Nowadays, manufacturing sectors harness the power of machine learning and data science algorithms to make predictions of the optimization of mechanical and microstructure properties of fabricated mechanical components. The application of these algorithms reduces the experimental cost beside leads to reduce the time of experiments. The present research work is based on the depth of penetration prediction using supervised machine learning algorithms such as support vector machines (SVM), random forest algorithm, and robust regression algorithm. A friction stir spot welding (FSSW) was used to join two specimens of AA1230 aluminum alloys. The dataset consists of three input parameters: rotational speed (rpm), dwelling time (s), and axial load (kN), on which the machine learning models were trained and tested. The robust regression machine learning algorithm outperformed the rest algorithms by resulting in the coefficient of determination of 0.96. The second-best algorithm is the support vector machine algorithm, which has a value of 0.895 on the testing dataset. The research work also highlights the application of image processing techniques to find the geometrical features of the weld formation. The eroding and dilating procedures were carried out by the kernel size (3, 3) of type int 8. The results showed that the used algorithms can be considered to calculate the area, major/minor axis lengths, and the perimeter of the FSSW samples.

No abstract

No abstract