A Digital Twin Model for Automatic Width Control of Hot Rolling Mill

• Published in: IEEE access Vol. 11; p. 1
• Main Authors: Song, Chaoqun, Shen, Xiaohui, Xia, Junchao
• Format: Journal Article
• Language: English
• Published: Piscataway IEEE 01.01.2023; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Automatic control; Boundary conditions; Casting; Continuous casting; Continuous casting slab; Continuous rolling; Data models; Deformation; digital twin; Digital twins; finite element; Finite element analysis; Finite element method; Hot rolling; Hot rolling mills; Mechanical properties; multi-layer perceptron; Multilayer perceptrons; Multilayers; Parameters; Predictive models; Production costs; Regression models; Slab casting; Slabs
• ISSN: 2169-3536; 2169-3536
• DOI: 10.1109/ACCESS.2023.3306782

Considering the head and tail deformation phenomenon in the slab rolling process, this paper studies the online width adjustment control problem of the continuous casting slab based on the digital twin framework. First, the material mechanical properties, geometric model and boundary conditions of the continuous casting slab rolling are given to establish the deformation model of the continuous casting slab rolling process by using the rigid-viscoplastic finite element method. Second, the deformation model of the rolled piece is mainly reflected by shape parameters of the head and tail. The feature design of the head and tail shape is carried out based on the finite element simulation results, and multi-layer perceptron is used to extract features and realize the model regression for obtaining a digital twin model. Then, in view of the parameters of the continuous casting slab, the digital twin model is used to predict the loss-width curve at the head and tail of the slab online, and then the roll gap of the vertical roll mill is corrected synchronously to realize the width adjustment technology of the continuous casting slab and reduce production costs. Finally, taking the slab rolling process of a steel factory as an example, the accuracy and effectiveness of the proposed method are illustrated.