Top

Journal of Iron and Steel Research International

Published in:

05-05-2023 | Original Paper

Data-driven flatness intelligent representation method of cold rolled strip

Authors: Yang-huan Xu, Dong-cheng Wang, Bo-wei Duan, Hong-min Liu

Published in: Journal of Iron and Steel Research International | Issue 5/2023

Activate our intelligent search to find suitable subject content or patents.

search-config

AI-assisted search

Off

Abstract

A high-accuracy flatness prediction model is the basis for realizing flatness control. Real flatness is typically reflected as the strain distribution, which is a vector. However, it is difficult to obtain ideal results if the real flatness is directly used as the output value of the flatness intelligent prediction model. Thus, it is necessary to seek an abstract representation method of real flatness. For this reason, two new intelligent flatness representation models were proposed based on the autoencoder of unsupervised learning theory: the flatness autoencoder representation (FAR) model and the flatness stacked sparse autoencoder representation (FSSAR) model. Compared with the traditional Legendre fourth-order polynomial representation model, the representation accuracies of the FAR and FSSAR models are significantly improved, better representing the flatness defects, like the double tight edge. The optimal number of bottleneck layer neurons in the FAR and FSSAR models is 5, which means that five basic patterns can accurately represent real flatness. Compared with the FAR model, the FSSAR model has higher representation accuracy, although the flatness basic pattern is more abstract, and the physical meaning is not clear enough. Furthermore, the accuracy of the FAR model is slightly lower than that of the FSSAR model. However, it can automatically learn the flatness basic pattern with a very clear physical meaning for both the theoretical and real flatness, which is an optimal intelligent representation method for flatness.

previous article Extended-state-observer-based robust torsional vibration suppression for rolling mill main drive system with input saturation

next article Roll gap prediction in acceleration and deceleration process of cold rolling based on a data-driven method

[1]

J. Sun, P.F. Shan, Z. Wei, Y.H. Hu, Q.L. Wang, W. Peng, D.H. Zhang, J. Iron Steel Res. Int. 28 (2021) 563–573. https://doi.org/10.1007/s42243-020-00505-x.

[2]

D. Xu, Q. Yang, X.C. Wang, H.N. He, Y.Z. Sun, W.P. Li, Micromachines 11 (2020) 916. https://doi.org/10.3390/mi11100916.

[3]

D.C. Wang, H.M. Liu, J. Liu, Chin J. Mech. Eng. 30 (2017) 1248–1261. https://doi.org/10.1007/s10033-017-0163-8.

[4]

M. Ataka, ISIJ Int. 55 (2015) 89–102. https://doi.org/10.2355/isijinternational.55.89.

[5]

J.D. Li, X.C. Wang, Q. Yang, J.W. Zhao, Z.D. Wu, Z.H. Wang, Int. J. Adv. Manuf. Technol. 123 (2022) 389–405. https://doi.org/10.1007/s00170-022-10196-1.

[6]

Q.L. Wang, J. Sun, X. Li, Y.M. Liu, P.F. Wang, D.H. Zhang, J. Manuf. Process 34 (2018) 637–649. https://doi.org/10.1016/j.jmapro.2018.07.008.

[7]

Y. Peng, H.M. Liu, D.C. Wang, J. Cent. South Univ. Technol. 14 (2007) 278–284. https://doi.org/10.1007/s11771-007-0055-7.

[8]

Y. Zhang, Q. Yang, X.C. Wang, J. Iron Steel Res. Int. 18 (2011) 27–32. https://doi.org/10.1016/S1006-706X(12)60030-2.

[9]

X.Y. Shan, H.M. Liu, C.Y. Jia, J.L. Sun, J. Iron Steel Res. Int. 19 (2012) 31–37. https://doi.org/10.1016/S1006-706X(12)60070-3.

[10]

D.C. Wang, H.M. Liu, J. Iron Steel Res. Int. 19 (2012) 22–27. https://doi.org/10.1016/S1006-706X(12)60055-7.

[11]

D.C. Wang, W. Zhang, Z.J. Wang, H.M. Liu, Iron and Steel 51 (2016) No. 9, 51–56. https://doi.org/10.13228/j.boyuan.issn0449-749x.20160017.

[12]

C. Cui, G. Cao, X. Li, Z. Gao, X. Zhou, Z. Liu, J. Mater. Process. Technol. 309 (2022) 117736. https://doi.org/10.1016/j.jmatprotec.2022.117736.

[13]

Y. Liu, Z.Y. Gao, X.M. Zhou, Q.D. Zhang, J. Mech. Eng. 56 (2020) No. 11, 121–131. https://doi.org/10.3901/JME.2020.11.121.

[14]

S.H. Zhang, L. Deng, L.Z. Che, J. Manuf. Process. 75 (2022) 100–109. https://doi.org/10.1016/j.jmapro.2021.12.063.

[15]

D.C. Wang, Y.H. Xu, T.Y. Zhang, X.B. Ma, H.M. Liu, Metall. Res. Technol. 118 (2021) 303. https://doi.org/10.1051/metal/2020090.

[16]

H. Choi, Y. Kim, H. Lee, IEEE Trans. Ind. Inform. 17 (2021) 3890–3900. https://doi.org/10.1109/TII.2020.3015003.

[17]

Jagadish, D.L. Soni, S. Barad, Trans. Indian Inst. Met. 73 (2020) 1535–1542. https://doi.org/10.1007/s12666-020-01928-6.

[18]

I. Mohanty, R. Banerjee, A. Santara, S. Kundu, P. Mitra, Ironmak. Steelmak. 48 (2021) 953–961. https://doi.org/10.1080/03019233.2020.1848303.

[19]

Y.H. Xu, D.C. Wang, Y.M. Wang, W.Y. Yuan, H.X. Yu, H.M. Liu, Iron and Steel 56 (2021) No. 9, 26–35. https://doi.org/10.13228/j.boyuan.issn0449-749x.20210259.

[20]

M. Soleimani, S. Toofan, J. Circuits Syst. Comput. 28 (2019) 1950097. https://doi.org/10.1142/S021812661950097X.

[21]

H.M. Liu, X.Y. Shan, C.Y. Jia, J. Iron Steel Res. Int. 20 (2013) No. 8, 1–7. https://doi.org/10.1016/S1006-706X(13)60133-8.

[22]

M.M. Song, H.M. Liu, D.C. Wang, Y.H. Xu, ISIJ Int. 60 (2020) 286–296. https://doi.org/10.2355/isijinternational.ISIJINT-2019-328.

[23]

P.F. Wang, H.F. Wang, X. Li, D.H. Zhang, W.T. Li, Y.L. Yao, Appl. Math. Model. 91 (2021) 863–874. https://doi.org/10.1016/j.apm.2020.09.028.

[24]

X.G. Li, Y.M. Fang, L. Liu, J. Braz. Soc. Mech. Sci. Eng. 42 (2020) 270. https://doi.org/10.1007/s40430-020-02357-8.

[25]

X.L. Zhang, W.Y. Gao, Y.J. Lai, Y.T. Cheng, J. Cent. South Univ. 24 (2017) 2222–2230. https://doi.org/10.1007/s11771-017-3631-5.

[26]

C.Y. Jia, X.Y. Shan, Y.C. Cui, T. Bai, F.J. Cui, J. Iron Steel Res. Int. 20 (2013) No. 10, 17–22. https://doi.org/10.1016/S1006-706X(13)60170-3.

[27]

H.X. Yu, D.C. Wang, H.M. Liu, T.Y. Zhang, L.P. Yang, ISIJ Int. 60 (2020) 939–947. https://doi.org/10.2355/isijinternational.ISIJINT-2019-472.

[28]

Y. LeCun, Y. Bengio, G. Hinton, Nature 521 (2015) 436–444. https://doi.org/10.1038/nature14539.

[29]

J. Pereira, T. Schwede, Science 374 (2021) 1319–1320. https://doi.org/10.1126/science.abm8295.

[30]

S. Dargan, M. Kumar, M.R. Ayyagari, G. Kumar, Arch. Comput. Method Eng. 27 (2020) 1071–1092. https://doi.org/10.1007/s11831-019-09344-w.

[31]

N. Dhengre, S. Sinha, Vis. Comput. 38 (2022) 837–847. https://doi.org/10.1007/s00371-020-02054-6.

[32]

J.T. Chien, C.W. Wang, IEEE Trans. Pattern Anal. Mach. Intell. 44 (2022) 4975–4986. https://doi.org/10.1109/TPAMI.2021.3068187.

[33]

B. Schölkopf, F. Locatello, S. Bauer, N.R. Ke, N. Kalchbrenner, A. Goyal, Y. Bengio, Proc. IEEE 109 (2021) 612–634. https://doi.org/10.1109/JPROC.2021.3058954.

Title: Data-driven flatness intelligent representation method of cold rolled strip
Authors: Yang-huan Xu
Dong-cheng Wang
Bo-wei Duan
Hong-min Liu
Publication date: 05-05-2023
Publisher: Springer Nature Singapore
Published in: Journal of Iron and Steel Research International / Issue 5/2023
Print ISSN: 1006-706X
Electronic ISSN: 2210-3988
DOI: https://doi.org/10.1007/s42243-023-00956-y

Springer Professional

Data-driven flatness intelligent representation method of cold rolled strip

Abstract

Premium Partners

Springer Professional

Abstract

Please log in to get access to your license.

Other articles of this Issue 5/2023

Extended-state-observer-based robust torsional vibration suppression for rolling mill main drive system with input saturation

Special issue on application of AI in steelmaking and ferrous materials

Prior austenite grain boundary recognition in martensite microstructure based on deep learning

Hot metal quality monitoring system based on big data and machine learning

Machine learning study on time–temperature–transformation diagram of carbon and low-alloy steel

Automatic recognition and intelligent analysis of central shrinkage defects of continuous casting billets based on deep learning

Premium Partners