"Tekhnichna Diahnostyka ta Neruinivnyi Kontrol" (Technical Diagnostics and Non-Destructive Testing) #2, 2025, pp. 3-11
Enhancing large-scale structure diagnostics through uav-based data and neural network analysis
L.M. Lobanov, I.L. Shkurat, D.I. Stelmakh, O.P. Shutkevych, V.V. Savitsky
E.O. Paton Electric Welding Institute of the NAS of Ukraine
11 Kazymyr Malevych Str., 03150, Kyiv, Ukraine. E-mail: innashkurat2909@gmail.com
The article presents an approach to remote diagnostics of damage to large-sized engineering structures using unmanned aerial
vehicles (UAVs) and convolutional neural networks. The study was conducted to automate the process of detecting structural
defects in the Kyiv TV tower. The research methodology involved the collection and preprocessing of 14187 images and the
development of a modified architecture of the U-Net neural network for damage segmentation. An experimental study of
different architectural settings of the model demonstrated the effectiveness of the proposed modifications, which reduced the
error of defect detection by 3...5 % compared to the baseline models. It was found that the optimal number of training iterations
is 15–20 epochs. The developed model demonstrated the ability to detect damage that may be missed by the operator, which
confirms the potential of automated diagnostic systems based on artificial intelligence. The study provides new prospects for
improving the efficiency of monitoring infrastructure facilities, especially in conditions of limited access or increased risks to
personnel. 41 Ref., 2 Tabl., 6 Fig.
Keywords: remote diagnostics, defects, artificial intelligence, neural networks, image segmentation, UAVs
Received: 06.03.25
Received in revised form: 04.04.25
Accepted: 08.05.25
References
1. Balayssac, J.-P., Garnier, V. et al. (2018) Non-Destructive testing and evaluation of civil engineering structures. STE Press Ltd., Elsevier Science.
https://doi.org/10.1016/C2016-0-01227-52. Reddy, K.A. (2017) Non-destructive testing, evaluation of stainless steel materials. Mater. Today Proc., 4(8), 7302-7312.
https://doi.org/10.1016/j.matpr.2017.07.0603. Deepak, J.R., Raja, V.K.B., Srikanth, D., Surendran, H., Nickolas, M.M. (2021) Non-destructive testing (NDT) techniques for low carbon steel welded joints: A review and experimental study. Mater. Today Proc., 44(8), 3732-3737.
https://doi.org/10.1016/j.matpr.2020.11.5784. Polimeno, M., Roselli, I., Luprano, V.A.M., Mongelli, M., Tatì, A., De Canio, G. (2018) A non-destructive testing methodology for damage assessment of reinforced concrete buildings after seismic events. Engineering Structures, 163, 122-136.
https://doi.org/10.1016/j.engstruct.2018.02.0535. Bahonar, M., Safizadeh, M. (2021) Investigation of real delamination detection in composite structure using air-coupled ultrasonic testing. Composite Structures, 280, 114939.
https://doi.org/10.1016/j.compstruct.2021.1149396. Chen, Y., Kang, Y., Feng, B., Li, Y., Cai, X. (2022) Automatic defect identification in magnetic particle testing using a digital model aided de-noising method. Measurement, 198, 111427.
https://doi.org/10.1016/j.measurement.2022.1114277. Van Steen, C., Pahlavan, P., Wevers, M., Verstrynge, E. (2018) Localisation and characterisation of corrosion damage in reinforced concrete by means of acoustic emission and X-ray computed tomography. Construction and Building Materials, 197, 21-29.
https://doi.org/10.1016/j.conbuildmat.2018.11.1598. Suzuki, T., Ogata, H., Takada, R., Aoki, M., Ohtsu, M. (2010) Use of acoustic emission and X-ray computed tomography for damage evaluation of freeze-thawed concrete. Construction and Building Materials, 24, 2347-2352.
https://doi.org/10.1016/j.conbuildmat.2010.05.0059. Pedram, M., Taylor, S., Hamill, G., Robinson, D., OBrien, E., Uddin, N. (2022) Experimental evaluation of heat transition mechanism in concrete with subsurface defects using infrared thermography. Construction and Building Materials, 360, 129531.
https://doi.org/10.1016/j.conbuildmat.2022.12953110. Shrestha, P., Avci, O., Rifai, S., Abla, F., Seek, M., Barth, K., Halabe, U. (2025) A review of infrared thermography applications for civil infrastructure. Structural Durability & Health Monitoring, 19(2), 193-231.
https://doi.org/10.32604/sdhm.2024.04953011. Lobanov, L.M., Stelmakh, D., Shkurat, I., Savitsky, V., Toldo, R., Alessi, A. (2025) Determination of a TV tower verticality using UAVs, RTK and photogrammetry. In: VIIth International Conference «Welding and Related Technologies », Yaremche, Ukraine, 7-10 October 2024, pp. 149-153.
https://doi.org/10.1201/9781003518518-3012. Lobanov, L., Stelmakh, D., Savitsky, V., Diadin, V., Shutkevych, O., Shkurat, I. (2024) Damage detection and analysis using unmanned aerial vehicles (UAVs) and photogrammetry method. Procedia Structural Integrity, 59, 43-49.
https://doi.org/10.1016/j.prostr.2024.04.00813. Lobanov, L.M., Stelmakh, D.I., Savitsky, V.V., Diadin, V.P., Shutkevych, O.P., Kozachek, A.G. (2023) Remote assessment of damage to Kyiv TV tower based on the application of aerial photography and photogrammetry method. Tekh. Diagnost. ta Neruiniv. Kontrol, 3, 16-20 [in Ukrainian].
https://doi.org/10.37434/tdnk2023.03.0314. Onososen, A., Musonda, I., Onatayo, D., Tjebane, M., Saka, A., Fagbenro, R. (2023) Impediments to construction site digitalization using unmanned aerial vehicles (UAVs). Drones, 7(1), 45.
https://doi.org/10.3390/drones701004515. Albeaino, G., Gheisari, M., Franz, B.W. (2019) A systematic review of unmanned aerial vehicle application areas and technologies in the AEC domain. J. of Information Technology in Construction (ITcon), 24, 381-405. DOI: https://doi.org/www.itcon.org/2019/20
16. Ham, Y., Han, K.K., Lin, J.J., Golparvar-Fard, M. (2016) Visual monitoring of civil infrastructure systems via cameraequipped unmanned aerial vehicles (UAVs): A review of related works. Visualization in Engineering, 4, 1.
https://doi.org/10.1186/s40327-015-0029-z17. Pant, S,, Nooralishahi, P., Avdelidis, N.P., Ibarra-Castanedo, C., Genest, M., Deane, S. et al. (2021) Evaluation and selection of video stabilization techniques for uav-based active infrared thermography application. Sensors, 21, 1604.
https://doi.org/10.3390/s2105160418. Ciampa, E., De Vito, L., Rosaria Pecce, M. (2019) Practical issues on the use of drones for construction inspections. J. of Physics: Conference Series, 1249, 012016.
https://doi.org/10.1088/1742-6596/1249/1/01201619. Duque, L., Seo, J., Wacker, J. (2018) Synthesis of unmanned aerial vehicle applications for infrastructures. J. Perform. Constr. Facil., 32(4).
https://doi.org/10.1061/(ASCE)CF.1943-5509.000118520. Rakha, T., Gorodetsky, A. (2018) A review of unmanned aerial system (UAS) applications in the built environment: Towards automated building inspection procedures using drones Aut. in Constr., 93, 252-264.
https://doi.org/10.1016/j.autcon.2018.05.00221. Wu, W., Qurishee, M.A., Owino, J., Fomunung, I., Onyango, M., Atolagbe, B. (2018) Coupling deep learning and UAV for infrastructure condition assessment automation. In: 2018 IEEE International Smart Cities Conference, ISC2, 2018 Sep 16-19, Kansas City, MO, USA.
https://doi.org/10.1109/ISC2.2018.865697122. Gu, J., Wang, Z., Kuen, J., Ma, L., Shahroudy, A., Shuai, B., Liu, T., Wang, X., Wang, G. (2016) Recent advances in convolutional neural networks. Pattern Recognition, 77, 354-377.
https://doi.org/10.1016/j.patcog.2017.10.01323. Gulgec, N.S., Takáč, M., Pakzad, S.N. (2017) Structural damage detection using convolutional neural networks. In: Conference Proceedings of the Society for Experimental Mechanics Series, pp. 331-337.
https://doi.org/10.1007/978-3-319-54858-6_3324. Krizhevsky, A., Sutskever, I., Hinton, G. (2012) Imagenet classification with deep convolutional neural networks. Advancesin Neural Information Processing Systems, 25(2), 1097-1105.
https://doi.org/10.1145/306538625. Lee, S.Y., Tama, B.A., Moon, S.J., Lee, S. (2019) Steel surface defect diagnostics using deep convolutional neural network and class activation map. Applied Sciences, 9(24), 5449.
https://doi.org/10.3390/app924544926. Tabernik, D., Šela, S., Skvarc, J., Skocaj, D. (2020) Segmentation-based deep-learning approach for surfacedefect detection. J. of Intelligent Manufacturing, 31(3), 759- 776.
https://doi.org/10.1007/s10845-019-01476-x27. Prappacher, N., Bullmann, M., Bohn, G.; Deinzer, F.; Linke, A. (2020) Defect detection on rolling element surface scans using neural image segmentation. Applied Sciences, 10(9), 3290.
https://doi.org/10.3390/app1009329028. Li, J., Su, Z., Geng, J., Yin, Y. (2018) Real-time detection of steel strip surface defects based on improved YOLO detection network. IFAC-PapersOnLine, 51(21), 76-81.
https://doi.org/10.1016/j.ifacol.2018.09.41229. Wei, R., Song, Y., Zhang, Y. (2020) Enhanced faster region convolutional neural networks for steel surface defect detection. ISIJ International, 60(3), 539-545.
https://doi.org/10.2355/isijinternational.ISIJINT-2019-33530. Cha, Y.-J., Choi, W., Buyukozturk, O. (2017) Deep learningbased crack damage detection using convolutional neural networks. Computer-Aided Civil and Infrastructure Engineering, 32(5), 361-378.
https://doi.org/10.1111/mice.1226331. Hutchinson, T., Chen, Z. (2006) Improved image analysis for evaluating concrete damage. J. of Computing in Civil Engineering, 20(3), 210-216.
https://doi.org/10.1061/(ASCE)0887-3801(2006)20:3(210)32. Dung, C., Sekiya, H., Hirano, S., Okatani, T., Miki, C. (2019) A vision-based method for crack detection in gusset plate welded joints of steel bridges using deep convolutional neural networks. Automation in Construction, 102, 217-229.
https://doi.org/10.1016/j.autcon.2019.02.01333. Shen, H.-K., Chen, P.-H., Chang, L.-M. (2013) Automated steel bridge coating rust defect recognition method based on color and texture feature. Automation in Construction, 31, 338-356.
https://doi.org/10.1016/j.autcon.2012.11.00334. Xu, Y., Bao, Y., Chen, J., Zuo, W., Li, H. (2018) Surface fatigue crack identification in steel box girder of bridges by a deep fusion convolutional neural network based on consumergrade camera images. Structural Health Monitoring, 18(3), 653-674.
https://doi.org/10.1177/147592171876487335. Prasanna, P., Dana, K.J., Gucunski, N. et al. (2016) Automated crack detection on concrete bridges. IEEE Transactions on Automation Science and Engineering, 13(2), 591-599.
https://doi.org/10.1109/TASE.2014.235431436. An, Y.-K., Jang, K.-Y., Kim, B., Cho, S. (2018) Deeplearningbased concrete crack detection using hybrid images. In: Proc. SPIE 10598, Sensors and Smart Structures Technologies for Civil, Mechanical, and Aerospace Systems, 1059812.
https://doi.org/10.1117/12.229495937. Chow, J.K., Su, Z., Wu, J., Tan, P.S. et al. (2020) Anomaly detection of defects on concrete structures with the convolutional autoencoder. Advanced Engineering Informatics, 45, 101105.
https://doi.org/10.1016/j.aei.2020.10110538. Miranda, J., Veith, J., Larnierc, S., Herbulot, A., Devya, M. (2019) Machine learning approaches for defect classification on aircraft fuselage images acquired by an UAV. In: Fourteenth International Conference on Quality Control by Artificial Vision, Vol. 11172, 1117208.
https://doi.org/10.1117/12.252056739. Avdelidis, N.P., Tsourdos, A., Lafiosca, P., Plaster, R., Plaster, A., Droznika, M. (2022) Defects recognition algorithm development from visual UAV inspections. Sensors, 22(13), 4682.
https://doi.org/10.3390/s2213468240. Ronneberger, O., Fischer, P., Brox, T. (2015) U-net: convolutional networks for biomedical image segmentation. In: Proceedings of the Medical Image Computing and Computer-Assisted Intervention (MICCAI 2015), 234-241.
https://doi.org/10.1007/978-3-319-24574-4_2841. Ren, J., Wang, H. (2023) Calculus and optimization. In: Mathematical Methods in Data Science, Chapter 3. Elsevier, pp. 51-89.
https://doi.org/10.1016/B978-0-44-318679-0.00009-0
Advertising in this issue: