Neural Processing Letters

, Volume 50, Issue 3, pp 2455–2479 | Cite as

Application of Mind Evolutionary Algorithm and Artificial Neural Networks for Prediction of Profile and Flatness in Hot Strip Rolling Process

  • Zhenhua WangEmail author
  • Gengsheng Ma
  • Dianyao Gong
  • Jie Sun
  • Dianhua Zhang


Strip shape prediction is one of the most important technical to improve the quality of products in hot strip rolling process. In this paper, three hybrid models, including GA-MLP, MEA-MLP and PCA-MEA-MLP, are proposed for profile and flatness predictions by combining genetic algorithm (GA), mind evolutionary algorithm (MEA), principal component analysis (PCA) and multi-layer perceptron (MLP) neural networks. Mean absolute error (MAE), mean absolute percentage error, root mean squared error are adapted to evaluate the performance of the models. The results show that the data-driven model based on intelligent algorithm optimization neural networks can achieve good prediction of profile and flatness. Comparing with the hybrid GA-MLP model, the training speed of the hybrid MEA-MLP model is faster and the training time is greatly reduced. The model establishing with the input data after dimensionality reduction by PCA can reduce training time and become simple. The innovation of this paper is to propose a data-driven fast response model based on intelligent algorithm optimization neural network to replace the traditional mechanism model based on mathematical formula analysis to study complex, non-linear strip shape control in hot rolling process.


Artificial neural network Mind evolutionary algorithm Principal component analysis Genetic algorithm Profile and flatness prediction Hot strip rolling 



Ant colony optimization


Artificial neural networks


Genetic algorithm


Hot strip mill process


Mean absolute error


Mean absolute percentage error


Mind evolutionary algorithm


Multi-layer perceptron


Mean impact value


Principal component analysis


PID neural network


Particles swarm optimization


Radial basis function


Root mean squared error



This work was supported by National Key R&D Program of China (2017YFB0304100), National Natural Science Foundation of China (51704067, 51774084, 51634002), Open Research Fund from the State Key Laboratory of Rolling and Automation, Northeastern University (2017RALKFKT009).


  1. 1.
    Pittner J, Simaan MA (2010) A useful control model for tandem hot metal strip rolling. IEEE Trans Ind Appl 46(6):2251–2258Google Scholar
  2. 2.
    Peng K, Zhong H, Zhao L, Xue K, Ji Y (2014) Strip shape modeling and its setup strategy in hot strip mill process. Int J Adv Manuf Technol 72(5–8):589–605Google Scholar
  3. 3.
    Peng K, Zhang K, Dong J, You B (2015) Quality-relevant fault detection and diagnosis for hot strip mill process with multi-specification and multi-batch measurements. J Frankl Inst 352(3):987–1006zbMATHGoogle Scholar
  4. 4.
    Wang PF, Peng Y, Liu HM, Zhang DH, Wang JS (2013) Actuator efficiency adaptive flatness control model and its application in 1250 mm reversible cold strip mill. J Iron Steel Res Int 20(6):13–20Google Scholar
  5. 5.
    Wang P, Qiao D, Zhang D, Sun J, Liu H (2016) Optimal multi-variable flatness control for a cold rolling mill based on a box-constraint optimisation algorithm. Ironmak Steelmak 43(6):426–433Google Scholar
  6. 6.
    Pin G, Francesconi V, Cuzzola FA, Parisini T (2013) Adaptive task-space metal strip-flatness control in cold multi-roll mill stands. J Process Control 23(2):108–119Google Scholar
  7. 7.
    Wang QL, Sun J, Liu YM, Wang PF, Zhang DH (2017) Analysis of symmetrical flatness actuator efficiencies for UCM cold rolling mill by 3D elastic–plastic FEM. Int J Adv Manuf Technol 92(1–4):1371–1389Google Scholar
  8. 8.
    Lippmann R (1994) Book Review:” Neural networks, a comprehensive foundation”, by Simon Haykin. Int J Neural Syst 5(04):363–364Google Scholar
  9. 9.
    Portmann NF, Lindhoff D, Sorgel G, Gramckow O (1995) Application of neural networks in rolling mill automation. Iron Steel Eng 72(2):33–36Google Scholar
  10. 10.
    Larkiola J, Myllykoski P, Korhonen AS, Cser L (1998) The role of neural networks in the optimisation of rolling processes. J Mater Process Technol s80–81(Suppl 5):16–23Google Scholar
  11. 11.
    Jeon E, Kim S (2000) A study on the texturing of work roll for temper rolling. J Korean Soc Mach Tool Eng 9(4):7–16Google Scholar
  12. 12.
    Lee D, Lee Y (2002) Application of neural-network for improving accuracy of roll-force model in hot-rolling mill. Control Eng Pract 10(4):473–478Google Scholar
  13. 13.
    Moussaoui A, Selaimia Y, Abbassi HA (2006) Hybrid hot strip rolling force prediction using a Bayesian trained artificial neural network and analytical models. Am J Appl Sci 3(6):1885–1889Google Scholar
  14. 14.
    Peng Y, Liu H, Du R (2008) A neural network-based shape control system for cold rolling operations. J Mater Process Technol 202(1):54–60Google Scholar
  15. 15.
    Zhang XL, Zhang SY, Zhao WB, Xu T (2013) Flatness intelligent control via improved least squares support vector regression algorithm. J Cent South Univ 20(3):688–695Google Scholar
  16. 16.
    Zhang XL, Zhao L, Zhao WB, Xu T (2015) Novel method of flatness pattern recognition via cloud neural network. Soft Comput 19(10):2837–2843Google Scholar
  17. 17.
    Zhang XL, Xu T, Zhao L, Fan H, Zang J (2015) Research on flatness intelligent control via GA-PIDNN. J Intell Manuf 26(2):359–367Google Scholar
  18. 18.
    Zhang XL, Cheng L, Hao S, Gao WY, Lai YJ (2016) The new method of flatness pattern recognition based on GA-RBF-ARX and comparative research. Nonlinear Dyn 83(3):1535–1548MathSciNetzbMATHGoogle Scholar
  19. 19.
    Zhang XL, Cheng L, Hao S, Gao WY, Lai YJ (2017) Optimization design of RBF-ARX model and application research on flatness control system. Optim Control Appl Methods 38(1):19–35MathSciNetzbMATHGoogle Scholar
  20. 20.
    Wang ZH, Gong DY, Li X, Li GT, Zhang DH (2017) Prediction of bending force in the hot strip rolling process using artificial neural network and genetic algorithm (ANN-GA). Int J Adv Manuf Technol 93(9–12):3325–3338Google Scholar
  21. 21.
    Yan ZW, Wang BS, Bu HN, Zhang DH (2018) Intelligent assignation strategy of collaborative optimization for flatness control. J Braz Soc Mech Sci 40(3):163Google Scholar
  22. 22.
    Shardt YA, Mehrkanoon S, Zhang K, Yang X, Suykens J, Ding SX, Peng K (2018) Modelling the strip thickness in hot steel rolling mills using least-squares support vector machines. Can J Chem Eng 96(1):171–178Google Scholar
  23. 23.
    Nandan R, Rai R, Jayakanth R, Moitra S, Chakraborti N, Mukhopadhyay A (2005) Regulating crown and flatness during hot rolling: a multiobjective optimization study using genetic algorithms. Mater Manuf Process 20(3):459–478Google Scholar
  24. 24.
    Liu HM, Zhang XL, Wang YR (2005) Transfer matrix method of flatness control for strip mills. J Mater Process Technol 166(2):237–242Google Scholar
  25. 25.
    Chakraborti N, Kumar BS, Babu VS, Moitra S, Mukhopadhyay A (2006) Optimizing surface profiles during hot rolling: a genetic algorithms based multi-objective optimization. Comput Mater Sci 37(1–2):159–165Google Scholar
  26. 26.
    John S, Sikdar S, Swamy PK, Das S, Maity B (2008) Hybrid neural–GA model to predict and minimise flatness value of hot rolled strips. J Mater Process Technol 195(1–3):314–320Google Scholar
  27. 27.
    Wang ZH, Liu YM, Gong DY, Zhang DH (2018) A new predictive model for strip crown in hot rolling by using the hybrid AMPSO-SVR-based approach. Steel Res Int 89(7):1800003Google Scholar
  28. 28.
    Tang X, Zhuang L, Cai J, Li C (2010) Multi-fault classification based on support vector machine trained by chaos particle swarm optimization. Knowl Based Syst 23(5):486–490Google Scholar
  29. 29.
    Chen HL, Yang B, Wang G, Liu J, Xu X, Wang SJ, Liu DY (2011) A novel bankruptcy prediction model based on an adaptive fuzzy -nearest neighbor method. Knowl Based Syst 24(8):1348–1359Google Scholar
  30. 30.
    Jie J, Zeng J, Han C (2007) An extended mind evolutionary computation model for optimizations. Appl Math Comput 185(2):1038–1049zbMATHGoogle Scholar
  31. 31.
    Xu L, Du X, Wang B (2018) Short-term traffic flow prediction model of wavelet neural network based on mind evolutionary algorithm. Int J Pattern Recognit. CrossRefGoogle Scholar
  32. 32.
    Sun C, Sun Y, Wei L (1998) Mind-evolution-based machine learning: framework and the implementation of optimization. In: Proceedings of IEEE international conference on intelligent engineering systems (INES’98), pp 355–359Google Scholar
  33. 33.
    Liu H, Tian H, Liang X, Li Y (2015) New wind speed forecasting approaches using fast ensemble empirical model decomposition, genetic algorithm, mind evolutionary algorithm and artificial neural networks. Renew Energy 83:1066–1075Google Scholar
  34. 34.
    Wang W, Tang R, Li C, Liu P, Luo L (2018) A BP neural network model optimized by Mind Evolutionary Algorithm for predicting the ocean wave heights. Ocean Eng 162:98–107Google Scholar
  35. 35.
    Karataş C, Sozen A, Dulek E (2009) Modelling of residual stresses in the shot peened material C-1020 by artificial neural network. Expert Syst Appl 36(2):3514–3521Google Scholar
  36. 36.
    Rafei M, Sorkhabi SE, Mosavi MR (2014) Multi-objective optimization by means of multi-dimensional MLP neural networks. Neural Netw World 24(1):31–56Google Scholar
  37. 37.
    Liu H, Tian HQ, Pan DF, Li YF (2013) Forecasting models for wind speed using wavelet, wavelet packet, time series and artificial neural networks. Appl Energy 107(4):191–208Google Scholar
  38. 38.
    Liu H, Tian HQ, Li YF, Zhang L (2015) Comparison of four Adaboost algorithm based artificial neural networks in wind speed predictions. Energ Convers Manag 92(92):67–81Google Scholar
  39. 39.
    Shahani AR, Setayeshi S, Nodamaie SA, Asadi MA, Rezaie S (2009) Prediction of influence parameters on the hot rolling process using finite element method and neural network. J Mater Process Technol 209(4):1920–1935Google Scholar
  40. 40.
    Holland JH (1992) Adaptation in natural and artificial systems: an introductory analysis with applications to biology, control, and artificial intelligence. MIT Press, CambridgeGoogle Scholar
  41. 41.
    Holland JH (1984) Genetic algorithms and adaptation. In: Adaptive control of ill-defined systems. Springer, Boston, MA, pp 317–333Google Scholar
  42. 42.
    Wang X, Shi F, Yu L, Li Y (2013) Forty-three neural network case analysis in matlab. Beihang University Press, BeijingGoogle Scholar
  43. 43.
    He Z, Li C, Shen Y, He A (2017) A hybrid model equipped with the minimum cycle decomposition concept for short-term forecasting of electrical load time series. Neural Process Lett 46(3):1059–1081Google Scholar
  44. 44.
    Sikdar S, Kumari S (2009) Neural network model of the profile of hot-rolled strip. Int J Adv Manuf Technol 42(5–6):450–462Google Scholar
  45. 45.
    Samarasinghe S (2006) Neural networks for applied sciences and engineering: from fundamentals to complex pattern recognition. Auerbach Publications, New YorkzbMATHGoogle Scholar
  46. 46.
    Malvoni M, De Giorgi MG, Congedo PM (2016) Photovoltaic forecast based on hybrid PCA-LSSVM using dimensionality reducted data. Neurocomputing 211:72–83Google Scholar
  47. 47.
    Franceschi F, Cobo M, Figueredo M (2018) Discovering relationships and forecasting PM10 and PM2.5 concentrations in Bogotá, Colombia, using artificial neural networks, principal component analysis, and k-means clustering. Atmos Pollut Res. CrossRefGoogle Scholar

Copyright information

© Springer Science+Business Media, LLC, part of Springer Nature 2019

Authors and Affiliations

  • Zhenhua Wang
    • 1
    • 2
    Email author
  • Gengsheng Ma
    • 1
  • Dianyao Gong
    • 1
    • 2
  • Jie Sun
    • 1
    • 2
  • Dianhua Zhang
    • 1
    • 2
  1. 1.The State Key Laboratory of Rolling and AutomationNortheastern UniversityShenyangPeople’s Republic of China
  2. 2.Collaborative Innovation Center of Steel TechnologyShenyangPeople’s Republic of China

Personalised recommendations