Abstract
A method for nonlinear surrogate synthesis of surface eddy current probes with a volumetric structure of the excitation system was proposed. This method a priori provides a given uniform distribution of eddy current density in the testing object area where the measuring coil is located. The implementation of the task using modern metaeuristic stochastic algorithms for finding the global extremum was achieved. For the effective usage of such algorithms, taking into account the effect of velocity, metamodels of eddy current probe were preliminarily created. They were built using a productive approximation technique based on artificial radial-basis neural networks with a Gaussian activation function. Acceptable accuracy of metamodels was achieved due to the simultaneous application of the search area decomposition technologies and plural neural networks based on the techniques of associative machines with group methods for obtaining a solution. For metamodels creation a multidimensional computer experiment design with high homogeneity was used on the basis of the parameterless additive Rd-Kronecker sequence. Numerical experiments to determine the eddy current density distributions which formed by synthesized excitation structures were carried out. The advantages of using a three-dimensional structure excitation system in comparison with classical and planar ones in terms of increasing the width of the testing zone, which is characterized by uniform sensitivity, were shown. Examples of practical implementation of an excitation system with a volumetric structure for an surface eddy current probe are given. References 13, figures 8, table 1.
References
Repelianto A.S., Kasai N. The improvement of flaw detection by the configuration of uniform eddy current probes. Sensors. 2019. Vol. 19. No 2. Article № 397. DOI: https://doi.org/10.3390/s19020397
Ribeiro A.L., Ramos H.G., Postolache O. A simple forward direct problem solver for eddy current non-destructive inspection of aluminum plates using uniform field probes. Measurement. 2012. Vol. 45. No 2. Pp. 213-217. DOI: https://doi.org/10.1016/j.measurement.2011.03.029
Postolache O., Lopes A., Ramos H.G. GMR array uniform eddy current probe for defect detection in conductive specimens. Measurement. 2013. Vol. 46. Pp. 4369–4378. DOI: https://doi.org/10.1109/IMTC.2010.5488189
Hoshikawa H., Koyama K., Mitsuhashi S. Eddy Current and Magnetic Testing of Magnetic Material by Uniform Eddy Current Probe. Review of Quantitative Nondestructive Evaluation. 2005. Vol. 24. Pp. 494-501. DOI: https://doi.org/10.1007/978-1-4615-5339-7_137
Li Y., Ren S., Yan B., Zainal Abidin I.M., Wang Y. Imaging of Subsurface Corrosion Using Gradient-Field Pulsed Eddy Current Probes with Uniform Field Excitation. Sensors. 2017. Vol. 17. Article № 1747. DOI: https://doi.org/10.3390/s17081747
Halchenko V.Ya., Trembovetskaya R.V., Tychkov V.V. Surface eddy current probes: excitation systems of the optimal electromagnetic field (review). Devices and Methods of Measurements. 2020. Vol. 11. No 2. Pр. 91-104. DOI: https://doi.org/10.21122/2220-9506-2020-11-2-91-104
Halchenko V.Ya., Trembovetska R.V., Tychkov V.V., Storchak A.V. Nonlinear surrogate synthesis of the surface circular eddy current probes. Przegląd elektrotechniczny. 2019. No 9. Pp. 76-82. DOI: https://doi.org/10.15199/48.2019.09.15
Halchenko V.Ya., Trembovetskaya R.V., Tychkov V.V. Development of excitation structure RBF-metamodels of moving concentric eddy current probe. Electrical Engineering & Electromechanics. 2019. No 1. Pp. 28-38. DOI: https://doi.org/10.20998/2074-272X.2019.2.05
Itaya T., Ishida K., Kubota Y., Tanaka A., Takehira N. Visualization of Eddy Current Distributions for Arbitrarily Shaped Coils Parallel to a Moving Conductor Slab. Progress In Electromagnetics Research M. 2016. Vol. 47. Pp. 1-12. DOI: https://doi.org/10.2528/PIERM16011204
Santner T.J., Williams B.J., Notz W.I. The Design and Analysis of Computer Experiments. New York: Springer (Springer series in statistics), 2018. 446 p. DOI: https://doi.org/10.1007/978-1-4939-8847-1
Halchenko V.Ya., Trembovetska R.V., Tychkov V.V., Storchak A.V. The Construction of Effective Multidimensional Computer Designs of Experiments Based on a Quasi-random Additive Recursive Rd–sequence. Applied Computer Systems. 2020. Vol. 25. No 1. Pp. 70-76. DOI: https://doi.org/10.2478/acss-2020-0009
Géron A. Hands-On Machine Learning with Scikit-Learn, Keras and TensorFlow: Concepts, Tools, and Techniques to Build Intelligent Systems. 2nd Edition. O'Reilly Media, Inc. 2019. 856 p.
Brink H., Richards J., Feverolf M. Machine Learning. SPb.: Peter, 2017. 336 p. (Rus.)

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
Copyright (c) 2021 Tekhnichna Elektrodynamika

