Inverse Problem Approach for Electrical Conductivity Measurement using Eddy Current NDE and Artificial Neural Networks: Modeling and Experimental Validation

Authors

  • Abdelkader Bouhlal Electromagnetic Propulsion-Induction Systems Laboratory (LSPIE Batna’2000), Faculty of Technology, University of Batna 2, Batna, 05001, Algeria | Electrical Engineering Department, Nuclear Research Center of Brine, Ain Oussera, Bp 180, Djelfa, 17200, Algeria
  • Nasreddine Nait-Said Electromagnetic Propulsion-Induction Systems Laboratory, Faculty of Technology, University of Batna 2, Algeria
  • Fatima-Zohra Louai Electromagnetic Propulsion-Induction Systems Laboratory, Faculty of Technology, University of Batna 2, Algeria
  • Said Touati Electrical Engineering Department, Nuclear Research Center of Brine, Ain Oussera, Djelfa, Algeria
Volume: 15 | Issue: 3 | Pages: 23479-23485 | June 2025 | https://doi.org/10.48084/etasr.10836

Received: 9 March 2025 | Revised: 4 April 2025 and 20 April 2025 | Accepted: 22 April 2025 | Online: 29 April 2025


Corresponding author: Abdelkader Bouhlal

Abstract

Conductors serve as essential components in various electrical and electronic applications (steel, aircraft, and nuclear industries). Therefore, an accurate evaluation of their electrical parameters, in particular their electrical conductivity (σ), remains critical for assessing their performance in industrial processes. Although numerous eddy current based methods exist for conductivity measurement, this study approaches the problem through inverse problem solving. A novel approach integrating Eddy Current Testing (ECT) with Artificial Neural Networks (ANNs) is proposed to determine electrical conductivity from probe impedance measurements. An experimental setup has been developed that includes a custom-designed bobbin coil probe used in conjunction with metal plate samples (targets) and data acquisition and signal processing systems. To validate the introduced approach, conductivity values predicted by the ANN model were rigorously compared with reference measurements obtained using the four-point Direct Current Potential Drop (DCPD) technique. This comparative analysis demonstrates the robustness and measurement fidelity of the proposed approach.

Keywords:

Artificial Neural Networks (ANNs), Direct Current Potential Drop (DCPD), Eddy Current Nondestructive Evaluation (ECNDE), electrical conductivity, FEM

Downloads

Download data is not yet available.

References

D. E. Hughes, "Induction-balance and Experimental Researches therewith," Proceedings of the Physical Society of London, vol. 3, no. 1, Jan. 1879, Art. no. 81.

C. J. Hellier, Ed., Handbook of Nondestructive Evaluation, 3rd Edition. New York, NY, USA: McGraw-Hill Education, 2020.

C. V. Dodd and W. E. Deeds, "Analytical Solutions to Eddy‐Current Probe‐Coil Problems," Journal of Applied Physics, vol. 39, no. 6, pp. 2829–2838, May 1968.

P. Huang et al., "Conductivity Measurement of Non-magnetic Material Using the Phase Feature of Eddy Current Testing," Journal of Nondestructive Evaluation, vol. 42, no. 2, Jun. 2023, Art. no. 50.

P. Huang, H. Pu, J. Li, L. Xu, and Y. Xie, "An Eddy Current Testing Method for Thickness and Conductivity Measurement of Non-Magnetic Material," IEEE Sensors Journal, vol. 23, no. 5, pp. 4445–4454, Mar. 2023.

J. Martinos, T. Theodoulidis, N. Poulakis, and A. Tamburrino, "A Benchmark Problem for Eddy Current Nondestructive Evaluation," IEEE Transactions on Magnetics, vol. 50, no. 2, pp. 1053–1056, Feb. 2014.

S. Bilicz, M. Lambert, S. Gyimothy, J. Pavo, and G. Pichenot, "Characterization of eddy-current testing inverse problems using adaptive databases," in 15th International Workshop on Electromagnetic Non–Destructive Evaluation (ENDE’10), Szczecin, Poland, Jun. 2010, pp. 29–30.

F. Foucher et al., "Working Group COFREND « Eddy Current NDT modeling »: Benchmarks for validating and improving simulation codes acceptation," in 11th European Conference on Non-Destructive Testing (ECNDT 2014), Prague, Czech Republic, Oct. 2014.

B. Helifa, "Contribution à la simulation du CND par courants de Foucault en vue de la caractérisation des fissures débouchantes," Ph.D. dissertation, University of Nantes, Nantes, France, 2012.

R. Chelouah, P. Siarry, G. Berthiau, and B. D. Barmon, "An optimization method fitted for model inversion in non destructive control by eddy currents," The European Physical Journal Applied Physics, vol. 12, no. 3, pp. 231–238, Dec. 2000.

D. Hou, S. Lu, G. Yi, J. Qiu, and J. Liu, "A Target-Focusing Optimization Method for 3-D Profile Reconstruction of Defects Using MFL Measurements," IEEE Transactions on Instrumentation and Measurement, vol. 72, pp. 1–11, 2023.

Y.-F. Shih, Y.-R. Wang, S.-S. Wei, and C.-W. Chen, "Improving Non-Destructive Test Results Using Artificial Neural NetworksImproving Non-Destructive Test Results Using Artificial Neural Networks," International Journal of Machine Learning and Computing, vol. 5, no. 6, pp. 480–483, Dec. 2015.

B. Zahran, "Using Neural Networks to Predict the Hardness of Aluminum Alloys," Engineering, Technology & Applied Science Research, vol. 5, no. 1, pp. 757–759, Feb. 2015.

B. P. C. Rao, B. Raj, T. Jayakumar, and P. Kalyanasundaram, "An artificial neural network for eddy current testing of austenitic stainless steel welds," NDT & E International, vol. 35, no. 6, pp. 393–398, Sep. 2002.

J. A. Buck, P. R. Underhill, J. E. Morelli, and T. W. Krause, "Simultaneous Multiparameter Measurement in Pulsed Eddy Current Steam Generator Data Using Artificial Neural Networks," IEEE Transactions on Instrumentation and Measurement, vol. 65, no. 3, pp. 672–679, Mar. 2016.

X. Cui, Y. Liu, Y. Zhang, and C. Wang, "Tire Defects Classification with Multi-Contrast Convolutional Neural Networks," International Journal of Pattern Recognition and Artificial Intelligence, vol. 32, no. 04, Apr. 2018, Art. no. 1850011.

Properties and Selection: Nonferrous Alloys and Special-Purpose Materials. Geauga County, OH, USA: ASM International, 1990.

D. R. Lide, Ed., CRC Handbook of Chemistry and Physics, 84th ed. Boca Raton, Fl, USA: CRC Press, 2003.

M. B. Heaney, "Electrical conductivity and resistivity," in The Measurement, Instrumentation and Sensors Handbook, 1st ed., Boca Raton, Fl, USA: CRC Press LLC, 1999.

S. Haykin, Neural Networks and Learning Machines, 3rd edition. London, UK: Pearson, 2008.

K. Pandya, D. Dabhi, P. Mochi, and V. Rajput, "Levy Enhanced Cross Entropy-based Optimized Training of Feedforward Neural Networks," Engineering, Technology & Applied Science Research, vol. 12, no. 5, pp. 9196–9202, Oct. 2022.

A. D. Pokrovskii and A. A. Khvostov, "Investigation of the parameters of samples that are used for eddy-current inspections," Russian Journal of Nondestructive Testing, vol. 49, no. 4, pp. 225–233, Apr. 2013.

Downloads

How to Cite

[1]
Bouhlal, A., Nait-Said, N., Louai, F.-Z. and Touati, S. 2025. Inverse Problem Approach for Electrical Conductivity Measurement using Eddy Current NDE and Artificial Neural Networks: Modeling and Experimental Validation. Engineering, Technology & Applied Science Research. 15, 3 (Jun. 2025), 23479–23485. DOI:https://doi.org/10.48084/etasr.10836.

Metrics

Abstract Views: 93
PDF Downloads: 57

Metrics Information

License

Copyright (c) 2025 Abdelkader Bouhlal, Nasreddine Nait-Said, Fatima-Zohra Louai, Said Touati

Creative Commons License

This work is licensed under a Creative Commons Attribution 4.0 International License.

Authors who publish with this journal agree to the following terms:

- Authors retain the copyright and grant the journal the right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.

- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.

- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) after its publication in ETASR with an acknowledgement of its initial publication in this journal.