Prediction of Tool Eccentricity Effects on the Mechanical Properties of Friction Stir Welded AA5754-H24 Aluminum Alloy Using ANN Model

Optimization of 2024-T3 Aluminum Alloy Friction Stir Welding Using Random Forest, XGBoost, and MLP Machine Learning Techniques

This study optimized friction stir welding (FSW) parameters for 1.6 mm thick 2024T3 aluminum alloy sheets. A 3 × 3 factorial design was employed to explore tool rotation speeds (1100 to 1300 rpm) and welding speeds (140 to 180 mm/min). Static tensile tests revealed the joints' maximum strength at 87% relative to the base material. Hyperparameter optimization was conducted for machine learning (ML) models, including random forest and XGBoost, and multilayer perceptron artificial neural network (MLP-ANN) models, using grid search. Welding parameter optimization and extrapolation were then carried out, with final strength predictions analyzed using response surface methodology (RSM). The ML models achieved over 98% accuracy in parameter regression, demonstrating significant effectiveness in FSW process enhancement. Experimentally validated, optimized parameters resulted in an FSW joint efficiency of 93% relative to the base material. This outcome highlights the critical role of advanced analytical techniques in improving welding quality and efficiency.

Modeling and Experimental Investigation of the Impact of the Hemispherical Tool on Heat Generation and Tensile Properties of Dissimilar Friction Stir Welded AA5083 and AA7075 Al Alloys

This study investigated the effect of a hemispherical friction stir welding (FSW) tool on the heat generation and mechanical properties of dissimilar butt welded AA5083 and AA7075 alloys. FSW was performed on the dissimilar aluminum alloys AA5083-H111 and AA7075-T6 using welding speeds of 25, 50, and 75 mm/min. The tool rotation rate was kept constant at 500 rpm. An analytical model was developed to calculate heat generation and temperature distribution during the FSW process utilizing a hemispherical tool. The experimental results were compared to the calculated data. The latter confirms the accuracy of the analytical model, demonstrating a high degree of agreement. Sound FSW dissimilar joints were achieved at welding speeds of 50 and 25 mm/min. Meanwhile, joints created at a welding speed of 75 mm/min exhibited a tunnel-like defect, which can be attributed to the minimal heat generated at this particular welding speed. At a lower welding speed of 25 mm/min, a higher tensile strength of the dissimilar FSWed joints AA5083 and AA7075 was achieved with a joint efficiency of over 97%.

Advanced Analytical Methods of the Analysis of Friction Stir Welding Process (FSW) of Aluminum Sheets Used in the Automotive Industry

The paper provides general information on selected methods of joining aluminum sheets. The main focus is on the strength of the friction stir welding connection and the energy consumption of the process. The practical part of the study used aluminum alloy 2024-T3, the most commonly used alloy in the automotive industry. The study consisted of the FSW welding of two pieces of overlapping sheet metal, using different process parameters. The thickness of the sheet used was 1 mm. After the welding was completed, the test specimens were broken on a testing machine. During the tests, the appropriate process parameters were selected at which the weld showed the highest strength. The effect of implementing the FSW process should be to increase the efficiency of sheet-metal joining. It should also result in a reduction in the energy intensity of the process, which will translate into the lower production cost of the final product. Strength tests were carried out on eighteen samples of joined sheets. The best results were obtained at a feed rate of 100 (mm/min) and a rotational speed of 900 (rpm). It can also be seen that friction welding is an efficient and low-emission way of joining metals. Through the analysis, it can be concluded that in order to perform one meter of satisfactory welding, CO₂ emissions will be approximately 310 g. These are calculations based on data published by the National Balancing and Emissions Management Centre from 2019. Analyzing the 2019 data from the Society of Automobile Manufacturers, it is safe to say that the potential for implementing the FSW method in the automotive industry is huge.