![]() | Only 14 pages are availabe for public view |
Abstract The present work was applied on 4 mm thick AA6061 aluminum alloy sheets used in the construction of aircraft structures, such as wings and fuselages, yacht construction, including small utility boats, automotive parts. Simple tool pin and concave shoulder profile have been manufactured and used in FSW of butt joints at different rotation speeds, traveling speeds, and down force. The weld joints are evaluated using visual inspection and macrostructure investigation, as well as tensile and hardness testing. The present work also investigates the prediction of the mechanical properties of friction stir welding using the Artificial Neural Network (ANN) in MATLAB program. The experimental results were used to develop the mathematical model. The combined influence of welding speed, rotation speed, and axial force on the mechanical properties of 6061 T6 Al plates was simulated. The Results of the tensile strength test were used to train and test ANN. However, the main quality indicator of neural network has generalization ability to predict accurately the output of unseen test data. Verification of the numerical modeling was carried out by comparing the simulation results to experimental data. The validation shows agreement and satisfaction. |