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{203939,
        author = {Polimetla James Joy},
        title = {Artificial Intelligence in Metallurgical Engineering: Paradigms, Applications, and Future Prospects A Comprehensive Review},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {13},
        number = {1},
        pages = {1307-1319},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=203939},
        abstract = {Artificial Intelligence (AI) encompassing expert systems, fuzzy logic, evolutionary algorithms, machine learning, deep learning, computer vision, natural language processing, and digital twin technologies is reshaping every sub-discipline of metallurgical engineering. This review provides a systematic and comprehensive examination of AI paradigms as applied to materials design, ironmaking and steelmaking process control, casting and solidification, deformation processing, heat treatment, corrosion science, failure analysis, non-destructive evaluation, and sustainable metallurgy. Unlike narrower reviews focused on individual algorithms or unit operations, this paper spans the full AI technology spectrum across the entire metallurgical value chain. A total of 140 peer-reviewed publications from 2010 to 2025 are critically evaluated, encompassing industrial deployments at integrated steel plants, academic proof-of-concept studies, and benchmark comparisons across AI methodologies. The review identifies the evolutionary trajectory from rule-based expert systems of the 1980s to today's physics-informed neural networks and generative AI tools for alloy design. Key findings include: (i) hybrid AI-physics models consistently outperform purely data-driven approaches in extrapolation scenarios; (ii) computer vision has achieved superhuman accuracy in microstructure classification and defect detection; (iii) digital twins enabled by AI are delivering 15–30% energy savings in blast furnace operations; and (iv) generative AI (variational autoencoders, generative adversarial networks) opens entirely new routes for inverse alloy design. The review concludes with a structured research agenda addressing data sovereignty, AI explainability in safety-critical applications, and the role of AI in decarbonising the global steel industry.},
        keywords = {Artificial Intelligence; Expert Systems; Deep Learning; Computer Vision; Digital Twin; Alloy Design; Steelmaking; Failure Analysis; Sustainable Metallurgy; Generative AI},
        month = {June},
        }