Skip to main content
SpringerLink
Log in

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

  • Technical Paper
  • Published:
Transactions of the Indian Institute of Metals Aims and scope Submit manuscript

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.

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

Access this article

Log in via an institution

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
Fig. 11

Similar content being viewed by others

References

  1. Liu L, Xiao H, Li Q, Liu Y, Li P, Yang Z, and Yu H, Mater Sci Eng A 688 (2017) 388.

    Article  Google Scholar 

  2. Qian D and Peng Y, J Mater Eng Perform 24 (2015) 1906.

    Article  Google Scholar 

  3. Eser A, Broeckmann C, and Simsir C, Comput Mater Sci 113 (2016) 280.

    Article  Google Scholar 

  4. Pouraliakbar H, Khalaj M J, Nazerfakhari M, and Khalaj G, J Iron Steel Res, Int 22 (2015) 446.

    Google Scholar 

  5. Powar A and Date P, Mat Sci Eng A 628 (2015) 89.

    Article  Google Scholar 

  6. Abraham S, Raisee M, Ghorbaniasl G, Contino F, and Lacor C, J Comput Phys 332 (2017) 461.

    Article  Google Scholar 

  7. Jovic O, Smrecki N, and Popovic Z, Talanta 150 (2016) 37.

    Article  Google Scholar 

  8. [8] Rakhshkhorshid M, and Teimouri Sendesi S A, J Iron Steel Res, Int 21 (2014) 246.

    Google Scholar 

  9. Kappatos V, Chamos A N, and Pantelakis S G, Mater Des 31 (2010) 336.

    Article  Google Scholar 

  10. Yang Z, Gu X S, Liang X Y, and Ling L C, Mater Des 31 (2010) 1042.

    Article  Google Scholar 

  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. Zhi J, Zhang G, Yang F, Yang R, Liu F, Song X, Zhao Y, and Li D, Geoderma Regional 10 (2017) 1.

    Article  Google Scholar 

  13. Zhao D, Wang Y, Liang D, and Zhang P, Mater Des 110 (2016) 676.

    Article  Google Scholar 

  14. Cevik A, J Constr Steel Res 63 (2007) 1305.

    Article  Google Scholar 

  15. Ahn J J, Byun H W, Oh K J, and Kim T Y, Expert Syst Appl 39 (2012) 8369.

    Article  Google Scholar 

  16. Chen F F, Breedon M, White P, Chu C, Mallick D, Thomas S, Sapper E, and Cole I, Mater Des 112 (2016) 410.

    Article  Google Scholar 

  17. He C L, Zong W J, Cao Z M, and Sun T, Mater Des 82 (2015) 216.

    Article  Google Scholar 

  18. Yang R, Er P V, Wang Z, and Tan K K, Neurocomputing 199 (2016) 31.

    Article  Google Scholar 

  19. Fathi A and Aghakouchak A A. Int J Fatigue 29 (2007) 261.

    Article  Google Scholar 

  20. Zhang Y Z, Dong J H, and Zhang Y F, Trans China Weld Inst 29 (2008) 81.

    Google Scholar 

  21. Shi D Y, Xiong G J, Chen J F, and Li Y H, Proc CSEE 34 (2014) 562.

    Google Scholar 

  22. Zhang H R, Zhang Y, Dai D B, Cao M, and Shen W F, Mater Des 92 (2016) 371.

    Article  Google Scholar 

  23. Lu W Z and Wang W J, Chemosphere 59 (2005) 693.

    Article  Google Scholar 

  24. Yeganeh B, Motlagh M S P, Rashidi Y, and Kamalan H, Atmos Environ 55 (2012) 357.

    Article  Google Scholar 

  25. Wang J F, Zhang L, Chen G X, and He X W, Appl Sci Technol 39 (2012) 28.

    Google Scholar 

  26. González Costa J J, Reigosa M J, Matías J M, and Covelo E F, Sci Total Environ 593–594 (2017) 508.

    Article  Google Scholar 

  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).

  28. Zhou Y S, Research on combination forecasting model based on attribute selection algorithm and support vector machine, Master Thesis, Lanzhou University, China (2017).

  29. Breiman L, Mach Learn 45 (2001) 5.

  30. Adusumilli S, Bhatt D, Wang H, Devabhaktuni V, and Bhattacharya P, Neurocomputing 166 (2015) 185.

    Article  Google Scholar 

  31. Cottrell G A, Kemp R, Bhadeshia H K D H, Odette G R, and Yamamoto T, J Nucl Mater 367–370 (2007) 603.

    Article  Google Scholar 

  32. Ndez-Delgado M, Cernadas E, Barro S, and Amorim D, J Mach Learn Res 15 (2014) 3133.

    Google Scholar 

Download references

Acknowledgements

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

Author information

Authors and Affiliations

  1. State Key Laboratory of Advanced Special Steel, School of Materials Science and Engineering, Shanghai University, Shanghai, 200444, People’s Republic of China

    Siwei Wu & Jian Yang

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

    Siwei Wu, Jiakuan Ren, Xiaoguang Zhou, Guangming Cao & Zhenyu Liu

Authors
  1. Siwei Wu
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Jiakuan Ren
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Xiaoguang Zhou
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Guangming Cao
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Zhenyu Liu
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Jian Yang
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding authors

Correspondence to Siwei Wu or Jian Yang.

Ethics declarations

Conflict of interest

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

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

Wu, S., Ren, J., Zhou, X. et al. Comparisons of Different Data-Driven Modeling Techniques for Predicting Tensile Strength of X70 Pipeline Steels. Trans Indian Inst Met 72, 1277–1288 (2019). https://doi.org/10.1007/s12666-019-01624-0

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s12666-019-01624-0

Keywords

Search

Navigation