Iterative Convergence for Solving the Exit Plastic Zone and Friction Coefficient Model of Ultra-thin Strip Rolling Force

• Published in: ISIJ International 2024/11/15, Vol.64(13), pp.1899-1908
• Main Authors: Zhang, Jie, Wang, Tao, Wang, Zhenhua, Liu, Xiao
• Format: Article
• Language: English
• Subjects: Fleck theory; frictional coefficient model; GWO-KELM neural network; rolling force prediction model; ultra-thin strip
• ISSN: 0915-1559; 1347-5460
• DOI: 10.2355/isijinternational.ISIJINT-2024-214

For the analytical model of rolling force of ultra-thin strip, the iterative conditions of the exit plastic zone are improved to solve the convergence problem of the Fleck model in small reduction rolling. The nonlinear law of friction coefficient in multi-pass rolling is analyzed, and the friction coefficient database for sample data is established through the friction coefficient calculation model, which is used GWO-KELM neural network training friction coefficient prediction model, the Fleck rolling force prediction model based on the modified friction coefficient is established ultimately. A comparative analysis of prediction errors is conducted on three different specifications of strip steel using actual production data from a multifunctional 280 mm 20-high mill. The results show that the best performing MSE, RMSE, MAE, MAPE and R2, with values of 170.48, 13.06 kN, 9.01 kN, 3.30%, and 0.989, respectively. The accuracy of the modified rolling force prediction model is significantly improved, and the data scale of friction coefficient database can be continuously expanded, so the accuracy of the rolling force prediction model can be continuously improved.