APPLICATION OF MACHINE LEARNING IN PROCESS ANALYSIS OF THE FRICTION-STIR WELDING TECHNIQUE

Friction Stir Welding (FSW) is a popular metal joining technique due to its solid-state deformation mechanism and high joining strength. The process is controlled by adjusting the process parameters, including rotational speed, translational speed, and axial force. However, the lack of proper settings and optimization of these parameters can result in a defective weld joint and unexpected failure. The traditional trial-and-error-based experimental and computational approaches for finding the optimal combination of parameters are expensive, time-consuming, and intricate. Machine Learning (ML), a data analysis technique, can be a useful alternative to optimize the process parameters in the FSW process. The tool rotational speed, translational speed, and axial force in FSW can be categorized as the input parameters or feature variables in the ML dataset. On the other hand, a performance parameter, such as the ultimate tensile strength of the welded joint, can be set as the output parameter or the target variable in the dataset. This study presents an ML modeling technique to predict the ultimate tensile strength for an FSW welded joint. A dataset is developed by collecting data for the three features and a target variable from experimental procedures. The skill of the trained ML model is estimated using the k-fold cross-validation procedure. The ML modeling findings for several supervised algorithms are evaluated based on the mean absolute error, root means squared error, relative absolute error, and root relative squared error. The sensitivity analysis is conducted by finding the global correlation coefficient. The ML model is validated by comparing its results with the experimental data and showing a good agreement between the ML model prediction and experimental results.