Computer Vision Algorithm for Predicting the Welding Efficiency of Friction Stir Welded Copper Joints from its Microstructures

¹ School of Industrial and Information Engineering, Politecnico Di Milano, Milan, Italy
² Symbiosis Institute of Technology, Symbiosis International (Deemed) University, Pune 412115, Maharashtra, India
³ Department of Finance, IIM Amritsar, India
⁴ Department of Material Science, Christian-Albrechts-University Kiel, Germany

^* Corresponding author: vijaykumar.jatti@sitpune.edu.in

Abstract

This research paper presents a study of the prediction of Friction Stir Welded (FSW) joint effectiveness using microstructure images with the aid of Convolutional Neural Networks (CNNs). A total of 3000 microstructure pictures were used for training the CNN, and 300 new microstructure photographs were used to test the accuracy of the model. The results showed that the CNN was able to accurately predict the effectiveness of FSW joints with an accuracy of 81 percent. The current work highlights the potential of using microstructure images and CNNs for improving the quality control and assessment of FSW joints in the materials and manufacturing industries. The findings of this study have important implications for the development of new techniques for improving the performance of FSW joints and for the wider application of computer vision and machine learning in the materials and manufacturing industries.