Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{203942,
        author = {Polimetla James Joy},
        title = {Machine Learning and Artificial Intelligence Applications in Metallurgical Engineering: A Comprehensive Review},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {13},
        number = {1},
        pages = {1320-1329},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=203942},
        abstract = {Over the past decade, machine learning (ML) and artificial intelligence (AI) have moved from peripheral curiosities to working tools across metallurgical engineering, reshaping how researchers and plant engineers approach materials discovery, process optimisation, and quality assurance. This review surveys that shift. We examine ML methods (supervised and unsupervised learning, deep neural networks, and reinforcement learning) as they have been applied to phase diagram prediction, mechanical property forecasting, steelmaking process control, corrosion modelling, heat treatment, additive manufacturing, and non-destructive evaluation. Throughout, our interest is in how traditionally empirical, experience-driven practice is giving way to data-driven, predictive frameworks. Drawing on 128 publications from 2015 to 2025, we map the prevailing algorithmic trends, point to benchmark datasets, and weigh the practical obstacles to deployment: limited data, weak physical interpretability, and uneasy integration with computational thermodynamics (CALPHAD). We also identify open research gaps and sketch a roadmap that includes physics-informed neural networks (PINNs), graph neural networks for microstructure representation, and federated learning for industrial data sharing. The aim is to provide a single point of reference for metallurgical researchers, process engineers, and educators moving into data-driven materials science.},
        keywords = {Machine Learning; Artificial Intelligence; Metallurgical Engineering; Materials Informatics; Neural Networks; Process Optimisation; Mechanical Properties; Phase Prediction},
        month = {June},
        }