Real‐Time Hot‐Rolled Coil Placement Recommendation System with Data‐Driven Model

• Published in: Advanced intelligent systems Vol. 7; no. 8
• Main Authors: Lee, Chihun, Shin, Da Seul, Kang, Youn Hee, Choi, Kanghyouk, Park, Dong Yong, Rho, Junsuk
• Format: Journal Article
• Language: English
• Published: Weinheim John Wiley & Sons, Inc 01.08.2025; Wiley
• Subjects: Accuracy; Artificial neural networks; coil cooling; coil yard management; Coils; Cooling; Costs; data‐driven modeling; Effectiveness; Finite element method; Hot rolling; hot‐rolled coils; Manufacturing; Mechanical properties; neural network; Neural networks; Optimization techniques; Placement; Product quality; Real time; Recommender systems; Simulation; Software; Steel making; Temperature
• ISSN: 2640-4567; 2640-4567
• DOI: 10.1002/aisy.202400826

Hot‐rolled coils (HRCs) are essential in various industries, including automotive, construction, and machinery. However, the cooling process of HRCs in the yard tends to be nonuniform because of complex thermal interactions between adjacent coils and varying environmental conditions, which affect the mechanical properties and steel quality. In this study, we used simplified heat transfer models based on the finite element method (FEM) to generate realistic simulation data. We developed a novel management system that integrates two trained artificial neural networks with deep and wide networks using hyperparameter tuning to improve prediction speed, a known limitation of FEM. The system predicts temperature variations at multiple points on the coil, enabling strategic placement that minimizes temperature deviations and enhances cooling uniformity. This real‐time computational approach eliminates the necessity for additional cooling equipment and ensures high product quality. The system's efficacy was validated through case studies, revealing dynamic adjustments and optimized placements. The proposed system achieved a mean absolute error of 3.44 and a mean absolute percentage error of 0.24%, outperforming conventional regression techniques. These results demonstrated the effectiveness of the system in simulating real‐world cooling scenarios and its feasibility for real‐time cooling optimization in steel manufacturing. A real‐time coil placement system is developed to enhance cooling uniformity in hot‐rolled steel coils. Combining finite element simulations with artificial neural networks, the system predicts temperature distributions under various yard layouts and recommends optimal positions. This intelligent framework reduces temperature deviation without extra cooling equipment, improving steel quality and operational efficiency.