Skip to main content

Advertisement

Springer Nature Link
Log in

Elman neural networks for characterizing voids in welded strips: a study

  • Original Article
  • Published:
Neural Computing and Applications Aims and scope Submit manuscript

Abstract

Within the framework of aging materials inspection, one of the most important aspects regarding defects detection in metal welded strips. In this context, it is important to plan a method able to distinguish the presence or absence of defects within welds as well as a robust procedure able to characterize the defect itself. In this paper, an innovative solution that exploits a rotating magnetic field is presented. This approach has been carried out by a finite element model. Within this framework, it is necessary to consider techniques able to offer advantages in terms of sensibility of analysis, strong reliability, speed of carrying out, low costs: its implementation can be a useful support for inspectors. To this aim, it is necessary to solve inverse problems which are mostly ill-posed; in this case, the main problems consist on both the accurate formulation of the direct problem and the correct regularization of the inverse electromagnetic problem. We propose a heuristic inversion, regularizing the problem by the use of an Elman network. Experimental results are obtained using a database created through numerical modeling, confirming the effectiveness of the proposed methodology.

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

Access this article

Log in via an institution

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

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

Similar content being viewed by others

Explore related subjects

Discover the latest articles and news from researchers in related subjects, suggested using machine learning.

References

  1. Bowler J (1994) Eddy current interaction with an ideal crack: I. The forward problem. J Appl Phys 75:8128–8137

    Article  Google Scholar 

  2. Cacciola M, Calcagno S, Laganá F, Megali G, Pellicanó D, Versaci M, Morabito F (2009) Advanced integration of neural networks for chracterizing voids in welded strips. Lect Notes Comput Sci Artif Neural Netw 5769:455–464

    Google Scholar 

  3. Chen S, Zhang Z (2011) Temperature prediction of friction stir welding based on bayesian neural network. Appl Mech Mater 48–49:1208–1212

    Article  Google Scholar 

  4. Draper N, Smith H (1998) Applied regression analysis. Wiley, New York

    MATH  Google Scholar 

  5. Elman J (1990) Finding structure in time. Cognitive 15:179–211

    Article  Google Scholar 

  6. Fratini L, Buffa G, Palmeria D (2009) Using a neural network for predicting the average grain size in friction stir welding processes. Comput Struct 87:1166–1174

    Article  Google Scholar 

  7. Grimberg R, Radu E, Mihalache O, Savin A (1997) Calculation of the induced electromagnetic field created by an arbitrary current distribution located outside a conductive cylinder. J Phys D Appl Phys 30:2285–2291

    Article  Google Scholar 

  8. Kohavi R (1995) A study of cross-validation and bootstrap for accuracy estimation and model selection. In: Proceedings of the 14th international joint conference on artificial intelligence, pp 1137–1143

  9. Kurková V (1992) Kolmogorov’s theorem and multilayer neural networks. Neural Netw 5:501–506

    Article  Google Scholar 

  10. Lewis AM (1992) A theoretical model of the response of an eddy-current probe to a surface-breaking metal fatigue crack in a flat test piece. J Appl Phys 25:319–326

    Google Scholar 

  11. Rodger D, Leonard P, Lai H (1992) Interfacing the general 3d a–ψ method with a thin sheet conductor model. IEEE Trans Magn 28:1115–1117

    Article  Google Scholar 

  12. Savin A, Grimberg R, Mihalache O (1997) Analytical solutions describing the operation of a rotating magnetic field transducer. IEEE Trans Magn 33:697–701

    Article  Google Scholar 

  13. Takagi T, Hashimoto M, Fukutomi H, Kurokawa M, Miya K, Tsuboi H (1994) Benchmark models of eddy current testing for steam generator tube: experiment and numerical analysis. Int J Appl Elect Mater 4:149–162

    Google Scholar 

  14. Takagi T, Huang H, Fukutomi H, Tani J (1998) Numerical evaluation of correlation between crack size and eddy current testing signals by a very fast simulator. IEEE Trans Magn 34:2582–2584

    Google Scholar 

  15. Trevisan F, Kettunen L (2004) Geometric interpretation of discrete approaches to solving magnetostatics. IEEE Trans Magn 40:361–365

    Article  Google Scholar 

  16. Tsuboi H, Misaki T (1987) Three dimensional analysis of eddy current distribution by the boundary element method using vector variables. IEEE Trans Magn 23:3044–3046

    Article  Google Scholar 

  17. Wei H, Kovacevic R (2011) A neural network and multiple regression method for the characterization of the depth of weld penetration in laser welding based on acoustic signatures. J Intell Manuf 22:131–143

    Article  Google Scholar 

  18. Weisstein E (2008) Euler angles. mathworld, a wolfram web resource. Available online http://www.mathworld.wolfram.com/EulerAngles.html

  19. Yufen G, Cheng X, Yu S, Ding F (2010) Study on bpnn based welding joint properties soft sensing method. In: Proceedings of the 6th international conference on natural computation (ICNC), pp 1865–1868

Download references

Author information

Authors and Affiliations

  1. DIMET, University Mediterranea of Reggio Calabria, Via Graziella Feo di Vito, 89100, Reggio Calabria, Italy

    Matteo Cacciola, Giuseppe Megali, Diego Pellicanó & Francesco Carlo Morabito

Authors
  1. Matteo Cacciola
    View author publications

    You can also search for this author inPubMed Google Scholar

  2. Giuseppe Megali
    View author publications

    You can also search for this author inPubMed Google Scholar

  3. Diego Pellicanó
    View author publications

    You can also search for this author inPubMed Google Scholar

  4. Francesco Carlo Morabito
    View author publications

    You can also search for this author inPubMed Google Scholar

Corresponding author

Correspondence to Matteo Cacciola.

Rights and permissions

Reprints and permissions

About this article

Cite this article

Cacciola, M., Megali, G., Pellicanó, D. et al. Elman neural networks for characterizing voids in welded strips: a study. Neural Comput & Applic 21, 869–875 (2012). https://doi.org/10.1007/s00521-011-0609-3

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00521-011-0609-3

Keywords

Profiles

  1. Francesco Carlo Morabito View author profile