Location via proxy:   [ UP ]  
[Report a bug]   [Manage cookies]                
Skip to main content

Advertisement

Springer Nature Link
Log in

Strip Crown Prediction in Hot Rolling Process Using Random Forest

  • Regular Paper
  • Published:
International Journal of Precision Engineering and Manufacturing Aims and scope Submit manuscript

Abstract

This paper established a model based on an ensemble method to predict strip crown using 230,000 coils of data obtained from a hot rolling line. Before modeling, a specific method was proposed to reduce noise and remove outliers, and a new dataset of 5657 samples was generated. Parameter tuning considering mean squared error (MSE) was carried out to establish three machine learning models including support vector machine (SVC), regression tree (RT), and random forest (RF). Determination coefficient (R2), mean absolute error (MAE) and root mean squared error (RMSE) were used as indicators to evaluate the prediction of models. Results showed that the RF had the best performance with the highest R2 of 0.707, as well as the lowest RMSE of 5.66 μm. Moreover, an additional method that repeated the three models 100 times was developed, and box plots were used to visualize the distribution of R2, MAE and RMSE. RF can correct for decision trees to reduce overfitting to their training set, improving the generalization, and in this paper, the trained RF which had stable performance is considered as the most recommended model. After that, for RF, rankings of rolling process variable were validated to make a comparison with the existing physical understanding.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10

Similar content being viewed by others

Abbreviations

A:

Averaged data

b:

Independent term

C40 :

Strip crown

CR :

Exit strip crown of model

e :

A vector of all ones

F B :

Bending force

F R :

Rolling force

h:

Thickness at 40 mm on the left

h′:

Thickness at 40 mm on the right

Hen :

Entry thickness

Hex :

Exit thickness

hc :

Thickness at the center of strip

L:

Number of samples

l 2 :

Barrel length

MAE:

Mean absolute error

MSE:

Mean squared error

Q:

A positive semidefinite matrix

\(R_{{{\text{BUR}}}}\) :

Back up roll crown

\(R_{{{\text{WR}}}}\) :

Work roll crown

R2 :

Determination coefficient

RC:

Rolling cycle subset

RF:

Random forest

RMSE:

Root mean squared error

RT:

Regression tree

S R :

Rolling shifting

S G :

Steel grade

SG:

Steel grade subset

ST:

Steel thickness subset

SVM:

Support vector machine

SVR:

Support vector regression

SW:

Steel width subset

W :

Exit width

x:

Vector of input samples

x′:

Vector of standard score

y:

Predicted value

\(\hat{y}\) :

Measured value

\(\overline{y}\) :

The arithmetic means of y

\(\alpha\) :

Dual coefficient

\(\alpha^{ * }\) :

Dual coefficient

\(\alpha_{{F_{{\text{R}}} }}\) :

Influence coefficients of rolling force for work up roll axial deflection

\(\alpha_{{{\text{WR}}}}\) :

Influence coefficients of work roll crown for work up roll axial deflection

\(\alpha_{{{\text{BUR}}}}\) :

Influence coefficients of back-up roll crown for work up roll axial deflection

\(\alpha_{{{\text{WRS}}}}\) :

Influence coefficients of work roll shifting for work up roll axial deflection

σ :

Standard deviation of x

\(\phi\) :

Identity function

\(\varepsilon\) :

Range of true predictions

\(\eta\) :

Strip crown inherent constant

\(\omega\) :

A vector to the hyperplane

μ:

Mean of x

\(\zeta\) :

Slack variable

\(\zeta^{ * }\) :

Slack variable

References

  1. Mücke, G., Pütz, P. D., & Gorgels, F. (2009). Methods of describing, assessing, and influencing shape deviations in strips (flat-rolled steel processes advanced technologies). Boca Raton: CRC.

    Google Scholar 

  2. Stone, M. D., & Gray, R. (1965). Theory and practical aspects in crown control. Iron and Steel Engineer, 42, 73–77.

    Google Scholar 

  3. Shohet, K. N., & Townsend, N. A. (1968). Roll bending methods of crown control in four-high plate mills. Journal of Iron and Steel Research International, 1088–1098.

  4. Ono, H., Watanabe, T., Yoshimoto, K., & Kaga, S. (1996). Industrial application of the HCX-MILL to hot strip mills. Hitachi Review, 45, 271–278.

    Google Scholar 

  5. Yasuda, K., Narita, K., Kobayashi, K., & Maeno, I. (1991). Shape controllability in new 6-high mill (UC-4 mill) with small diameter work rolls. ISIJ International, 31(6), 594–598.

    Article  Google Scholar 

  6. Aratani, H., Ozono, R., & Nakano, T. (1993). Expansion of pair cross mill applications to hot and cool rolling mills. Iron and Steel Engineer, 70, 32–37.

    Google Scholar 

  7. Bald, W., Beisemann, G., Feldmann, H., & Schultes, T. (1987). Continuously variable crown (CVC) rolling. Iron and Steel Engineer, 64, 32–41.

    Google Scholar 

  8. Zhang, T., Li, L., Shi-hong, L., Zhang, J.-B., & Gong, H. (2018). Comparisons of flow behavior characteristics and microstructure between asymmetrical shear rolling and symmetrical rolling by macro/micro coupling simulation. Journal of Computational Science, 29, 142–152.

    Article  Google Scholar 

  9. Faini, F., Attanasio, A., & Ceretti, E. (2018). Experimental and FE analysis of void closure in hot rolling of stainless steel. Journal of Materials Processing Technology, 259, 235–242.

    Article  Google Scholar 

  10. Mohanty, I., Bhattacharjee, D., & Datta, S. (2011). Designing cold rolled IF steel sheets with optimized tensile properties using ANN and GA. Computational Materials Science, 50(8), 2331–2337.

    Article  Google Scholar 

  11. Bu, H. N., Zhou, H. G., Yan, Z. W., & Zhang, D. H. (2019). Multi-objective optimization of bending force preset in cold rolling. Engineering Computations, 36(6), 2048–2065.

    Article  Google Scholar 

  12. Kim, J. M., Won, S. B., & Kim, B. M. (2018). Study on hot rolling process of the D51 large-diameter threaded bars (vol 32, pg 1761, 2018). Journal of Mechanical Science and Technology, 32(6), 2969–2970.

    Article  Google Scholar 

  13. Bouhouche, S., Yazid, L. L., Hocine, S., & Bast, J. (2010). Evaluation using online support-vector-machines and fuzzy reasoning. Application to condition monitoring of speeds rolling process. Control Engineering Practice, 18(9), 1060–1068.

    Article  Google Scholar 

  14. Hu, Y., Sun, J., Peng, W., & Zhang, D. (2020). A novel forecast model based on CF-PSO-SVM approach for predicting the roll gap in acceleration and deceleration process. Engineering Computations.

  15. Agarwal, K., Shivpuri, R., Zhu, Y. J., Chang, T. S., & Huang, H. (2011). Process knowledge based multi-class support vector classification (PK-MSVM) approach for surface defects in hot rolling. Expert Systems with Applications, 38(6), 7251–7262.

    Article  Google Scholar 

  16. Jung, J., Yoon, J. I., Park, S. J., Kang, J. Y., Kim, G. L., & Song, Y. H. (2019). Modelling feasibility constraints for materials design: Application to inverse crystallographic texture problem. Computational Materials Science, 156, 361–367.

    Article  Google Scholar 

  17. Xu, K., Ai, Y. H., & Wu, X. Y. (2013). Application of multi-scale feature extraction to surface defect classification of hot-rolled steels. International Journal of Minerals Metallurgy and Materials, 20(1).

  18. Okura, T., Ahmad, I., Kano, M., Hasebe, S., Kitada, H., & Murata, N. (2013). High-performance prediction of molten steel temperature in Tundish through gray-box model. ISIJ International, 53(1), 76–80.

    Article  Google Scholar 

  19. Li, L., Wang, Y. Y., Xu, J. T., Flora, J. R. V., Hoque, S., & Berge, N. D. (2018). Quantifying the sensitivity of feedstock properties and process conditions on hydrochar yield, carbon content, and energy content. Bioresource Technology, 262, 284–293.

    Article  Google Scholar 

  20. Wang, B., Qu, X. L., & Chen, Y. (2019). Identification of the potential prognostic genes of human melanoma. Journal of Cellular Physiology, 234(6), 9810–9815.

    Article  Google Scholar 

  21. Wang, Z. Y., Wang, Y. R., Zeng, R. C., Srinivasan, R. S., & Ahrentzen, S. (2018). Random forest based hourly building energy prediction. Energy Buildings, 171, 11–25.

    Article  Google Scholar 

  22. Peng, K. X., Zhong, H., Zhao, L., Xue, K., & Ji, Y. D. (2014). Strip shape modeling and its setup strategy in hot strip mill process. International Journal of Advanced Manufacturing Technology, 72(5–8), 589–605.

    Article  Google Scholar 

  23. Deng, J., Sun, J., Peng, W., Hu, Y., & Zhang, D. (2019). Application of neural networks for predicting hot-rolled strip crown. Applied Soft Computing, 78, 119–131.

    Article  Google Scholar 

  24. Wang, G. D. (1990). Fundamental of strip crown and flatness (1st ed.). China: China Railway Publishing House.

    Google Scholar 

  25. Cortes, C., & Vapnik, V. (1995). Support-vector networks. Machine Learning, 20(3), 273–297.

    MATH  Google Scholar 

  26. Hastie, T., Tibshirani, R., & Friedman, J. (2009). The elements of statistical learning (2nd ed.). New York: Springer.

    Book  Google Scholar 

  27. Breiman, L. (2001). Random forests. Machine Learning, 45(1), 5–32.

    Article  Google Scholar 

Download references

Acknowledgements

This study is financially supported by the National Key Research and Development Program of China (No. 2018YFB1308700), the National Natural Science Foundation of China (Nos. 51704067, 51774084, and 51634002), the Fundamental Research Funds for the Central Universities (Nos. N160704004, N170708020, and N2004010), and Liaoning Revitalization Talents Program (XLYC1907065).

Author information

Authors and Affiliations

  1. State Key Laboratory of Rolling and Automation, Northeastern University, Shenyang, 110819, Liaoning, People’s Republic of China

    Jie Sun, Jifei Deng, Wen Peng & Dianhua Zhang

Authors
  1. Jie Sun
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Jifei Deng
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Wen Peng
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Dianhua Zhang
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Jie Sun.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Sun, J., Deng, J., Peng, W. et al. Strip Crown Prediction in Hot Rolling Process Using Random Forest. Int. J. Precis. Eng. Manuf. 22, 301–311 (2021). https://doi.org/10.1007/s12541-020-00454-1

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s12541-020-00454-1

Keywords

Search

Navigation