UDC 621.396
This paper proposes an approach to predicting the effectiveness of meta-screen screening based on an artificial neural network. The meta-screen is considered as a periodic structure of resonator copper plates on a dielectric substrate. An artificial neural network was trained for the task of predicting the effectiveness of meta-screen screening, based on computer modeling data as reference values, which demonstrated the potential applicability of the method in real conditions. Based on numerical simulation, a sample is formed that includes the values of the shielding efficiency in dB at the target frequency for various combinations of parameters. To approximate the nonlinear mapping of vector X to the value of screening efficiency, a multilayer fully connected neural network is used, trained in a supervised mode using the metric of the average absolute percentage error. The influence of hyperparameters and network structure on the convergence and accuracy of the model is analyzed. It is shown that with the optimal choice of architecture, the test prediction error does not exceed 7.01%, and the calculated values of the shielding efficiency are in good agreement with the results of electrodynamic modeling. The results obtained demonstrate the possibility of using the developed model in the tasks of accelerated parametric synthesis of meta-screens and automation of procedures for predicting screening efficiency.
meta-screen, shielding, electromagnetic compatibility, artificial neural network.
1. Gainutdinov R.R., Chermoshentsev S.F. Methodology of research of electromagnetic resistance of technical systems under external electromagnetic influences from several sources // Izvestiya vysshikh uchebnykh zavedeniy. Aviation equipment. 2023. No. 1. pp. 135-141.
2. Gainutdinov R.R. Investigation of the effectiveness of shielding composite material for the fuselage of an aircraft // Proceedings of MAY 2023, No. 133.
3. Hossain M.B., Faruque M.R.I., Islam M.T. Double elliptical resonator based quadruple band metamaterial absorber for EMI shielding applications in microwave regime // Alexandria Engineering Journal. 2023. Vol. 69. P. 193-206. DOI:https://doi.org/10.1016/j.aej.2023.01.035.
4. Felbacq D. An Invitation to Metamaterials: Theory and Applications. Cham: Springer, 2025. XVIII, 382 p. (Lecture Notes in Applied and Computational Mechanics; vol. 101). ISBN 978-3-031-86587-9.
5. Gainutdinov R.R., Chermoshentsev S.F. Experimental studies of electromagnetic interference in aircraft communication lines under the influence of radiation from radio transmitter antennas // News of higher educational institutions. Aviation equipment. 2024. No. 4. pp. 198-204.
6. Ivanov A.A., Komnatnov M.E. A device for indirect measurements of the effectiveness of electromagnetic shielding of small-sized shielding structures // Journal of Radio Electronics [Electronic resource]. 2022. № 11. URL: https://doi.org/10.30898/1684-1719.2022.11.1.
7. Qiu Y., Ye H., Zhang H., Zheng Y. Machine learning-driven optimization design of hydrogel-based negative hydration expansion metamaterials // Computer-Aided Design. 2024. Vol. 166. 103631. DOI:https://doi.org/10.1016/j.cad.2023.103631.
8. Boukraichi H., Akkari N., Casenave F., Ryckelynck D. A priori compression of convolutional neural networks for wave simulators // Engineering Applications of Artificial Intelligence. 2023. Vol. 126, Part C. 106973. DOI:https://doi.org/10.1016/j.engappai.2023.106973.
9. Gizatullin Z.M., Fatykhov I.D., Nurtdinov R.S. Prediction of side electromagnetic radiation from an electric power converter using an artificial neural network // Journal of Radio Electronics [Electronic resource]. 2025. No. 8. DOI:https://doi.org/10.30898/1684-1719.2025.8.13.
10. Amirkhanov A.A., Gainutdinov R.R. Prediction of crosstalk in aircraft communication cable lines based on an artificial neural network // Proceedings of MAY 2024, No. 139.
11. Kubík Z., Skála J. Shielding Effectiveness Simulation of Small Perforated Shielding Enclosures Using FEM // Energies. 2016. Vol. 9, no. 3. P. 129. DOI:https://doi.org/10.3390/en9030129.
12. Periyasamy A.P., Muthusamy L.P., Militký J. Neural network model applied to electromagnetic shielding effectiveness of ultra-light Ni/Cu coated polyester fibrous materials // Scientific Reports. 2022. Vol. 12. 8609. DOI:https://doi.org/10.1038/s41598-022-12593-8.
13. Feng Y., Li P., Xi R., Yun Y., Ren J., Yin Y.-Z. Broadband Phase Prediction of Electromagnetic Metamaterials Based on Deep Neural Network // Proceedings of 2021 IEEE 4th International Conference on Electronic Information and Communication Technology (ICEICT). 2021. P. 804-807. DOI:https://doi.org/10.1109/ICEICT53123.2021.9531157.
14. Dimitriadis A.I., Karamanos T.D., Kantartzis N.V., Tsiboukis T.D. Effective-surface modeling of infinite periodic metascreens exhibiting the extraordinary transmission phenomenon // Journal of the Optical Society of America B. 2016. Vol. 33, no. 3. P. 434-444.
15. Cerniauskas G., Sadia H., Alam P. Machine intelligence in metamaterials design: a review // Oxford Open Materials Science. 2024. Vol. 4, no. 1. itae001. DOI:https://doi.org/10.1093/oxfmat/itae001.
16. Gao J., Feng C., Wu X., et al. Deep neural network training method based on vectorgraphs for designing of metamaterial broadband polarization converters // Scientific Reports. 2023. Vol. 13. 5009. DOI:https://doi.org/10.1038/s41598-023-32142.
17. Tiwari S., Sharma P., Ali S. Metamaterial Parameter Estimation by Machine Learning Method // Research Square [Preprint]. 2024. DOI:https://doi.org/10.21203/rs.3.rs-4650387/v1.
18. Tian Z., Yang Y., Zhou S., et al. High-dimensional Bayesian optimization for metamaterial design // MGE Advances. 2024. Vol. 2, no. 4. e79. DOI:https://doi.org/10.1002/mgea.79.
19. Yang Z., Buehler M.J. High-Throughput Generation of 3D Graphene Metamaterials and Property Quantification Using Machine Learning // Small Methods. 2022. Vol. 6. 2200537. DOI:https://doi.org/10.1002/smtd.202200537.
20. Z. Yang, M. J. Buehler, High-Throughput Generation of 3D Graphene Metamaterials and Property Quantification Using Machine Learning. Small Methods 2022, 6, 2200537. https://doi.org/10.1002/smtd.202200537
