EXPLAINABLE ARTIFICIAL INTELLIGENCE FOR PREDICTING MATERIAL PROPERTIES IN SMART MANUFACTURING AND ENGINEERING EDUCATION

Abstract

Artificial Intelligence (AI) is increasingly transforming manufacturing systems through predictive analytics, process optimization, and intelligent decision-making. In materials engineering and metallurgy, machine learning models have demonstrated significant potential for predicting material properties such as hardness, tensile strength, wear resistance, and impact toughness based on processing parameters and microstructural characteristics. However, the adoption of AI-driven solutions in industrial and educational environments remains limited due to the "black-box" nature of many machine learning algorithms, which often provide predictions without transparent explanations. This lack of interpretability creates challenges for engineers, educators, and students who require a clear understanding of the relationships between manufacturing variables and material performance. This paper explores the role of Explainable Artificial Intelligence (XAI) as a framework for enhancing transparency, trust, and educational value in smart manufacturing systems. A conceptual model is proposed for integrating XAI techniques into materials engineering and mechatronics education, enabling learners to visualize and understand how process parameters influence predicted material properties. The framework combines machine learning prediction models with explain ability methods to support both industrial decision-making and engineering learning outcomes. Particular attention is given to applications involving heat treatment processes and advanced metallic materials, where accurate prediction and interpretation of property changes are critical. The study argues that explain ability should be considered not only a technical requirement but also an ethical and educational necessity in the era of Industry 5.0. By improving transparency and human understanding, XAI can strengthen collaboration between artificial intelligence systems and engineering professionals while preparing future engineers to responsibly utilize AI technologies