Comparative Review on Machine Learning-Based Predictive Modeling for Mechanical Characterization

Abstract

The development of machine learning (ML) methods in the field of material science has provided new possibilities for predictive modeling, especially in the field of mechanical material evaluation. The study provides an in-depth investigation of the utilization of various machine learning methods in predicting of mechanical characteristics throughout a range of different materials. A range of supervised learning models, such as regression tree models, support vector machine models, and neural networks, have been used to examine and forecast significant mechanical properties, including strength, ductility, and toughness. The models completed training as well as validation processes employing broad datasets obtained from experimental mechanical tests, covering tensile, compression, and fatigue examinations. Major focus was given to the process of choosing features and optimization in order to boost the accuracy and dependability of the predictions. This approach not only simplifies the method of material development but also improves understanding of the complex links among material composition, methods of processing, and mechanical properties. The research further examines the barriers and potential outcomes of applying machine learning (ML) in material characterization. It stresses the possibility for further improvements in predicted precision and efficiency of computing. Support vector machines, supervised artificial neural network, regression trees are most popular ML technique used in conducting predictive modelling.