Hamid Gharaei, Mahdi Salehi, Mehran Nahvi, Behzad Sadeghian,
Volume 2, Issue 2 (11-2016)
Abstract
In this research, artificial neural network (ANN) and genetic algorithm (GA) were used in order to produce and develop the NiAl intermetallic coating with the best wear behavior and the most value of hardness. The effect of variations of current, voltage and gas flow on the hardness and wear resistance were optimized by ANN and GA. In the following, the optimum values of current, voltage and gas flow were obtained 90(A), 10(v) and 9 (Lit/min), respectively. Then, the wear behavior in the environment temperature and high temperature for optimized NiAl compound was compared with two other experimental samples.
B. Sadeghian, A. Taherizadeh, M. Atapour, T Salehi, M Nosouhian,
Volume 3, Issue 1 (8-2017)
Abstract
Aluminum to stainless steel joints are broadly used in industries in order to reduce fuel consumption. While fusion welding is not a suitable method to join these metals. solid state welding, like friction welding (FW), is an effective way to this process. However, risk of intermetallic compounds (IMCs) formation is probable in these welds. In previews investigations formation of FeAl3, Fe2Al5 and Fe4Al13 is reported. In this study, effect of different parameters on generated heat and temperature distribution that lead to formation of these compounds in a FW of aluminum alloy to stainless steel is investigated using Finite Element Method (FEM). Additionally, a mathematical modeling of the parameters is performed using Artificial Neural Network (ANN) and the optimum level of the parameters has been found.
M. Mosallaee, A.h. Morshedy,
Volume 9, Issue 2 (1-2024)
Abstract
In this research, the optimization of the artificial neural network (ANN) capability for predecting the tensile strength and elongation of friction stir welded Al-5083 (FS-welded Al-5083) was carried out. The effective parameters of ANN, such as the number of layers, number of neurons in hidden layers, transfer function between layers, the learning algorithm and etc. were investigated and the efficient neural network was determined to predict the tensile properties of FS-welded Al-5083. The investigations revealed that the perceptron neural network with two hidden layers and 17 neurons numbers, Lunberg-Marquardt training algorithm and Logsig transfer function for the intermediate layers and Tansig transformation function for the output layer is the most optimized neural network for the prediction. The optimized network has an optimal structure based on the minimum value of the mean square error of 0.05, the maximum total correlation coefficient of 0.93 and the line regression with an angle of 45 degrees between the actual and estimated values. Therefore, this network has a good performance for training, generalizing and estimating of tensile strength and elongation of FS-welded Al-5083.
