IoT-based framework for digital twins in steel production: A case study of key parameter prediction and optimization for CSR

Abstract

Cold-rolled strips are a pivotal product of advanced strip rolling technology in iron and steel production with stringent process standards. Over an extended period, the existence of 'information silos' between cold strip rolling (CSR) and its upstream processes, particularly hot strip rolling (HSR), causes a persistent challenge in achieving collaborative optimization throughout the entire process, thereby constraining progress in product quality. To overcome this challenge, a digital twin framework was proposed to consolidate diverse data from HSR and CSR production lines into a centralized data centre, forming a 'data continent.' This approach establishes a comprehensive dataset for model-driven training and prediction in virtual space. An improved Light gradient boosting machine (IlightGBM) is introduced, enabling high-precision rolling force prediction in unsteady-state rolling and providing essential variables for establishing the tension optimization objective function. A control function is implemented to minimize rolling force fluctuations, and three population algorithms (TPA) are devised for its solution. This strategy successfully realizes collaborative tension optimization across multiple stands, with the rolling speed acting as a follower. The proposed approach was implemented in a large-scale steel plant equipped with a complete HSR and CSR production line, effectively mitigating flatness defects and thickness deviation in the strip's head section. Thus, the proposed framework is reliable and can be flexibly applied to strip manufacturing processes.