Ensemble Deep Learning Ultimate Tensile Strength Classification Model for Weld Seam of Asymmetric Friction Stir Welding

Friction stir welding is a material processing technique used to combine dissimilar and similar materials. Ultimate tensile strength (UTS) one of the most common objectives welding, especially friction (FSW). Typically, destructive testing utilized measure UTS welded seam. Testing for weld seam typically involves cutting specimen utilizing machine capable UTS. In this study, an ensemble deep learning model was developed classify FSW Consequently, could quality in relation its using only image Five distinct convolutional neural networks (CNNs) were employed form heterogeneous proposed model. addition, segmentation, augmentation, efficient decision fusion approach implemented To test model, 1664 pictures seams created tested The divided into three categories: below 70% (low quality), 70–85% (moderate above 85% (high quality) base material. AA5083 AA5061 materials study. computational results demonstrate that accuracy suggested 96.23%, which 0.35% 8.91% greater than literature’s advanced CNN