Roll contour design is a core technology for strip shape control; however, its application is hindered by challenges such as poor adaptability across multiple product specifications, difficulty in multi-objective optimisation, and low simulation efficiency. Existing studies typically rely on finite element simulations to optimise roll contours, but these simulations are time-consuming and struggle to cover the full range of specifications. Artificial intelligence and surrogate modelling techniques offer a novel approach to addressing this issue: by constructing machine learning based surrogate models of finite element simulations, computational efficiency can be significantly improved while maintaining accuracy. This article focused on a cold rolling mill, where optimisation weights were determined based on industrial big data. Multi-objective data were obtained through finite element simulations, and a surrogate model of roll system deformation was constructed using the support vector regression algorithm to achieve multi-objective roll contour optimisation. This approach is adaptable to a wide range of strip specifications and effectively mitigates shape defects, providing a feasible pathway for intelligent roll contour design.
WangDCLiuHMLiuJ. Research and development trend of shape control for cold rolling strip. Chin J Mech Eng2017; 30: 1248–1261.
2.
CaoJGChaiXTLiYL, et al.Integrated design of roll contours for strip edge drop and crown control in tandem cold rolling mills. J Mater Process Technol2018; 252: 432–439.
3.
CaoJGQiJBZhangJ, et al.Backup roll contour for edge drop control technology in tandem cold rolling mill. J Cent South Univ2008; 39: 1011–1016.
4.
MontmitonnetPFourmentLRipertU, et al.State of the art in rolling process modelling. BHM Berg-und Hüttenmännische Monatshefte2016; 161: 396–404.
5.
LinghuKZJiangZYLiF, et al.FEM Analysis of profile control capability during rolling in a 6-high CVC cold rolling mill. Adv Mater Res2014; 988: 257–262.
6.
LinghuKJiangZZhaoJ, et al.3D FEM analysis of strip shape during multi-pass rolling in a 6-high CVC cold rolling mill. Int J Adv Manuf Technol2014; 74: 1733–1745.
7.
LiHZhaoZZhangJ, et al.Analysis of flatness control capability based on the effect function and roll contour optimization for 6-h CVC cold rolling mill. Int J Adv Manuf Technol2019; 100: 2387–2399.
8.
RenZXiaoHWangT, et al.Plate profile control during ultra-thin strip rolling utilizing work roll edge contact. J Braz Soc Mech Sci Eng2019; 41: 28.
9.
LiYCaoJQiuL, et al.Research on ASR work roll contour suitable for all width electrical steel strip during hot rolling process. Int J Adv Manuf Technol2018; 97: 3453–3458.
10.
WeiZWangQSunJ, et al.Edge drop control characteristics of the taper-work roll contour for six-high cold mill. Int J Adv Manuf Technol2023; 126: 3615–3635.
11.
LiHBZhangJCaoJG, et al.Analysis and selection of crown control ranges for CVC work rolls in CSP hot rolling. Chin J Mech Eng2010; 32: 118–122.
12.
HeYZhouHLiY, et al.Multi-task learning model of continuous casting slab temperature based on DNNs and SHAP analysis. Mater Trans B2024; 55: 5120–5132.
13.
ZhangFHuangSWangLJ, et al.Online segmented thickness prediction of hot rolling strip based on IBA-XGBoost. Int J Data Sci Anal2025; 19: 141–154.
14.
LiJWangXYangQ, et al.Modeling and validation of bending force for 6-high tandem cold rolling mill based on machine learning models. Int J Adv Manuf Technol2022; 123: 389–405.
15.
YanZWWangBSBuHN, et al.Intelligent assignation strategy of collaborative optimization for flatness control. J Braz Soc Mech Sci Eng2018; 40: 163.
16.
JiYSongLYuanH, et al.Prediction of strip section shape for hot-rolled based on mechanism fusion data model. Appl Soft Comput2023; 146: 110670.
17.
SongCNCaoJGWangLL, et al.The prediction model for transverse thickness difference of electric steel in 6-high cold rolling mills based on GA-PSO-SVR approach. Steel Res Int2022; 93: 2200302.
18.
WuZDWangXCYangQ, et al.Deformation resistance prediction of tandem cold rolling based on grey wolf optimization and support vector regression. J Iron Steel Res Int2023; 30: 1803–1820.
19.
LuJHaoLWangP, et al.Wear prediction model of hot rolling backup roll based on FEM+ ML algorithm. Int J Adv Manuf Technol2024; 131: 5923–5939.
20.
KudelaJMatousekR. Recent advances and applications of surrogate models for finite element method computations. Soft Comput2022; 26: 13709–13733.
21.
SamadianDMuhitIBDawoodN. Application of data-driven surrogate models in structural engineering: a literature review. Arch Comput Method Eng2025; 32: 735–784.
22.
CaiHXiaoWZhengK. The prediction of part thickness using machine learning in aluminum hot stamping process with partition temperature control. Int J Adv Manuf Technol2022; 119: 3891–3902.
23.
SlimaniKZaafMBalanT. Accurate surrogate models for the flat rolling process. Int J Mater Form2023; 16: 23.
24.
SongLXuDWangC, et al.A novel intelligent method for slab front-end bending control in hot rolling. Int J Adv Manuf Technol2023; 126: 4199–4212.
25.
AbioABonadaFPujanteJ, et al.Machine learning-based surrogate model for press hardening process of 22MnB5 sheet steel simulation in industry 4.0. Materials (Basel)2022; 15: 3647.
26.
InapakurthiRKMitraK. Towards faster multi-objective surrogate optimization using SVR: a casting case study. Trans Indian Inst Met2024; 77: 4345–4354.
27.
QazaniMRBidabadiBSAsadiH, et al.Multiobjective optimization of roll-forming procedure using NSGA-II and type-2 fuzzy neural network. IEEE Trans Autom Sci Eng2023; 21: 3842–3851.
28.
ZengGLiSHYuZQ, et al.Optimization design of roll profiles for cold roll forming based on response surface method. Mater Des2009; 30: 1930–1938.
29.
ChenCCShaoJHeAR, et al.Comprehensive shape control technology for CSP hot strip mills. Int J Autom Comput2015; 12: 611–619.
30.
CaoJGWeiGCZhangJ, et al.VCR And ASR technology for profile and flatness control in hot strip mills. J Cent South Univ Technol2008; 15: 264–270.
31.
CaoJGLiuSJZhangJ, et al.ASR Work roll shifting strategy for schedule-free rolling in hot wide strip mills. J Mater Process Technol2011; 211: 1768–1775.
32.
WeiZWangGSunJ, et al.Development of cold-rolling edge-drop control technology for electrical steel. Steel Res Int2023; 94: 2200919.
33.
KongNCaoJWangY, et al.Development of smart contact backup rolls in ultra-wide stainless strip rolling process. Mater Manuf Process2014; 29: 129–133.
34.
SarakumTSukpancharoenS. Non-destructive sweetness classification of Khao Tang Kwa pomelos using machine learning with acoustic and image processing. J Food Compos Anal2025; 142: 107385.
35.
KarthikRMMalghanRLKaraF, et al.Influence of support vector regression (SVR) on cryogenic face milling. Adv Mater Sci Eng2021; 2021: 9984369.
36.
TuntiwongwatTThammawisetSSrinophakunTR, et al.BCLH2Pro: a novel computational tools approach for hydrogen production prediction via machine learning in biomass chemical looping processes. Energy and AI2024; 18: 100414.
37.
SukpancharoenSSakdeePPhetyimN, et al.Multi-task deep learning for simultaneous prediction of steel purity and carbon capture rate using membrane separation technology in integrated steelmaking processes. Array2025; 27: 100485.
