Abstract
In the cold rolling process, inaccurate rolling force settings and the resulting strip thickness fluctuations and other quality problems occur, reducing the yield and product quality. To improve the accuracy of rolling force prediction, this paper proposes three methods to combine a T-S fuzzy neural network and rolling force analytical model based on their advantages and characteristics, to construct a combined rolling force prediction model, and to fully utilize the features and benefits of each model for rolling force prediction. The model’s performance is evaluated by selecting the mean absolute error (MAE), mean absolute percentage error (MAPE), and root mean squared error (RMSE). The model experiments with historical production data obtained from industrial sites. The experimental results show that the combined prediction models have a more robust rolling force prediction capability than the T-S fuzzy neural network model alone, especially the combined form of using the calculated value of the rolling force analytical model as the input to the T-S fuzzy neural network without destroying the self-learning of the rolling force analytical model, which has better calculation accuracy and reliability for rolling force than other models. The model can provide an essential reference for the online prediction of cold rolling force and high precision rolling production and has high usability.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
Availability of data and materials
The authors confirm that the data and material supporting the findings of this work are available within the article.
Code availability
Not applicable.
References
Sun J, Peng W, Ding JG, Li X, Zhang DH (2018) Key intelligent technology of steel strip production through process. Metals 8(8):597. https://doi.org/10.3390/met8080597
Zhou FQ, Cao JG, Zhang J, Yin XQ, Jia SH, Zeng W (2006) Prediction model of rolling force for tandem cold rolling mill based on neural networks and mathematical models. Journal of Central South University 37(6):1155–1160. https://doi.org/10.1016/S1872-1508(06)60066-1
Liu HQ, Tang D, Yang Q, Guo LW (2006) Rolling force prediction model of a multi-roll cold tandem mill by fuzzy cerebellum model articulation controller. J Univ Sci Technol Bei**g 28(10):969–972. https://doi.org/10.3321/j.issn:1001-053X.2006.10.014
Zhang DZ, Cheng BX, Li MW, Sun YK, Guan KZ (2000) Rolling force models of cold tandem rolling mill based on genetic neural networks. J Univ Sci Technol Bei**g 22(4):384–388. https://doi.org/10.13374/j.issn1001-053x.2000.04.058
Guo LW, Yang Q, Guo L (2007) Comprehensive parameters self-adapting for a rolling force model of tandem cold rolling process control. J Univ Sci Technol Bei**g 29(4):413–416. https://doi.org/10.3321/j.issn:1001-053X.2007.04.015
Lin JC (2002) Prediction of rolling force and deformation in three-dimensional cold rolling by using the finite-element method and a neural network. Int J Adv Manuf Technol 20(11):799–806. https://doi.org/10.1007/s001700200219
Blake JJ, Maguire LP, Roche B, Mcginnity TM, Mcdaid LJ (1998) The implementation of fuzzy systems, neural networks and fuzzy neural networks using FPGAs. Inform Sciences 112(1–4):151–168. https://doi.org/10.1016/S0020-0255(98)10029-4
Han M, Sun YN, Fan YN (2008) An improved fuzzy neural network based on T-S model. Expert Syst Appl 34(4):2905–2920. https://doi.org/10.1016/j.eswa.2007.05.020
Neelakanta APS, Abusalah CST, De Groff ADF, Park BJC (1998) Fuzzy nonlinear activity and dynamics of fuzzy uncertainty in the neural complex. Neurocomputing 20(1–3):123–153. https://doi.org/10.1016/S0925-2312(98)00006-X
Sun JQ, Xu HB (1997) Fuzzy neural network based on T-S model. J Tsinghua Univ 37(3):5
Tsang ECC, Lee JWT, Yeung DS (2002) Tuning certainty factor and local weight of fuzzy production rules by using fuzzy neural network. IEEE Trans Cybern 32(1):91–98. https://doi.org/10.1109/3477.979963
Chen SZ, Peng W, Ji YF, Zhang DH (2013) Parameters adaptation of the rolling force model based on the objective function in tandem cold rolling. J Northeast Univ 34(8):1128–1131
Jiang ZY, Tieu AK (2002) Elastic–plastic finite element method simulation of thin strip with tension in cold rolling. J Mater Process Tech 130–131:511–515. https://doi.org/10.1016/S0924-0136(02)01020-8
Lv C, Jiao ZJ, Liu XH, Wang GD (2000) Hill explicit expression of rolling force taking into consideration elastic deformation of rolled stock. Res Iron Steel (03):32–33+46
Hwang R, Jo H, Kim KS, Hwang HJ (2020) Hybrid model of mathematical and neural network formulations for rolling force and temperature prediction in hot rolling processes. IEEE Access 99:1–1. https://doi.org/10.1109/ACCESS.2020.3016725
Jiang ZY, Zhu HT, Tieu AK (2003) Effect of rolling parameters on cold rolling of thin strip during work roll edge contact. J Mater Process Tech 140(1–3):535–541. https://doi.org/10.1016/S0924-0136(03)00783-0
Jia CY, Shan XY, Niu ZP (2008) High precision prediction of rolling force based on fuzzy and nerve method for cold tandem mill. J Iron Steel Res Int 15(2):5. https://doi.org/10.1016/S1006-706X(08)60025-4
Wang ZH, Zhang DH, Gong DY, Peng W (2019) A new data-driven roll force and roll torque model based on FEM and hybrid PSO-ELM for hot strip rolling. ISIJ Int 59(9):1604–1613. https://doi.org/10.2355/isi**ternational.isi**t-2018-846
**e HB, Jiang ZY, Tieu AK, Liu XH, Wang GD (2008) Prediction of rolling force using an adaptive neural network model during cold rolling of thin strip. Int J Mod Phys B 22(31&32):5723–5727. https://doi.org/10.1142/9789814261579_0056
He F, Zhang LY (2018) Mold breakout prediction in slab continuous casting based on combined method of GA-BP neural network and logic rules. Int J Adv Manuf Tech 95(9–12):4081–4089. https://doi.org/10.1007/s00170-017-1517-1
Liu CY, Ding WF, Li Z, Yang CY (2016) Prediction of high-speed grinding temperature of titanium matrix composites using BP neural network based on PSO algorithm. Int J Adv Manuf Tech 89:2277–2285. https://doi.org/10.1007/s00170-016-9267-z
Funding
The work would like to thank the National Natural Science Foundation of China (Grant No. 51975043) and the China Postdoctoral Science Foundation (Grant No. 2021M690352) for their financial support.
Author information
Authors and Affiliations
Contributions
**gdong Li analyzed the simulation data, completed the draft; **aochen Wang instructed the revision of the draft; Quan Yang provided constructive suggestions on modeling; Ziao Guo helped to verify the precision of the first combined form of rolling force prediction model; Lebao Song helped to verify the precision of the second combined form of rolling force prediction model; **ng Mao helped to verify the precision of the rest form of the rolling force prediction model.
Corresponding author
Ethics declarations
Ethics approval
Not applicable.
Consent to participate
Not applicable.
Consent for publication
This work is approved by all authors for publication.
Conflict of interest
The authors declare that they have no conflict of interest.
Additional information
Publisher's note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Li, J., Wang, X., Yang, Q. et al. Rolling force prediction in cold rolling process based on combined method of T-S fuzzy neural network and analytical model. Int J Adv Manuf Technol 121, 4087–4098 (2022). https://doi.org/10.1007/s00170-022-09567-5
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00170-022-09567-5