Advertisement

Comparisons of Different Data-Driven Modeling Techniques for Predicting Tensile Strength of X70 Pipeline Steels

  • Siwei WuEmail author
  • Jiakuan Ren
  • Xiaoguang Zhou
  • Guangming Cao
  • Zhenyu Liu
  • Jian YangEmail author
Technical Paper
  • 24 Downloads

Abstract

Mechanical property prediction for X70 pipeline steels attracts people’s attention because of maintaining high process stability and controlling production quality. Data-driven model is widely used and has the advantage of little professional knowledge requirement compared with phenomenological model. This paper introduced two new modeling techniques, namely ridge regression (RR) and random forest (RF). As a case, tensile strength prediction model of X70 pipeline steels was established and comparisons of different data-driven models, including the two new techniques and the already extensively used stepwise regression (SR), Bayesian regularization neural network (BRNN), radial-basis function neural network (RBFNN) and support vector machine (SVM), were made. The results show that all the models have reached good accuracies with relative error of ± 7%. On account of the excellent nonlinear fitting capability, models established by using intelligent algorithms (BRNN, RBFNN, SVM and RF) obtain better performance than multiple linear regression (SR and RR). Among the six models, RR provides a visualizing approach of the variable selection for multiple linear regression and RF achieves the best performance (R = 0.95 and MSE = 278.7 MPa2) on this data set.

Keywords

Multiple linear regression Intelligent algorithm Modeling Tensile strength X70 pipeline steels 

Notes

Acknowledgements

This work was supported by the National Key Research and Development Program of China (2017YFB0304900).

Compliance with Ethical Standards

Conflict of interest

The authors declared that they have no conflicts of interest to this work.

References

  1. 1.
    Liu L, Xiao H, Li Q, Liu Y, Li P, Yang Z, and Yu H, Mater Sci Eng A 688 (2017) 388.CrossRefGoogle Scholar
  2. 2.
    Qian D and Peng Y, J Mater Eng Perform 24 (2015) 1906.CrossRefGoogle Scholar
  3. 3.
    Eser A, Broeckmann C, and Simsir C, Comput Mater Sci 113 (2016) 280.CrossRefGoogle Scholar
  4. 4.
    Pouraliakbar H, Khalaj M J, Nazerfakhari M, and Khalaj G, J Iron Steel Res, Int 22 (2015) 446.Google Scholar
  5. 5.
    Powar A and Date P, Mat Sci Eng A 628 (2015) 89.CrossRefGoogle Scholar
  6. 6.
    Abraham S, Raisee M, Ghorbaniasl G, Contino F, and Lacor C, J Comput Phys 332 (2017) 461.CrossRefGoogle Scholar
  7. 7.
    Jovic O, Smrecki N, and Popovic Z, Talanta 150 (2016) 37.CrossRefGoogle Scholar
  8. 8.
    [8] Rakhshkhorshid M, and Teimouri Sendesi S A, J Iron Steel Res, Int 21 (2014) 246.Google Scholar
  9. 9.
    Kappatos V, Chamos A N, and Pantelakis S G, Mater Des 31 (2010) 336.CrossRefGoogle Scholar
  10. 10.
    Yang Z, Gu X S, Liang X Y, and Ling L C, Mater Des 31 (2010) 1042.CrossRefGoogle Scholar
  11. 11.
    Zhao Y H, Weng Y, Peng N Q, Tang G B, and Liu Z D, J Iron Steel Res, Int 20 (2013) 9.Google Scholar
  12. 12.
    Zhi J, Zhang G, Yang F, Yang R, Liu F, Song X, Zhao Y, and Li D, Geoderma Regional 10 (2017) 1.CrossRefGoogle Scholar
  13. 13.
    Zhao D, Wang Y, Liang D, and Zhang P, Mater Des 110 (2016) 676.CrossRefGoogle Scholar
  14. 14.
    Cevik A, J Constr Steel Res 63 (2007) 1305.CrossRefGoogle Scholar
  15. 15.
    Ahn J J, Byun H W, Oh K J, and Kim T Y, Expert Syst Appl 39 (2012) 8369.CrossRefGoogle Scholar
  16. 16.
    Chen F F, Breedon M, White P, Chu C, Mallick D, Thomas S, Sapper E, and Cole I, Mater Des 112 (2016) 410.CrossRefGoogle Scholar
  17. 17.
    He C L, Zong W J, Cao Z M, and Sun T, Mater Des 82 (2015) 216.CrossRefGoogle Scholar
  18. 18.
    Yang R, Er P V, Wang Z, and Tan K K, Neurocomputing 199 (2016) 31.CrossRefGoogle Scholar
  19. 19.
    Fathi A and Aghakouchak A A. Int J Fatigue 29 (2007) 261.CrossRefGoogle Scholar
  20. 20.
    Zhang Y Z, Dong J H, and Zhang Y F, Trans China Weld Inst 29 (2008) 81.Google Scholar
  21. 21.
    Shi D Y, Xiong G J, Chen J F, and Li Y H, Proc CSEE 34 (2014) 562.Google Scholar
  22. 22.
    Zhang H R, Zhang Y, Dai D B, Cao M, and Shen W F, Mater Des 92 (2016) 371.CrossRefGoogle Scholar
  23. 23.
    Lu W Z and Wang W J, Chemosphere 59 (2005) 693.CrossRefGoogle Scholar
  24. 24.
    Yeganeh B, Motlagh M S P, Rashidi Y, and Kamalan H, Atmos Environ 55 (2012) 357.CrossRefGoogle Scholar
  25. 25.
    Wang J F, Zhang L, Chen G X, and He X W, Appl Sci Technol 39 (2012) 28.Google Scholar
  26. 26.
    González Costa J J, Reigosa M J, Matías J M, and Covelo E F, Sci Total Environ 593594 (2017) 508.CrossRefGoogle Scholar
  27. 27.
    Shen X R, Study on the methods of fault detection and prediction in non-linear industrial processes based on support vector machine, Master Thesis, Bohai University, China (2017).Google Scholar
  28. 28.
    Zhou Y S, Research on combination forecasting model based on attribute selection algorithm and support vector machine, Master Thesis, Lanzhou University, China (2017).Google Scholar
  29. 29.
    Breiman L, Mach Learn 45 (2001) 5.Google Scholar
  30. 30.
    Adusumilli S, Bhatt D, Wang H, Devabhaktuni V, and Bhattacharya P, Neurocomputing 166 (2015) 185.CrossRefGoogle Scholar
  31. 31.
    Cottrell G A, Kemp R, Bhadeshia H K D H, Odette G R, and Yamamoto T, J Nucl Mater 367370 (2007) 603.CrossRefGoogle Scholar
  32. 32.
    Ndez-Delgado M, Cernadas E, Barro S, and Amorim D, J Mach Learn Res 15 (2014) 3133.Google Scholar

Copyright information

© The Indian Institute of Metals - IIM 2019

Authors and Affiliations

  1. 1.State Key Laboratory of Advanced Special Steel, School of Materials Science and EngineeringShanghai UniversityShanghaiPeople’s Republic of China
  2. 2.State Key Laboratory of Rolling and AutomationNortheastern UniversityShenyangPeople’s Republic of China

Personalised recommendations