Transactions of the Indian Institute of Metals

, Volume 72, Issue 9, pp 2443–2448 | Cite as

Application of BP Neural Networks on the Thickness Prediction of Sherardizing Coating

  • J. B. Long
  • X. B. LiEmail author
  • Y. C. Zhong
  • D. Peng
Technical Paper


Sherardizing is a surface protection method for obtaining Fe–Zn coating on the steel surface by thermal diffusion. The thickness of coating is critical for its performance. Therefore, it is necessary to propose a model to predict coating thickness based on different process parameters. The model for the relationship between sherardizing process parameters and the total thickness and each layer phase thickness of the coating is built using a three-layer backpropagation (BP) artificial neural network based on Levenberg–Marquardt algorithm. The results show that neural network model has a good predictive effect on the total thickness and each layer phase thickness of Fe–Zn coating. The prediction error of the model on the thickness of the coating is within 4.71%, and the coefficient of determination is 0.99974. It presents a new method for prediction of the thickness of sherardizing coating.


Sherardizing Fe–Zn coating BP neural network Prediction 



  1. 1.
    Chaliampalias D, Pistofidis N, and Vourlias G, Surf Eng 24 (2014) 259.CrossRefGoogle Scholar
  2. 2.
    Marder AR, Prog Mater Sci 45 (2000) 191.CrossRefGoogle Scholar
  3. 3.
    Chatterjee B, Met Finish 102 (2004) 40.CrossRefGoogle Scholar
  4. 4.
    Zhang L Y, Ma A, Jiang J H, Song D, Chen J Q, and Yang D H, Prog Nat Sci-Mater 22 (2012) 327.Google Scholar
  5. 5.
    Yada A P, Katayam H, Noda K, Masuda H, Nishikata A, and Tsuru T. Corros Sci 49 (2007) 3716.CrossRefGoogle Scholar
  6. 6.
    Price G C, Anti-Corros Method M 10 (1963) 171.CrossRefGoogle Scholar
  7. 7.
    Hajian A, Styles P, Artificial Neural Networks, Application of Soft Computing and Intelligent Methods in Geophysics, Cham (2018) p 9.Google Scholar
  8. 8.
    Hosseinpour S, Aghbashlo M, Tabatabaei M, and Mehrpooya M, Energy 138 (2017) 474.CrossRefGoogle Scholar
  9. 9.
    Jean M D, Liu C D, and Wang J T, Appl Surf Sci 245 (2005) 291.CrossRefGoogle Scholar
  10. 10.
    Samarasinghe S, Neural Networks for Applied Scienves and Engineering, Taylor & Francis New York (2007).Google Scholar
  11. 11.
    Jing L, Cheng J H, Shi J Y, and Huang F, Brief Introduction of Back Propagation (BP) Neural Network Algorithm and Its Improvement, Advances in Computer Science and Information Engineering, Springer Berlin Heidelberg, (2012) p 554.Google Scholar
  12. 12.
    Mao Q Q, Softw Guide 16 (2017) 145.Google Scholar
  13. 13.
    Gao H Y, Li X B, Feng W Y, and Peng D, Surf Tech 47 (2018) 135.Google Scholar
  14. 14.
    Wortelen D, Frieling R, Bracht H, Graf W, and Natrup F, Surf Coat Tech 263 (2015) 66.CrossRefGoogle Scholar
  15. 15.
    Sun W C, Tian M M, Zhang P, Wei H J, Hou G Q, and Wang Y, Trans Indian Inst Met 69 (2016) 1501.CrossRefGoogle Scholar
  16. 16.
    Han Y, Foundry Tech 8 (2014) 1720.Google Scholar
  17. 17.
    DeTienne K B, DeTienne D H, J Strat Market 25 (2017) 290.CrossRefGoogle Scholar
  18. 18.
    Lu T, Lü X S, Viljanen M, Energy Buildings 81 (2014) 270.CrossRefGoogle Scholar
  19. 19.
    Hebb D, The Organization of Behavior, Wiley, Massachusetts (1988).Google Scholar
  20. 20.
    Zhang W J, Computational Ecology:Artificial Neural Networks and Their Applications, World Scientific, Singapore (2010) p 6.CrossRefGoogle Scholar
  21. 21.
    Pandey A, Srivastava J K, Rajput N S, and Prasad R, Russ Agric Sci 36 (2010) 71.CrossRefGoogle Scholar
  22. 22.
    Hagan M T, and Menhaj M B, IEEE T Neural Networ 5 (1994) 989.CrossRefGoogle Scholar

Copyright information

© The Indian Institute of Metals - IIM 2019

Authors and Affiliations

  1. 1.School of Materials Science and EngineeringXiangtan UniversityXiangtanChina
  2. 2.Key Laboratory of Materials Design and Preparation Technology of Hunan ProvinceXiangtanChina

Personalised recommendations