Skip to main content

Advertisement

SpringerLink
Log in

An Efficient Procedure for Identifying the Prediction Model Between Residual Stress and Barkhausen Noise

  • Published:
Journal of Nondestructive Evaluation Aims and scope Submit manuscript

Abstract

Residual stress of case-hardened steel samples is predicted in this paper with the linear multivariable regression model. The development of the prediction model is based on the huge set of features calculated from the Barkhausen noise measurement signal among which the most suitable ones are chosen. The selection uses a genetic algorithm with leave-multiple-out cross-validation in the objective function. The original feature set contains collinear features that make the selection task even more complex. Thus a feature elimination procedure based on the successive projections algorithm is studied in this paper. Also the standard genetic algorithm is slightly modified to better serve the feature selection task. The obtained results are good showing that the proposed procedures suit well for residual stress predictions. Also the applied feature elimination procedure is applicable and can be safely used to reduce the dimensionality of the selection problem.

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

Similar content being viewed by others

References

  1. Jiles, D.C.: Dynamics of domain magnetization and the Barkhausen effect. Czechoslov. J. Phys. 50, 893–988 (2000)

    Article  Google Scholar 

  2. Saquet, O., Chicois, J., Vincent, A.: Barkhausen noise from plain carbon steels: analysis of the influence of microstructure. Mater. Sci. Eng. A, Struct. Mater.: Prop. Microstruct. Process. 269, 73–82 (1999)

    Article  Google Scholar 

  3. Blaow, M., Evans, J.T., Shaw, B.A.: Effect of hardness and composition gradients on Barkhausen emission in case hardened steel. J. Magn. Magn. Mater. 303, 153–159 (2006)

    Article  Google Scholar 

  4. Stefanita, C.-G., Atherton, D.L., Clapham, L.: Plastic versus elastic deformation effects on magnetic Barkhausen noise in steel. Acta Mater. 48, 3545–3551 (2000)

    Article  Google Scholar 

  5. Stewart, D.M., Stevens, K.J., Kaiser, A.B.: Magnetic Barkhausen noise analysis of stress in steel. Curr. Appl. Phys. 4, 308–311 (2004)

    Article  Google Scholar 

  6. Santa-aho, S., Vippola, M., Sorsa, A., Latokartano, J., Lindgren, M., Leiviskä, K., Lepistö, T.: Development of Barkhausen noise calibration blocks for reliable grinding burn detection. J. Mater. Process. Technol. 212, 408–416 (2012)

    Article  Google Scholar 

  7. O’Sullivan, D., Cotterell, M., Tanner, D.A., Mészáros, I.: Characterisation of ferritic stainless steel by Barkhausen techniques. Nondestruct. Test. Eval. Int. 37, 489–496 (2004)

    Google Scholar 

  8. Blaow, M., Evans, J.T., Shaw, B.: Effect of deformation in bending on magnetic Barkhausen noise in low alloy steel. Mater. Sci. Eng. A, Struct. Mater.: Prop. Microstruct. Process. 386, 74–80 (2004)

    Google Scholar 

  9. Moorthy, V., Choudhary, B.K., Vaidyanathan, S., Jayakumar, T., Rao, K.B.S., Raj, B.: An assessment of low cycle fatigue damage using magnetic Barkhausen emission in 9Cr-1Mo ferritic steel. Int. J. Fatigue 21, 263–269 (1999)

    Article  Google Scholar 

  10. Santa-aho, S., Vippola, M., Sorsa, A., Leiviskä, K., Lindgren, M., Lepistö, T.: Utilization of Barkhausen noise magnetizing sweeps for case-depth detection from hardened steel. Nondestruct. Test. Eval. Int. 52, 95–102 (2012)

    Google Scholar 

  11. Sorsa, A., Leiviskä, K., Santa-aho, S., Lepistö, T.: A data-based modelling scheme for estimating residual stress from Barkhausen noise measurements. Insight 54, 278–283 (2012)

    Article  Google Scholar 

  12. Sorsa, A., Leiviskä, K., Santa-aho, S., Lepistö, T.: Quantitative prediction of residual stress and hardness in case-hardened steel based on the Barkhausen noise measurement. Nondestruct. Test. Eval. Int. 46, 100–106 (2012)

    Google Scholar 

  13. Guyon, I., Elisseeff, A.: An introduction to variable and feature selection. J. Mach. Learn. Res. 3, 1157–1182 (2003)

    MATH  Google Scholar 

  14. Alexandridis, A., Patrinos, P., Sarimveis, H., Tsekouras, G.: A two-stage evolutionary algorithm for variable selection in the development of RBF neural network models. Chemom. Intell. Lab. Syst. 75, 149–162 (2005)

    Article  Google Scholar 

  15. Gardner, J.W., Boilot, P., Hines, E.L.: Enhancing electronic nose performance by sensor selection using a new integer-based genetic algorithm approach. Sens. Actuators B, Chem. 106, 114–121 (2005)

    Article  Google Scholar 

  16. Santa-aho, S., Vippola, M., Saarinen, T., Isakov, M., Sorsa, A., Lindgren, M., Leiviskä, K., Lepistö, T.: Barkhausen noise characterization during elastic bending and tensile-compression loading of case-hardened and tempered samples. J. Mater. Sci. 47, 6520–6528 (2012)

    Article  Google Scholar 

  17. Sorsa, A., Leiviskä, K.: Comparison of feature selection methods applied to Barkhausen noise data set. In: Bittanti, S., Cenedese, A., Zampieri, S. (eds.) Preprints of the 18th IFAC World Congress, Milano, Italy, 28 August–2 September 2011. IFAC, 6p

    Google Scholar 

  18. Leardi, R., González, A.L.: Genetic algorithms applied to feature selection in PLS regression: how and when to use them. Chemom. Intell. Lab. Syst. 41, 195–207 (1998)

    Article  Google Scholar 

  19. Gauchi, J.-P., Chagnon, P.: Comparison of selection methods of explanatory variables in PLS regression with application to manufacturing process data. Chemom. Intell. Lab. Syst. 58, 171–193 (2001)

    Article  Google Scholar 

  20. Baumann, K.: Cross-validation as the objective function for variable-selection techniques. TrAC, Trends Anal. Chem. 22, 395–406 (2003)

    Article  Google Scholar 

  21. Piotrowski, L., Augustyniak, B., Chmielewski, M., Hristoforou, E.V., Kosmas, K.: Evaluation of Barkhausen noise and magnetoacoustic emission signals properties for plastically deformed Armco iron. IEEE Trans. Magn. 46, 239–242 (2010)

    Article  Google Scholar 

  22. Araújo, M.C.U., Saldanha, T.C.B., Galvão, R.K.H., Yoneyama, T., Chame, H.C., Visani, V.: The successive projections algorithm for variable selection in spectroscopic multicomponent analysis. Chemom. Intell. Lab. Syst. 57, 65–73 (2001)

    Article  Google Scholar 

  23. Galvão, R.K.H., Araújo, M.C.U., Fragoso, W.D., Silva, E.C., José, G.E., Soares, S.F.C., Paiva, H.M.: A variable elimination method to improve the parsimony of MLR models using the successive projections algorithm. Chemom. Intell. Lab. Syst. 92, 83–91 (2008)

    Article  Google Scholar 

  24. Michalewicz, Z.: Genetic Algorithms + Data Structures = Evolution Programs. Springer, New York (1996)

    Book  MATH  Google Scholar 

  25. Sorsa, A., Leiviskä, K., Santa-aho, S., Vippola, M., Lepistö, T.: A study on laser-processed grinding burn simulation and analysis on Barkhausen noise measurement. Insight 52, 293–297 (2010)

    Article  Google Scholar 

  26. Harrell, F.E. Jr.: Regression Modeling Strategies with Applications to Linear Models, Logistic Regression, and Survival Analysis, 1st edn. Springer, New York (2001)

    MATH  Google Scholar 

  27. Stoppiglia, H., Dreyfus, G., Dubois, R., Oussar, Y.: Ranking a random feature for variable and feature selection. J. Mach. Learn. Res. 3, 1399–1414 (2003)

    MATH  Google Scholar 

  28. Hemmateenejad, B.: Correlation ranking procedure for factor selection in PC-ANN modeling and application to ADMETox evaluation. Chemom. Intell. Lab. Syst. 75, 231–245 (2005)

    Article  Google Scholar 

  29. Zhang, Y.X.: Artificial neural networks based on principal component analysis input selection for clinical pattern recognition analysis. Talanta 73, 68–75 (2007)

    Article  Google Scholar 

  30. McLeod, G., Clelland, K., Tapp, H., Kemsley, E.K., Wilson, R.H., Poulter, G., Coombs, D., Hewitt, C.J.: A comparison of variate pre-selection methods for use in partial least squares regression: a case study on NIR spectroscopy applied to monitoring beer fermentation. J. Food Eng. 90, 300–307 (2009)

    Article  Google Scholar 

  31. Mierczak, L., Jiles, D.C., Fantoni, G.: A new method for evaluation of mechanical stress using the reciprocal amplitude of magnetic Barkhausen noise. IEEE Trans. Magn. 47, 459–465 (2011)

    Article  Google Scholar 

  32. Wilson, J.W., Tian, G.Y., Moorthy, V., Shaw, B.A.: Magneto-acoustic emission and magnetic Barkhausen emission for case depth measurement in En36 gear steel. IEEE Trans. Magn. 45, 177–183 (2009)

    Article  Google Scholar 

  33. Sorsa, A.: Prediction of material properties based on non-destructive Barkhausen noise measurement. Doctoral dissertation. University of Oulu Graduate School, Acta Universitatis Ouluensis (2013)

Download references

Author information

Authors and Affiliations

  1. Control Engineering Laboratory, University of Oulu, P.O. Box 4300, 90014, University of Oulu, Finland

    Aki Sorsa & Kauko Leiviskä

  2. Department of Materials Science, Tampere University of Technology, P.O. Box 589, 33101, Tampere, Finland

    Suvi Santa-aho, Minnamari Vippola & Toivo Lepistö

Authors
  1. Aki Sorsa
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Kauko Leiviskä
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Suvi Santa-aho
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Minnamari Vippola
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Toivo Lepistö
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Aki Sorsa.

Rights and permissions

Reprints and permissions

About this article

Cite this article

Sorsa, A., Leiviskä, K., Santa-aho, S. et al. An Efficient Procedure for Identifying the Prediction Model Between Residual Stress and Barkhausen Noise. J Nondestruct Eval 32, 341–349 (2013). https://doi.org/10.1007/s10921-013-0187-7

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s10921-013-0187-7

Keywords

Search

Navigation