Abstract
The wear of backup rolls will have a great impact on the quality of the shape of hot rolled strip sheet. In order to overcome the limitations of the finite element method (FEM) in calculating backup roll wear in terms of efficiency and accuracy, this paper proposes a tandem FEM + ML hybrid model to optimise the predictive effect of the finite element method (FEM) on backup roll wear. Firstly, a backup roll wear model based on FEM is established. Secondly, in order to select the optimal machine learning (ML) algorithm as the finite element error compensation model, three types of finite element error compensation models were established based on the random forest (RF) algorithm, the radial basis function (RBF) neural network algorithm, and the particle swarm optimisation support vector machine (PSO-SVM) algorithm. Finally, the three types of finite element error compensation models were connected in series with the FEM model to compare the prediction performance of the three types of FEM + ML models on backup roll wear. The numerical experimental results show that the FEM + PSO-SVM model can better predict the wear of the backup roll, and the PSO-SVM algorithm is the most suitable for building the finite element error compensation model. It is proved that the FEM + ML model proposed in this paper can effectively improve the accuracy and computational efficiency of the FEM model for predicting backup roll wear without adding microelements. In addition, among the hot rolling parameters, the rolling force has the greatest influence on the backup roll wear, and excessive rolling force for a single pass should be avoided to slow down the backup roll wear.
Similar content being viewed by others
References
Li Y, Wu Q, Liu C (2019) Effects of chemical composition and heat treatment on wear properties of backup rolls steel. Mater Express 9:764–772. https://doi.org/10.1166/mex.2019.1562
Frolish M, Beynon J (2004) Design criteria for rolling con tact fatigue resistance in back-up rolls. Ironmak Steelmak 31:300–304. https://doi.org/10.1179/030192304225018181
Ivanov Y, Matz W, Rotshtein V, Günzel R, Shevchenko N (2002) Pulsed electron-beam melting of high-speed steel: structural phase transformations and wear resistance. Surf Coat Technol 150:188–198. https://doi.org/10.1016/S0257-8972(01)01542-0
Goto K, Matsuda Y, Sakamoto K, Sugimoto Y (1992) Basic characteristics and microstructure of high-carbon high speed steel rolls for hot rolling mill. ISIJ Int 32:1184–1189. https://doi.org/10.2355/isijinternational.32.1184
Lee J, Oh J, Park J, Lee H, Lee S (2001) Effects of tempering temperature on wear resistance and surface roughness of a highspeed steel roll. ISIJ Int 41:859–865. https://doi.org/10.2355/isijinternational.41.859
Servin-Castañeda R, Garcia-Lara AM, Mercado-Solís RD, Vega-Lebrun CA (2014) Development of mathematical model for control wear in backup roll for hot strip mill. J Iron Steel Res Int 21:46–51. https://doi.org/10.1016/S1006-706X(14)60008-X
Liu X, Shi X, Li S, Xu J, Wang G (2007) FEM analysis of rolling pressure along strip width in cold rolling process. J Iron Steel Res Int 14:22–26. https://doi.org/10.1016/S1006-706X(07)60068-5
Yang G, Cao J, Zhang J, Jia S, Tan R (2008) Backup roll contour of a Smart Crown tandem cold rolling mill. J Univ Sci Tech 15:357–361. https://doi.org/10.1016/S1005-8850(08)60067-5
Sun J, Deng J, Peng W, Zhang D (2021) Effects strip crown prediction in hot rolling process using random forest. Int J Precis Eng Man 22:301–311. https://doi.org/10.1007/s12541-020-00454-1
Cui C, Wang H, Gao X, Cao G (2021) Machine learning model for thickness evolution of oxide scale during hot strip rolling of steels. Metall Mater Trans A 52:4112–4124. https://doi.org/10.1007/s11661-021-06368-5
Xing S, Ju J, Xing J (2019) Learning research on hot-rolling steel products quality control based on BP neural network inverse model. Neural Comput Appl 31:1577–1584. https://doi.org/10.1007/s00521-018-3547-5
Ji Y, Song L, Sun J, Peng W, Li H, Ma L (2021) Application of SVM and PCA-CS algorithms for prediction of strip crown in hot strip rolling. J Cent South Univ 28:2333–2344. https://doi.org/10.1007/s11771-021-4773-z
Li G, Gong D, Lu X, Zhang D (2021) Ensemble learning based methods for crown prediction of hot-rolled strip. ISIJ Int 61:1603–1613. https://doi.org/10.2355/isijinternational.ISIJINT-2020-639
Song L, Xu D, Wang X, Yang A, Ji Y (2022) Application of SVM and PCA-CS algorithms for prediction of strip crown in hot strip rolling. Int J Adv Manuf Technol 120:881–890. https://doi.org/10.1007/s00170-022-08825-w
Zhang Y, Lin R, Zhang H, Peng Y (2023) Vibration prediction and analysis of strip rolling mill based on XG boost and Bayesian optimization. Complex Intell Syst 9:133–145. https://doi.org/10.1007/s40747-022-00795-6
Ma X, Ma B, Li J, Chen P, Peng Y, Ren Z (2023) Effect of strip profile of hot-rolled silicon steel on transverse thickness difference of cold-rolled strip. Ironmak Steelmak 50:921–935. https://doi.org/10.1080/03019233.2023.2166264
Estela R, Diego F, Miguel C, Ana L, Valentín A, Federico G (2020) Machine learning algorithms for the prediction of the strength of steel rods: an example of data-driven manufacturing in steelmaking. Int J Comput Integr Manuf 33:880–894. https://doi.org/10.1080/0951192X.2020.1803505
Wang Y, Cao J, Song C, Wang L, Sun L, Xie D, Lu Y (2022) Research on high-precision transverse thickness difference control strategy based on data mining in 6-high tandem cold rolling mills. Steel Res Int 93:2100514. https://doi.org/10.1002/srin.202100514
Salah B, Laib L, Sissaoui H, Jürgen B (2010) Evaluation using online support-vector-machines and fuzzy reasoning. Application to condition monitoring of speeds rolling process. Control Eng Pract 18:1060–1068. https://doi.org/10.1016/j.conengprac.2010.05.010
Xu K, Ai Y, Wu X (2013) Application of multi-scale feature extraction to surface defect classification of hot-rolled steels. Int J Miner Metall Mater 20:37–41. https://doi.org/10.1007/s12613-013-0690-y
Ji Y, Song L, Yuan H, Li H, Peng W, Sun J (2023) Prediction of strip section shape for hot-rolled based on mechanism fusion data model. Appl Soft Comput 146:110670. https://doi.org/10.1016/j.asoc.2023.110670
He X, Zhou X, Tian T, Li W (2011) Prediction of mechanical properties of hot rolled strips with generalized RBFNN and composite expectile regression. IEEE Access 10:106534–106542. https://doi.org/10.1109/ACCESS.2022.3212053
Zhang X, Cheng L, Hao S, Gao W, Lai Y (2017) Optimization design of RBF-ARX model and application research on flatness control system. Optim Control Appl Methods 38:19–35. https://doi.org/10.1002/oca.2240
Trzepiecinski T, Szwajka K, Szewczyk M, Gao W, Lai Y (2023) An investigation into the friction of cold-rolled low-carbon DC06 steel sheets in sheet metal forming using radial basis function neural networks. Appl Sci-Basel 13:9572. https://doi.org/10.3390/app13179572
Deng L, Wang C, Luo J, Tu J, Guo N, Xu H, He P, Xia S, Yao Z (2022) Preparation and property optimization of FeCrAl-based ODS alloy by machine learning combined with wedge-shaped hot-rolling. Mater Charact 188:111894. https://doi.org/10.1016/j.matchar.2022.111894
John S, Sikdar S, Mukhopadhyay A, Pandit A (2006) Roll wear prediction model for finishing stands of hot strip mill. Ironmak Steelmak 33:169–175. https://doi.org/10.1179/174328106X80091
Hu W, Zheng Z, Gao X, Panos M (2019) An improved method for the hot strip mill production scheduling proble. Int J Prod Res 57:3238–3254. https://doi.org/10.1080/00207543.2019.1579932
Jiang Z, Tieu A (2007) A Contact mechanics and work roll wear in cold rolling of thin strip. Wear 263:1447–1453. https://doi.org/10.1016/j.wear.2006.12.068
Wang X, Li F, Li B, Dong L, Zhang B (2012) Design and application of an optimum backup roll contour configured with CVC work roll in hot strip mill. ISIJ Int 9:1637–1643. https://doi.org/10.2355/isijinternational.52.1637
Dong Q, Wang Z, He Y, Shang F, Li Z (2022) The effect of shifting modes on work roll wear in strip steel hot rolling process. Ironmak Steelmak 50:67–74. https://doi.org/10.1080/03019233.2022.2083929
Kirchdoerfer T, Ortiz M (2016) Data-driven computational mechanics. Comput Methods Appl Mech Eng 304:81–101. https://doi.org/10.1016/j.cma.2016.02.001
Jin Y, Wang H, Miettinen K (2019) Data-driven evolutionary optimization: an overview and case studies. IEEE Trans Evol 23:442–458. https://doi.org/10.1109/TEVC.2018.2869001
Chen Y, Tang X, Qi X, Li C, Xiao R (2022) Learning graph normalization for graph neural networks. Neurocomputing 493:613–562. https://doi.org/10.1016/j.neucom.2022.01.003
Kumar S, Gupta S, Arora S (2022) A comparative simulation of normalization methods for machine learning-based intrusion detection systems using KDD Cup’ 99 dataset. J Intell Fuzzy Syst 42:1749–1766. https://doi.org/10.3233/JIFS-211191
Zhao Y, Song Y, Li F, Yan X (2022) Prediction of mechanical properties of cold rolled strip based on improved extreme random tree. J Iron Steel Res Int 30:293–304. https://doi.org/10.1007/s42243-022-00815-2
Li W, Xie L, Wang W (2020) Prediction model for mechanical properties of hot-rolled strips by deep learning. J Iron Steel Res Int 27:1045–1053. https://doi.org/10.1007/s42243-020-00450-9
Huang Y, Zhou X, Gao Z (2022) Thickness prediction of thin strip cold rolling based on VBGM-RBF. Int J Adv Manuf Technol 120:5865–5884. https://doi.org/10.1007/s00170-022-09122-2
Victor S, Elisabeth L (2016) Radial basis function partition of unity methods for pricing vanilla basket options. Comput Math with Appl 71:185–200. https://doi.org/10.1016/j.camwa.2015.11.007
Hu Y, Sun J, Wen P, Zhang D (2020) A novel forecast model based on CF-PSO-SVM approach for predicting the roll gap in acceleration and deceleration process. Eng Comput (Swansea) 38:1117–1133. https://doi.org/10.1108/EC-08-2019-0370
Gong Y, Li J, Zhou Y, Yi L, Chung H, Shi Y, Zhang J (2016) Genetic learning particle swarm optimization. IEEE Trans Cybern 46:2277–2290. https://doi.org/10.1109/TCYB.2015.2475174
Wang S, Tan D, Liu L (2018) Particle swarm optimization algorithm: an overview. Soft Comput 22:387–408. https://doi.org/10.1007/s00500-016-2474-6
Wang Z, Zhang D, Gong D, Wen P (2019) A new data-driven roll force and roll torque model based on fem and hybrid PSO-ELM for hot strip rolling. Isij int 9:1604–1613. https://doi.org/10.2355/isijinternational.ISIJINT-2018-846
Cui C, Gao G, Li X, Gao Z, Zhou X, Liu Z (2022) The coupling machine learning for microstructural evolution and rolling force during hot strip rolling of steels. J Mater Process Technol 309:117736. https://doi.org/10.1016/j.jmatprotec.2022.117736
Wang T, Yeh P (2020) Reliable accuracy estimates from k-fold cross validation. IEEE Trans Knowl Data Eng 32:1586–1594. https://doi.org/10.1109/TKDE.2019.2912815
Fushiki T (2011) Estimation of prediction error by using K-fold cross-validation. Stat Comput 21:137–146. https://doi.org/10.1007/s11222-009-9153-8
Yoonsuh J (2018) Multiple predicting K-fold cross-validation for model selection. J Nonparametr Stat 30:197–215. https://doi.org/10.1080/10485252.2017.1404598
Li C, Yu H, Deng G, Liu X, Wang G (2007) Numerical simulation of temperature field and thermal stress field of work roll during hot strip rolling. J Iron Steel Res Int 14:18–21. https://doi.org/10.1016/S1006-706X(07)60067-3
Funding
This work is supported by the National Natural Science Foundation of China (Grant Nos. 52074242 and U20A20187), the Central Guiding Local Science and Technology Development Special Fund Project (Grant No. 216Z1602G), the Natural Science Foundation of Hebei Province (Grant No. E2020203068), the fund of the State Key Laboratory of Rolling and Automation (Grant No. 2022RALKFKT001), and the Liao Ning Revitalization Talents Program of Liao Ning Province (No. XLYC2007087). L.S. is very grateful for the financial support from the Australian Research Council (ARC) through Discovery Early Career Researcher Award (DECRA) fellowship (Grant No. DE180100124). G.D. would like to acknowledge the support from the University of Queensland (UQ) through the UQ Research Stimulus Allocation Fellowship.
Author information
Authors and Affiliations
Contributions
All authors contributed to the study conception and design. Jia Lu has established the optimisation method, designed the experiments, and written the program and the manuscript; Luhan Hao and Pengfei Wang have conducted the experiments and analysed and arranged data; Huagui Huang has organised the project and reviewed the manuscript; Xu Li and Changchun Hua have conducted the experiments and collected and analysed data; Guanyu Deng and Lihong Su have reviewed the manuscript. All authors read and approved the final manuscript.
Corresponding authors
Ethics declarations
Competing interests
The authors declare no competing interests.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Lu, J., Hao, L., Wang, P. et al. Wear prediction model of hot rolling backup roll based on FEM + ML algorithm. Int J Adv Manuf Technol 131, 5923–5939 (2024). https://doi.org/10.1007/s00170-024-13311-6
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00170-024-13311-6