skip to main content

Sensitivity Improvement of an In-Line Electromagnetic Metal Detector for Chemical Process Streams Using a Radial Basis Function Neural Network

Department of Control Science, University of Science, Pyongyang 355, North Korea

Received: 15 Sep 2026; Revised: 13 Oct 2026; Accepted: 26 Oct 2026; Available online: 19 Nov 2026; Published: 30 Jun 2027.
Editor(s): Istadi Istadi
Open Access Copyright (c) 2027 by Authors, Published by Universitas Diponegoro and BCREC Publishing Group
Creative Commons License This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Fulltext View|Download

Citation Format:
Cover Image
Abstract

Tramp-metal contamination in chemical process streams damages crushers, mills, and extruders, degrades product purity, and can provide ignition sources in combustible-dust atmospheres. In-line electromagnetic induction (EMI) metal detectors are the standard countermeasure, but their practical sensitivity is limited by the product effect—the channel-correlated background signal produced by conductive or moist process materials—which forces conservative detection thresholds and causes false alarms or missed small fragments. This paper presents an in-line EMI metal detector whose sensitivity and false-alarm stability are improved by a radial basis function (RBF) neural network that estimates the size and cross-sectional position of a metallic fragment from the induced voltages of a six-coil array mounted on a process pipe. A prototype was dynamically validated over 200 passes with 125 metallic objects, achieving 99.2% detection accuracy and a 3 mm minimum detectable radius. Because the prototype's component-level documentation is no longer available, a fully parameterized simulation of the in-line configuration was conducted with representative design values and a product-effect model: on 2400 training and 1500 test samples, the RBF network matched a conventional amplitude-threshold detector at the nominal product level (AUC 0.949 versus 0.962) while a two-hidden-layer multilayer perceptron baseline performed comparably (AUC 0.945); the decisive advantage appeared under product-effect drift, where the false-alarm rate of the RBF detector rose to only 20.3% at 2.5× the nominal product level against 71.1% for the amplitude threshold, without recalibration. The RBF estimator also localized fragments with a mean absolute error of 2.0 mm (pipe radius 45 mm), an estimation capability the threshold detector does not provide. These results indicate that a lightweight trained estimator can substantially improve the operability of in-line metal detection in chemical plants. Copyright © 2027 by Authors, Published by Universitas Diponegoro and BCREC Publishing Group. This is an open access article under the CC BY-SA License (https://creativecommons.org/licenses/by-sa/4.0).

Keywords: metal detector; electromagnetic induction; chemical process; product effect; sensitivity; radial basis function neural network; orthogonal least squares; in-line instrumentation

Article Metrics:

  1. Mills, D. (2016). Pneumatic Conveying Design Guide (3rd ed.). Oxford, U.K.: Butterworth-Heinemann. DOI: 10.1016/C2014-0-02678-0
  2. Eckhoff, R.K. (2003). Dust Explosions in the Process Industries (3rd ed.). Amsterdam, The Netherlands: Gulf Professional Publishing. DOI: 10.1016/B978-0-7506-7602-1.X5000-8
  3. European Parliament and Council (2000). Directive 1999/92/EC on minimum requirements for improving the safety and health protection of workers potentially at risk from explosive atmospheres (ATEX). Official Journal of the European Communities, L 23, 57–64
  4. Wait, J.R. (1971). Electromagnetic induction technique for locating a buried source. IEEE Transactions on Geoscience Electronics, 9(2), 95–98. DOI: 10.1109/TGE.1971.271473
  5. Das, Y., McFee, J.E., Toews, J., Stuart, G.C. (1990). Analysis of an electromagnetic induction detector for real-time location of buried objects. IEEE Transactions on Geoscience and Remote Sensing, 28(3), 278–287. DOI: 10.1109/36.54354
  6. Wynn, W.M., Frahm, C.P., Carroll, P.J., Clark, R.H., Wellhoner, J., Wynn, M.J. (1975). Advanced superconducting gradiometer/magnetometer arrays and a novel signal processing technique. IEEE Transactions on Magnetics, 11(2), 701–707. DOI: 10.1109/TMAG.1975.1058672
  7. Nabighian, M.N., Grauch, V.J.S., Hansen, R.O., LaFehr, T.R., Li, Y., Peirce, J.W., Phillips, J.D., Ruder, M.E. (2005). The historical development of the magnetic method in exploration. Geophysics, 70(6), 33ND–61ND. DOI: 10.1190/1.2133784
  8. Citak, H. (2020). Pulse induction metal detector: A performance application. IEEE Transactions on Plasma Science, 48(6), 2210–2223. DOI: 10.1109/TPS.2020.2996182
  9. Goodfellow, I., Bengio, Y., Courville, A. (2016). Deep Learning. Cambridge, MA, USA: MIT Press
  10. LeCun, Y., Bengio, Y., Hinton, G. (2015). Deep learning. Nature, 521, 436–444. DOI: 10.1038/nature14539
  11. Park, J., Sandberg, I.W. (1991). Universal approximation using radial-basis-function networks. Neural Computation, 3(2), 246–257. DOI: 10.1162/neco.1991.3.2.246
  12. Bishop, C.M. (1995). Neural Networks for Pattern Recognition. Oxford, U.K.: Oxford University Press
  13. Chen, S., Cowan, C. F. N., and Grant, P. M. (1991). Orthogonal least squares learning algorithm for radial basis function networks. IEEE Transactions on Neural Networks, 2(2), 302–309. DOI: 10.1109/72.80341
  14. Schwenker, F., Kestler, H.A., Palm, G. (2001). Three learning phases for radial-basis-function networks. Neural Networks, 14(4–5), 439–458. DOI: 10.1016/S0893-6080(01)00027-2
  15. Haykin, S. (2009). Neural Networks and Learning Machines (3rd ed.). Upper Saddle River, NJ, USA: Pearson
  16. Rumelhart, D.E., Hinton, G.E., Williams, R.J. (1986). Learning representations by back-propagating errors. Nature, 323, 533–536. DOI: 10.1038/323533a0
  17. Bradski, G. (2000). The OpenCV library. Dr. Dobb's Journal of Software Tools
  18. Fawcett, T. (2006). An introduction to ROC analysis. Pattern Recognition Letters, 27(8), 861–874. DOI: 10.1016/j.patrec.2005.10.010
  19. Hornik, K., Stinchcombe, M., and White, H. (1989). Multilayer feedforward networks are universal approximators. Neural Networks, 2(5), 359–366. DOI: 10.1016/0893-6080(89)90020-8
  20. Pedregosa, F., Varoquaux, G., Gramfort, A., Michel, V., Thirion, B., Grisel, O., Blondel, M., Prettenhofer, P., Weiss, R., Dubourg, V., Vanderplas, J., Passos, A., Cournapeau, D., Brucher, M., Perrot, M., and Duchesnay, E. (2011). Scikit-learn: Machine learning in Python. Journal of Machine Learning Research, 12, 2825–2830
  21. Sheen, D.M., McMakin, D.L., Hall, T.E. (2001). Three-dimensional millimeter-wave imaging for concealed weapon detection. IEEE Transactions on Microwave Theory and Techniques, 49(9), 1581–1592. DOI: 10.1109/22.942570
  22. European Parliament and Council (2016). General Data Protection Regulation (GDPR), Regulation (EU) 2016/679
  23. European Parliament and Council (2024). Artificial Intelligence Act, Regulation (EU) 2024/1689

Last update:

No citation recorded.

Last update:

No citation recorded.