Aiming at the problem that previous product quality prediction models cannot directly assess product quality before hot rolling, this paper presents a joint model for process parameters generation and quality prediction based on Conditional Generative Adversarial Nets and Artificial Neural Network. After generated actual process parameters by the generation module, this model would predict the quality of products ahead of schedule according to the generated parameters before hot rolling, which do not rely on inputting actual process parameter online anymore. Finally, the model has been trained and tested with the actual data from a certain hot rolling plant. The experimental results show that the generated process parameters agree well with actual production and quality prediction accuracy can meet the production requirements, which confirms the proposed model can be applied to simulate the actual rolling process and predict strip quality ahead of hot rolling production, providing a reference for the adjustment of planning and scheduling in the future.
Get full access to this article
View all access options for this article.
References
1.
DemaRRAmirovRNLatypovOR.Mathematical model for assessing the management of quality parameters of hot-rolled strips according to the criterion of local thickness variation. Mater Today Proc. 2019;19:2417–2421. DOI:10.1016/j.matpr.2019.08.047.
2.
SongLXuDWangXet al.Application of machine learning to predict and diagnose for hot-rolled strip crown. Int J Adv Manuf Technol. 2022;120(1):881–890. DOI:10.1007/s00170-022-08825-w.
3.
GinzburgVB.High-quality steel rolling: theory and practice. New York: CRC Press; 1993.
4.
ÖzgürAUygunYHüttMT.A review of planning and scheduling methods for hot rolling mills in steel production. Comput Ind Eng. 2021;151:106606. DOI:10.1016/j.cie.2020.106606.
5.
PimenovVADagmanAIKovalevDA.Analysis and mathematical simulation of formation regularities of strip transversal profile during hot rolling. Steel Trans. 2020;50(2):107–111. DOI:10.3103/S0967091220020060.
6.
MückeGPützPDGorgelsF.Chapter 27. Methods of describing, assessing, and influencing shape deviations in strips. In: Flat-rolled steel processes. advanced technologies. New York (NY): CRC Press; 2009. p. 287–298. DOI:10.1201/9781420072938.
7.
CaoJLiuSZhangJet al.ASR work roll shifting strategy for schedule-free rolling in hot wide strip mills. J Mater Process Technol. 2011;211(11):1768–1775.
8.
LiuMFangSDongHet al.Review of digital twin about concepts, technologies, and industrial applications. J Manuf Syst. 2021;58:346–361. DOI:10.1016/j.jmsy.2020.06.017.
9.
HwangRJoHKimKSet al.Hybrid model of mathematical and neural network formulations for rolling force and temperature prediction in hot rolling processes. IEEE Access. 2020;8:153123–153133. DOI:10.1109/ACCESS.2020.3016725.
10.
ChenSLiWLiuX.Calculation of rolling pressure distribution and force based on improved karman equation for hot strip mill. Int J Mech Sci. 2014;89:256–263. DOI:10.1016/j.ijmecsci.2014.09.011.
11.
GlowackiM.The mathematical modelling of thermo-mechanical processing of steel during multi-pass shape rolling. J Mater Process Technol. 2005;168(2):336–343. DOI:10.1016/j.jmatprotec.2004.12.007.
12.
OreshinaMPimenovVDabasM. Software for modeling the temperature distribution of strip and work rolls during hot rolling[C]. 2019 1st International Conference on Control Systems, Mathematical Modelling, Automation and Energy Efficiency (SUMMA), IEEE, 2019. p. 269–274. DOI:10.1109/SUMMA48161.2019.8947620.
13.
WisselinkHHHuétinkJ.3D FEM simulation of stationary metal forming processes with applications to slitting and rolling. J Mater Process Technol. 2004;148(3):328–341. DOI:10.1016/j.jmatprotec.2004.02.036.
14.
Fang-chenYDian-huaZYu-chengZ.Dynamic modeling and rolling data analysis of the tandem hot rolling process. Simulation. 2017;93(4):307–321. DOI:10.1177/0037549716666688.
15.
ZhangCLiuZZhangCet al.A self-learning method for improving the hot-rolled plate shape. IOP Conf Series Mater Sci Eng. 2018;452(2): 022024. DOI:10.1088/1757-899X/452/2/022024.
16.
LiXLuanFWuY.A comparative assessment of six machine learning models for prediction of bending force in hot strip rolling process. Metals. 2020;10(5):685. DOI:10.3390/met10050685.
17.
WangZHGongDYLiXet al.Prediction of bending force in the hot strip rolling process using artificial neural network and genetic algorithm (ANN-GA). Int J Adv Manuf Technol. 2017;93(9):3325–3338. DOI:10.1007/s00170-017-0711-5.
18.
WuYLiXLuanFet al.A novel GPR-based prediction model for strip crown in hot rolling by using the improved local outlier factor. IEEE Access. 2020;9:458–469. DOI:10.1109/ACCESS.2020.3046685.
19.
DengJSunJPengWet al.Application of neural networks for predicting hot-rolled strip crown. Appl Soft Comput. 2019;78:119–131. DOI:10.1016/j.asoc.2019.02.030.
20.
SunJDengJPengWet al.Strip crown prediction in hot rolling process using random forest. Int J Prec Eng Manuf. 2021;22(2):301–311. DOI:10.1007/s12541-020-00454-1.
DouzasGBacaoF.Effective data generation for imbalanced learning using conditional generative adversarial networks. Expert Syst Appl. 2018;91:464–471. DOI:10.1016/j.eswa.2017.09.030.
23.
Vega-MárquezBRubio-EscuderoCRiquelmeJCet al. Creation of synthetic data with conditional generative adversarial networks. International Workshop on Soft Computing Models in Industrial and Environmental Applications. Cham: Springer; 2019. p. 231–240. DOI:10.1007/978-3-030-20055-8_22.
