömer Halisdemir Üniversitesi Mühendislik Bilimleri Dergisi
Yazarlar: Özge YETİK
Konular:Mühendislik, Makine
DOI:10.28948/ngumuh.771650
Anahtar Kelimeler:Levenberg-Marquardt,Heat transfer,Numerical simulation,Artificial neural network.
Özet: Artificial neural network (ANN) is a modelling of the human brain. The aim of this study is to estimate the heat distribution with ANN around different cylinders. Within the scope of the study, square and circular cylinders were discussed. In this study, the temperature analysis of the cylinders was carried out with a program written in Fortran, not using a package program whose exact background is unknown. The results obtained from a writing code are more reliable. The study is discussed in two dimensions. The 3 most commonly used algorithms (Levenberg – Marguardt (LM), Pola-Ribiere Conjugate Gradient (CGP) and Scaled Conjugate Gradient (SCG)) were used to train with ANN. Cylinder type, x-coordinate and y-coordinate were the input variables; and temperature was the output variable. The most suitable algorithm was found to be LM-18 algorithm. The proximity of artificial neural networks and real values was evaluated statistically. These were R2, CoV and RMSE. R2, CoV and RMSE values in the training phase of Levenberg – Marguardt -18 neuron were determined to be 0.9939, 0.0044, 0.0107 while their values in the test phase were 0.9850, 0.0043 and 0.0190 respectively. The fact that the R2 value is so close to 1 is an indication that ANN is working very well.