AI-Enabled Pathways For Circular Economy Transition In Steel Industry To Foster Reuse And Recycle

Abstract

This research aims to adopt CE strategies within the steel industry to mitigate greenhouse gas emissions and resource waste; therefore, we will examine the potential of AI in supporting CE practices throughout the entire lifecycle of steel products (including both pre-and post-manufactured products). This research paper presents a review of qualitative case studies aligned to the research questions and a systematic literature review, following the PRISMA Guidelines, of 31 research articles from the past ten years to determine how AI applications, technological enablement, and performance improvements can enhance the economic viability and sustainable performance of steel manufacturing operations. We have found that by integrating machine learning, deep learning, and predictive analytics into their processes, companies can increase the amount of recycled material used and decrease their reliance on virgin resource content; hence, AI applications allow steel producers to become more environmentally and financially sustainable. The steel industry faces several challenges to become more circular, including the presence of heterogeneous materials, fragmented lifecycle data, and very little integration of AI and other digital devices (D/E/S) into the supply chain. To facilitate a better understanding of how to implement AI to create a sustainable, closed-loop steel supply chain, a conceptual framework has been developed, which provides practical guidance on successfully implementing sustainable steel production processes. Future research in this area should continue to explore the feasibility of using AI technology in conjunction with digital twins, multi-modal modelling merging data stream from multiple sectors, and enhanced cross-sectoral collaboration in creating a fully closed-loop steel supply chain.