Abstract
Control cooling is an essential method for microstructure and mechanical property control in hot rolling strip making. Therefore, it is vital to realize high-precision temperature distribution prediction and control in cooling process to ensure the industrial production. In this paper, a traditional mechanism model based on finite-difference method combined with online cycle velocity calculation strategy was introduced as one of the baseline methods estimating temperature distribution. However, considering calculation time, variable-velocity rolling makes it difficult to rapidly realize temperature and modifying water distribution of all segments in cooling zone. Herein, a temperature distribution prediction method based on recurrent neural network was proposed, by fully considering the variable-velocity rolling dynamic characteristics. And the temperature distribution prediction performance of the model with different recurrent cell and time steps was evaluated. The results indicated that the proposed model could realize temperature distribution prediction, and the model based on bi-LSTM and 48 timesteps has the highest determination coefficient value of 0.976, the lowest root mean square error of 8.03, and a mean absolute error of 5.7. Furthermore, compared with baseline model, the proposed model retained lower computational cost, making it applicable in industrial application by providing real-time temperature distribution prediction.
Similar content being viewed by others
Data Availability
All the data that supports the findings of study is available from the corresponding author upon reasonable request.
References
Herman JC (2001) Impact of new rolling and cooling technologies on thermomechanically processed steels. Ironmak Steelmak 28:159–163. https://doi.org/10.1179/030192301677894
Tsuyama S (2015) Thick plate technology for the last 100 years: a world leader in Thermo Mechanical Control Process. ISIJ Int 55:67–78. https://doi.org/10.2355/isijinternational.55.67
Uranga P, Rodríguez-Ibabe JM (2020) Thermomechanical processing of steels Metals 10(5):641. https://doi.org/10.3390/met10050641
Li C, Yuan G, Fet Ji, Kang J, Misra D, Wang GD (2015) Mechanism of microstructural control and mechanical properties in hot rolled plain C-Mn steel during controlled cooling. ISIJ Int 55:1721–1729. https://doi.org/10.2355/isijinternational.ISIJINT-2015-040
Shi J, Yuan G, Jiang LY, Li ZL, Zhao K, Wang GD (2015) Heat transfer symmetry of the strip surface due to agroup oblique slot jet impingement after hot rolling. Steel Res Int 86:1548–1557. https://doi.org/10.1002/srin.201400529
Timm W, Weinzierl K, Leipertz A, Zieger H, Zouhar G (2002) Modelling of heat transfer in hot strip mill run out table cooling. Steel Res 73:97–104. https://doi.org/10.1002/srin.200200180
Li HJ, Li ZL, Yuan G, Wang ZD, Wang GD (2013) Development of new generation cooling control system after rolling in hot rolled strip based on UFC. J Iron Steel Res Int 20:29–34. https://doi.org/10.1016/S1006-706X(13)60122-3
Gong DY, Xu JZ, Cai XH, Zheng H, Liu XH, Wang GD (2007) Model building of finishing temperature control for accelerative hot strip rolling. Key Eng Mater 340–341:633–638. https://doi.org/10.4028/www.scientific.net/kem.340-341.633
Xie HB, Jiang ZY, Liu XH, Wang GD, Zhou TG, Tieu AK (2007) On-line optimization of coiling temperature control on run-out table for hot strip mills. Key Eng Mater 340–341:701–706. https://doi.org/10.4028/www.scientific.net/kem.340-341.701
Latzel S (2001) Advanced automation concept of run out table strip cooling for hot strip and plate mills. IEEE Trans Ind Appl 37:1088–1097. https://doi.org/10.1109/28.936401
Zhang DZ, Ye HL, Xiang XF (2010) Coiling temperature optimal setting control model based on genetic algorithms and application in hot strip rolling mill. 2010 International Conference on Electrical and Control Engineering. IEEE. https://doi.org/10.1109/iCECE.2010.151
Zheng Y, Li N, Li S (2013) Hot-rolled strip laminar cooling process plant-wide temperature monitoring and control. Control Eng Pract 21:23–30. https://doi.org/10.1016/j.conengprac.2012.09.004
Xie HB, Liu XH, Wang GD, Zhang ZP (2006) Optimization and model of laminar cooling control system for hot strip mills. J Iron Steel Res Int 13:18–22. https://doi.org/10.1016/S1006-706X(06)60019-8
Li S, Li X, Yang Y (2016) Intelligent model building and GPC-PID based temperature curve control strategy for metallurgical industry. Math Probl Eng. https://doi.org/10.1155/2016/7454805
Li S, Zhou C, Deng ZH, Li X (2015) Application of genetic algorithm and least squares support vector machines in laminar cooling process. J Comput Theor Nanosci 12:1467–1471. https://doi.org/10.1166/jctn.2015.3915
Li S, Li X, Deng ZH (2014) A new kind of model of laminar cooling: by ls-svm and genetic algorithm. 9th International Conference on Bio-Inspired Computing-Theories and Applications (BIC-TA). Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-662-45049-9_41
Li S, Li X, Deng ZH (2015) A T-S fuzzy model-based intelligent temperature prediction model of laminar cooling system. 2015 Chinese automation congress (CAC) https://doi.org/10.1109/CAC.2015.7382685
Zheng Y, Li S, Wang XB (2011) Horizon-varying model predictive control for accelerated and controlled cooling process. IEEE Trans Ind Electron 58:329–336. https://doi.org/10.1109/TIE.2010.2045321
Zheng Y, Li S, Wang X (2009) Distributed model predictive control for plant-wide hot-rolled strip laminar cooling process. J Process Control 19:1427–1437. https://doi.org/10.1016/j.jprocont.2009.04.012
Li HJ, Li LG, Li YL et al (2015) Online monitor and control of cooling temperature on run-out table of hot strip mill. Steel Res Int 86:1225–1233. https://doi.org/10.1002/srin.201400269
Chen XL, Wang GD, Tian Y, Wang BX, Guo Y, Wang ZD (2014) An on-line finite element temperature field model for plate ultra fast cooling process. J Iron Steel Res Int 21:481–487. https://doi.org/10.1016/S1006-706X(14)60075-3
Li ZL, Li HJ, Yuan G, Wang GD, Wang XQ (2015) Research and application of ultra-fast cooling system and velocity controlled strategy for hot rolled strip. Steel Res Int 86:478–488. https://doi.org/10.1002/srin.201400077
Zheng Y, Li S, Wang X (2010) An approach to model building for accelerated cooling process using instance-based learning. Expert Syst Appl 37:5364–5371. https://doi.org/10.1016/j.eswa.2010.01.020
Zhang T, Xie Q, Wang B, Wu ZQ, Wang ZD, Wang GD (2016) A novel variable scale grid model for temperature self-adaptive control: an application on plate cooling process after rolling. Steel Res Int 87:1213–1219. https://doi.org/10.1002/srin.201500344
Schlang M, Broese E, Feldkeller B, Granckow O; Jansen M, Pappe T, Schaffner C, Sorgel G (1997) Neural networks for process control in steel manufacturing. 1997 IEEE International conference on Acoustics, Speech, and Signal Processing(ICASSP). IEEE. https://doi.org/10.1109/ICASSP.1997.599582
Liu EY, Peng W, Cao N, Yu SR, Xu J, Peng LG, Zhang DH (2014) Prediction of coiling temperature of hot rolled strip based on BP neural network. Appl Mech Mater 633–634:679–683. https://doi.org/10.4028/www.scientific.net/AMM.633-634.679
Deng J, Sun J, Peng W, Hu YH, Zhang DH (2019) Application of neural networks for predicting hot-rolled strip crown. Appl Soft Comput J 78:119–131. https://doi.org/10.1016/j.asoc.2019.02.030
Colla V, Vannucci M, Dimatteo A (2010) Diagnosis of the instability of the cooling behaviour of flat steel products through parametric characterisation, neural networks and statistics. ISA Trans 49:235–243. https://doi.org/10.1016/j.isatra.2010.01.001
Xing G, Ding J, Chai TY, Afshar P, Wang H (2012) Hybrid intelligent parameter estimation based on grey case-based reasoning for laminar cooling process. Eng Appl Artif Intell 25:418–429. https://doi.org/10.1016/j.engappai.2011.10.007
Rumelhart DE, Hintont GE, Williams RJ (1986) Learning representations by back-propagating errors. Nature 323:533–536. https://doi.org/10.1038/323533a0
Connor JT, Martin RD, Atlas LE (1994) Recurrent neural networks and robust time series prediction. IEEE Trans Neural Networks 5:240–254. https://doi.org/10.1109/72.279188
Gregor K, Danihelka I, Graves A, Rezende DJ, Wierstra D (2015) DRAW: a recurrent neural network for image generation. 2015 Proceedings of The 32nd International Conference on Machine Learning(ICML) 37: 1462–1471. http://proceedings.mlr.press/v37/gregor15.html
Graves A, Mohamed AR, Hinton G (2013) Speech recognition with deep recurrent neural networks, 2013 IEEE International Conference on Acoustics, Speech and Signal Processing(ICASSP). IEEE. https://doi.org/10.1109/ICASSP.2013.6638947
Sak H, Senior A, Beaufays F (2014) Long short-term memory recurrent neural network architectures for large scale acoustic modeling. 2014 15th Annual Conference Of The International Speech Communication Association (INTERSPEECH). ISCA. 2014:338–342. https://doi.org/10.21437/Interspeech.2014-80
Graves A, Schmidhuber J (2005) Framewise phoneme classification with bidirectional LSTM and other neural network architectures. Neural Netw 18:602–610. https://doi.org/10.1016/j.neunet.2005.06.042
JC Heck FM Salem (2017) Simplified minimal gated unit variations for recurrent neural networks. 2017 IEEE 60th international midwest symposium on circuits and systems (MWSCAS) IEEE https://doi.org/10.1109/MWSCAS.2017.8053242
Dey R, Salemt FM (2017). Gate-variants of Gated Recurrent Unit (GRU) neural networks. 2017 IEEE 60th 60th international midwest symposium on circuits and systems (MWSCAS). IEEE. https://doi.org/10.1109/MWSCAS.2017.8053243
Li L, Wen Z, Wang Z (2016) Outlier detection and correction during the process of groundwater lever monitoring base on pauta criterion with self-learning and smooth processing. Commun Comput Inf Sci 643:497–503. https://doi.org/10.1007/978-981-10-2663-8_51
Thireou T, Reczko M (2007) Bidirectional long short-term memory networks for predicting the subcellular localization of eukaryotic proteins. IEEE-ACM Transcations on computational biology and bioinformattics 4:441–446. https://doi.org/10.1109/TCBB.2007.1015
Lee SY, Tama BA, Choi C et al (2020) Spatial and sequential deep learning approach for predicting temperature distribution in a steel-making continuous casting process. IEEE Access 8:21953–21965. https://doi.org/10.1109/ACCESS.2020.2969498
Funding
This work was supported by the National Natural Science Foundation of China (51804074), Project funded by China Postdoctoral Science Foundation (2020M680964), Fundamental Research Funds for the Central Universities (N2107004), and Northeastern University Postdoctoral Foundation (20200323).
Author information
Authors and Affiliations
Contributions
Dong Chen: methodology, data curation, visualization, investigation, writing — original draft. Rui Zhang data curation, software, visualization. Zhenlei Li: conceptualization, methodology, supervision, validation, writing — review and editing. Yunjie Li: visualization. Guo Yuan: conceptualization, supervision, validation, writing — review and editing.
Corresponding author
Ethics declarations
Ethics approval
We promise that our research in this work is in compliance with ethical standards all the while.
Consent to participate
All the authors consent to participate in this work.
Consent to publication
The authors agree to publication in the Journal indicated below and also to publication of article in English by Springer in Springer’s corresponding English-language journal.
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
About this article
Cite this article
Chen, D., Zhang, R., Li, Z. et al. Temperature distribution prediction in control cooling process with recurrent neural network for variable-velocity hot rolling strips. Int J Adv Manuf Technol 120, 7533–7546 (2022). https://doi.org/10.1007/s00170-022-09065-8
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00170-022-09065-8