Prediction of rolling force and spread in hot rolling process by artificial neural network and multiple linear regression

Abstract

The aim of this study is to compare the performance of multiple linear regression (MLR) and artificial neural network (ANN) models in predicting rolling force and spread during free rolling in the hot rolling process. Accurate prediction of rolling force and spread in hot rolling is critical for ensuring homogeneous load distribution across rolling stands, enhancing energy efficiency, reducing failure stops, and achieving dimensional accuracy and high-quality final products. The data used in this study were generated through FEM analysis, with a portion of the results verified experimentally. The dataset includes variables such as material temperature, rolled material dimensions, reduction amount, and rolling speed, all of which influence rolling force and spread. A maximum acceptable error rate of 2.9% for spread and 6.7% for rolling force was determined. Both MLR and ANN models were applied to the dataset, and their prediction performances were compared using the mean square error (MSE). For rolling force estimation, the ANN model achieved a training R value of 0.9888 and a test R value of 0.9844, while the MLR model obtained an R2 value of 0.9651 and an adjusted R2 value of 0.9829. In spread estimation, the ANN model achieved a training R value of 0.9947 and a test R value of 0.9844, compared to the MLR model's R2 value of 0.9871 and adjusted R2 value of 0.9863. The results indicate that both models perform comparably well in estimating rolling force and spread. However, the artificial neural network model demonstrates a slight advantage, offering marginally superior prediction performance.

Keywords

• Artificial neural networks (ANN)
• Hot rolling
• Multiple linear regression (MLR)
• Prediction performance
• Rolling force
• Spreading amount

References

1. 1. Kun He and Li Wang, A review of energy use and energy-efficient technologies for the iron and steel industry, Renewable and Sustainable Energy Reviews, 2016, 70: p. 1022-1038.
2. 2. Viktoriya Chubenko, Аlla Khinotskaya, Tatiana Yarosh, and Levan Saithareiev, Sustainable development of the steel plate hot rolling technologydue to energy-power process parameters justification, ICSF 2020, 166(06009).
3. 3. Huipping Hong, Roll Pass Design and Simulation on Continuous Rolling of Alloy Steel Round Bar, 9th International Conference on Physical and Numerical Simulation of Materials Processing, 2019, 37: p. 127-131.
4. 4. D.H. Kim, Y. Lee, B.M. Kim, Application of ANN for the dimensional accuracy of workpiece in hot rod rolling process, Journal of Materials Processing Technology, 2002, 130-131: p. 214-218.
5. 5. Jingyi Liu, Xinxin Liu and Ba Tuan Le, Rolling force prediction of hot rolling based on GA-MELM, Hindawi Complexity 2019, Volume 2019(3476521).
6. 6. L. G. M. Sparling, B.Eng., Formhla For ‘Spread’ In Hot Flat Rollıng, Applıed Mechanıcs Group, 1961, 175(1): p.604-640.
7. 7. J. Bartnıckı, Fem Analysıs Of Hollow Hub Formıng In Rollıng Extrusıon Process, Metabk, 2014, 53(4): p. 641-644.
8. 8. Ana Claudia González-Castillo, José de Jesús Cruz-Rivera, Mitsuo Osvaldo Ramos-Azpeitia, Pedro Garnica-González, Carlos Gamaliel Garay-Reyes, José Sergio Pacheco-Cedeño ve José Luis Hernández-Rivera, 3D-FEMSimulation of Hot Rolling Process and Characterization of the Resultant Microstructure of a Light-Weight Mn Steel, Crystals, 2021, 11(5):569.

9. 9. Shafaa Al-Maqdi, Jaber Abu Qudeiri and Aiman Ziout, Optimization of flat rolling process through a simulation approach using simufact forming, Proceedings of the International Conference on Industrial Engineering and Operations Management, 2020. Dubai: p. 2031-2044.
10. 10. X. Wanga, K. Chandrashekhara, M.F. Buchely, S. Lekakh, D.C. Van Aken, R.J. O’Malley, G.W. Ridenour, E. Scheid, Experiment and simulation of static softening behavior of alloyed steel during round bar hot rolling, Journal of Manufacturing Processes, 2020, 52:p 281-288.
11. 11. Mehmet Akkaş, Burak Onder, Ezgi Sevgi, Osman Çulha, Computer Aided Design, Analysis and Manufacturing of Hot Rolled Bulb Flat Steel Profiles, ECJSE , 2020, 7(1): p. 9-19.
12. 12. Zhenhua Wang, Dianhua Zhang, Dianyao Gong And Wen Peng, A new data-driven roll force and roll torque model based onfem and hybrid pso-elm for hot strip rolling, ISIJ International, 2019, 59(9): p. 1604–1613.
13. 13. U. Hanoglu, B. Šarler, Multi-pass hot-rolling simulation using a meshless method, Computers and Structures, 2017, 194: p. 1-14.
14. 14. Emre Alan, İ. İrfan Ayhan, Bilgehan Ögel and Deniz Uzunsoy, A comparative assessment of artificial neural network and regression models to predict mechanical properties of continuously cooled low carbon steels: an external data analysis approach, Journal of Innovative Engineering and Natural Science, 2024, 4(2): p. 495-513.
15. 15. D. M. Jones, J. Watton and K. J. Brown, Comparison of hot rolled steel mechanical property prediction models using linear multiple regression, non-linear multiple regression and non-linear artificial neural networks, Ironmaking and Steelmaking, 2005, 32(5): p. 435-442.
16. 16. Mahdi Bagheripoor, Hosein Bisadi, Application of artificial neural networks for the prediction of roll force and roll torque in hot strip rolling process, Applied Mathematical Modelling, 2013, 37(7): p. 4593-4607.
17. 17. Muhammad Asif Zahoor Raja, Muhammad Anwaar Manzar, Raza Samar, An efficient computational intelligence approach for solving fractional order Riccati equations using ANN and SQP, Applied Mathematical Modelling, 2015, 39(10-11): p. 3075-3093.
18. 18. Ruihua Jiao, Kaixiang Peng, Member, IEEE, and Jie Dong, Remaining useful life prediction for a roller in a hot strip mill based on deep recurrent neural networks, IEEE/CAA Journal Of Automatica Sinica, 2021, 8(7): p. 1345-1354.
19. 19. Rakhoon Hwang, Hyeontae Jo, Kyung Seok Kim, and Hyung Ju Hwang, Hybrid model of mathematical and neural network formulations for rolling force and temperature prediction in hot rolling processes, IEEE Access, 2017, 8: p. 153123 - 153133.
20. 20. Zhen-Hua Wang, Dian-Yao Gong, Xu Li & Guang-Tao Li, Dian-Hua Zhang, 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: p. 3325-3338.
21. 21. Jifei Deng, Jie Sun, Wen Peng, Yaohui Hu, Dianhua Zhang, Application of neural networks for predicting hot-rolled strip crown, Applied Soft Computing Journal, 2019, 78: p. 119-131.
22. 22. F. Capece Minutolo, M. Durante, L. Giorleo, and A. Langella, Specific pressure in steel rod rolling with grooves, JMEPEG, 2005, 14: p. 378-382.
23. 23. Yusuf Karabacak, Doğan Şimşek and Nuri Atik, Combined application of ANN prediction and RSM optimization of performance and emission parameters of A Diesel Engine Using Diesel-Biodiesel-Propanol Fuel Blends, International Advanced Researches And Engineering Journal, 2023, 7(3): p. 165-177.
24. 24. Burcu Ozcan, Pınar Yıldız Kumru and Alpaslan Fığlalı, Forecasting operation times by using Artificial Intelligence, International Advanced Researches And Engineering Journal, 2018, 2(2): p. 109-116.
25. 25. Francesco Lambiase, Prediction of geometrical profile in slit rolling pass, Int J Adv Manuf Technol, 2014, 71: p. 1285-1293.
26. 26. Xingdong Li, Rolling force prediction of hot strip based on combined friction, Materials Science and Engineering, 2017. 4th AMMSE 2017 269(012053).
27. 27. Matruprasad Rout, Surjya K. Pal, Shiv B. Singh, Finite element modeling of hot rolling: Steady- and unsteady-state analyses, Computational Methods and Production Engineering, 2017, p. 83-124.
28. 28. Zhenhua Wang, Gengsheng Ma, Dianyao Gong, Jie Sun, Dianhua Zhang, Application of mind evolutionary algorithm and artificial neural networks for prediction of profile and flatness in hot strip rolling process, Neural Processing Letters, 2019, 50: p. 2455-2479.
29. 29. Y. Mahmoodkhani, M. A. Wells, G. Song, Prediction of roll force in skin pass rolling using numerical and artificial neural network methods, Ironmaking & Steelmaking, 2016, 44(4): p.281-286.