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.
Mr. Davoud Ramazani, Dr. Saeid Jabbarzare, Dr. Masoud Kasiri-Asgarani, Dr Mojtaba Alchian,
Volume 9, Issue 2 (8-2026)
Abstract
In this study, the effect of tool rotational speed in the double-sided friction stir welding (FSW) process on the microstructural characteristics, phase distribution, and hardness of annealed AA7075 aluminum alloy was investigated. Aluminum sheet specimens were welded from both sides at three tool rotational speeds of 800, 1000, and 1200 rpm and a constant traverse speed of 50 mm/min. After friction stir welding of the AA7075 alloy, the specimens were prepared for metallographic, microstructural, and mechanical examinations. Macrostructural and microstructural evaluations were carried out using appropriate chemical etching, optical microscopy, and scanning electron microscopy equipped with energy-dispersive spectroscopy (SEM–EDS). In addition, X-ray diffraction (XRD) analysis was employed to identify the phases and intermetallic compounds. The microhardness distribution across the transverse cross-section of the joint was also measured using the Vickers method in order to evaluate variations in mechanical properties across different weld regions. Microscopic examination of the weld zone revealed that increasing the tool rotational speed increased the weld zone width from approximately 6.5 to 8.3 mm. The average grain size decreased markedly, from 224 µm in the base metal to the range of 15–20 µm in the weld zone. XRD analysis confirmed the presence of MgZn2 and Al2CuMg/Al2Mg3Zn intermetallic phases. With increasing rotational speed, these precipitates became more spheroidal and finer in size. The distribution and size of precipitates in the weld zone changed significantly compared with those in the base metal; owing to the thermal and mechanical effects induced by tool movement, the precipitates became more dispersed and refined. The local hardness in the weld zone increased with increasing rotational speed, reaching approximately 165 HV, which represents a significant improvement compared with the base metal hardness of 135 HV. This hardness enhancement is attributed to grain refinement and an increase in the density of intermetallic precipitates, which contribute to improved mechanical strengthening. Moreover, all welded specimens were free from structural defects such as cracks or porosity, indicating excellent weld quality. The present results can provide an effective guideline for optimizing friction stir welding parameters in high-performance aluminum alloys.
