MACHINE LEARNING CLASSIFICATION MODELS FOR DETECTION OF THE FRACTURE LOCATION IN DISSIMILAR FRICTION STIR WELDED JOINT

Data analysis is divided into two categories i.e. classification and prediction. These two categories can be used for extraction of models from the dataset and further determine future data trends or important set of classes available in the dataset. The aim of the present work is to determine location of the fracture failure in dissimilar friction stir welded joint by using various machine learning classification models such as Decision Tree, Support Vector Machine (SVM), Random Forest, Naïve Bayes and Artificial Neural Network (ANN). It is observed that out of these classification algorithms, Artificial Neural Network results have the best accuracy score of 0.95.