Volume 3 · Issue 7 (2026)
DOI number:
10.66521/2938-9933-2026071902
Optimization of Rolling Process Parameters in Metallurgical Engineering and Analysis of Engineering Applications
Mengyao Zhang*, Wanning He
School of Materials and Metallurgy, University of Science and Technology Liaoning, Anshan 114051, Liaoning, China
Corresponding Author: Mengyao Zhang (1686973734@qq.com)
Abstract: Rolling is a key metallurgical operation that connects billet preparation with steel-product forming. Rolling temperature, rolling force, rolling speed, reduction ratio and cooling schedule jointly govern microstructural evolution, mechanical properties, dimensional accuracy and energy consumption. To address the limitation that empirical parameter settings can no longer meet the requirements of high-precision, low-energy production, this study focuses on hot- and cold-rolling processes, systematically examines how the core parameters affect product quality and production efficiency, and develops a multi-objective parameter-optimization strategy that integrates response surface methodology, a genetic algorithm and a data-mechanism hybrid model. A representative operating case is analyzed for Q235B strip produced on a 1780 mm hot continuous rolling line in a steel enterprise. In the proposed scheme, furnace exit temperature, roughing reduction ratio, finishing reduction ratio and finishing speed are incorporated into a unified solution framework. Plant statistics show that, while yield strength and thickness deviation satisfy the process requirements, the standard deviation of yield strength decreases from 18.0 MPa to 15.8 MPa, unit rolling energy consumption decreases from 72 kWh/t to 66 kWh/t, and the qualified-product rate increases from 94.5% to 98.2%. The results indicate that coupled multi-parameter optimization can simultaneously improve quality stability, balance equipment load and enhance production economy, thereby providing a practical reference for refined control of hot continuous rolling.
Keywords: Metallurgical engineering; Rolling process; Parameter optimization; Response surface methodology; Genetic algorithm; Data-mechanism fusion
References
[1]
Fang Wei, Huang Jiaxin, Peng Tiexu, Long Yang, Yin Fuxing. Machine learning-based performance predictions for steels considering manufacturing process parameters: a review [J]. Journal of Iron and Steel Research International, 2024, 31(7): 1555-1581. DOI: 10.1007/s42243-024-01179-5.
[2]
Shang Fei, Chen Huilin, Wang Sifang, Zhao Jipeng, Ma Yonghao, Ba Yuwu. Machine learning-based process parameter optimisation and strip plate shape improvement in steel production [J]. Ironmaking & Steelmaking, 2025, 52(8): 975-1010. DOI: 10.1177/03019233251359803.
[3]
Cao Lei, Li Xu, Li Xiaohua, Dong Zishuo, Zhang Dianhua. Variable speed rolling force prediction with theoretical and data-driven models [J]. International Journal of Mechanical Sciences, 2024, 264: 108833. DOI: 10.1016/j.ijmecsci.2023.108833.
[4]
Wan Liangwei, Zhang Shunhu, Yin Ziqi, Tian Wenhao, Li Weigang. Adaptive modeling of rolling force for hot rolled plate based on industrial data [J]. Journal of Manufacturing Processes, 2024, 129: 253-260. DOI: 10.1016/j.jmapro.2024.08.053.
[5]
Wang Xiaoyong, Gao Zhiying, Xin Yanli. Prediction and optimization of dynamic rolling force in strip rolling process driven by data-mechanism cooperation [J]. Journal of Mechanical Science and Technology, 2024, 38(11): 5937-5948. DOI: 10.1007/s12206-024-1014-z.
[6]
Han Guomin, Li Hongbo, Wang Gang, Liu Yujin, Zhang Jie, Hu Zhiyuan, You Xuechang, Xie Yu. Prediction and control of profile for silicon steel strip in the whole tandem cold rolling based on PSO-BP algorithm [J]. Journal of Manufacturing Processes, 2024, 120: 250-259. DOI: 10.1016/j.jmapro.2024.04.050.
[7]
Xu Dewei, Ding Chengyan, Liu Yu, Sun Jie, Peng Wen, Zhang Dianhua. Industrial big data-driven modeling and prediction for hot-rolled strip crown with multigrade and multispecification data [J]. Steel Research International, 2024, 95(7): 2300736. DOI: 10.1002/srin.202300736.
[8]
Meng Lingming, Ding Jingguo, Li Xiaojian, Cao Guoyu, Li Ye, Zhang Dianhua. Novel shape control system of hot-rolled strip based on machine learning fused mechanism model [J]. Expert Systems with Applications, 2024, 255: 124789. DOI: 10.1016/j.eswa.2024.124789.
[9]
Xue Rundong, Fei Aigeng. Multi-objective optimization of low-alloy hot-rolled strip cooling process based on gray correlation analysis [J]. Metals, 2024, 14(2): 246. DOI: 10.3390/met14020246.
[10]
Ding Jingguo, Du Haozhan, Meng Lingming, Zhao Jian, Wang Guiqiao, Zhang Dianhua. Deep stochastic configuration networks with different distributions for crown prediction of hot-rolled non-oriented silicon steel [J]. Journal of Manufacturing Processes, 2024, 123: 83-95. DOI: 10.1016/j.jmapro.2024.05.060.
[11]
Yilmaz Fatih, Guvenc Mehmet Ali, Mistikoglu Selcuk. Optimization of rolling forces in multi-pass hot rolling using MLR and ABC algorithm for enhanced product quality and energy efficiency [J]. The International Journal of Advanced Manufacturing Technology, 2025, 139: 2409-2429. DOI: 10.1007/s00170-025-16008-6.
[12]
Wang Zhixuan, Zhang Ji, Wang Zhuo, Wang Hao, Bai Zhenhua. Research on optimization strategy for steel strip temper rolling elongation based on model predictive control [J]. Engineering Applications of Artificial Intelligence, 2025, 159: 111785. DOI: 10.1016/j.engappai.2025.111785.
Download PDF