The work solves the problem of increasing the accuracy and efficiency of the classification of defects in renewable energy facilities under conditions of limited computing resources and uncertainty of input data. An adaptive intelligent system based on cascade bagging of neuro-fuzzy models has been proposed, which combines the hypersector Fuzzy LVQ method, the associative FBSB model and the modified Wang–Mendel method. The formation of the feature space has been carried out by constructing a compact four-dimensional vector that corresponds to the main classes of defects and provides a reduction in computational costs while maintaining resolution. An adaptive mechanism for determining weight coefficients between cascades has been developed, which allows taking into account the current quality of classification and increasing the consistency of solutions of individual modules. Experimental studies performed in the Active-HDL environment have confirmed the operability of the system in real time with a latency of one clock cycle. According to the results of testing on a sample of 60 examples, a classification accuracy of 98% has been achieved. It has been shown that the proposed approach provides high resilience to uncertainty, effective integration of classification results, and low resource costs, which makes it promising for application in embedded monitoring systems.
[1] Song, X., Xing, Z., Jia, Y., Song, X., Cai, C., Zhang, Y., Wang, Z., Guo, J., & Li, Q. (2022). Review on the Damage and Fault Diagnosis of Wind Turbine Blades in the Germination Stage. Energies, 15(20), 7492. DOI: https://doi.org/10.3390/en15207492
[2] Ying Du, Shengxi Zhou, Xingjian Jing, Yeping Peng, Hongkun Wu, Ngaiming Kwok (2020). Damage detection techniques for wind turbine blades: A review. Mechanical Systems and Signal Processing, V.144, 106445. DOI: https://doi.org/10.1016/j.ymssp.2019.106445
[3] Barbosa, N. B., Nunes, D. D. G., Santos, A. Á. B., & Machado, B. A. S. (2023). Technological Advances on Fault Diagnosis in Wind Turbines: A Patent Analysis. Applied Sciences, 13(3), 1721. DOI: https://doi.org/10.3390/app13031721
[4] Sun, H., Dong, J., Liu, H., Shi, W., Feng, Q., Yao, K., Huang, S., Peng, L., & Cai, Z. (2025). Review of Non-Destructive Testing for Wind Turbine Bolts. Sensors, 25(18), 5726. DOI: https://doi.org/10.3390/s25185726
[5] Mardanshahi, A., Sreekumar, A., Yang, X., Barman, S. K., & Chronopoulos, D. (2025). Sensing Techniques for Structural Health Monitoring: A State-of-the-Art Review on Performance Criteria and New-Generation Technologies. Sensors, 25(5), 1424. DOI: https://doi.org/10.3390/s25051424
[6] Lu, B., Li, Y., Wu, X. & Yang, Z. (2009). A review of recent advances in wind turbine condition monitoring and fault diagnosis. IEEE Power Electronics and Machines in Wind Applications, Lincoln, NE, USA, pp. 1-7, DOI: 10.1109/PEMWA.2009.5208325
[7] Ding, S., Yang, C., & Zhang, S. (2023). Acoustic-Signal-Based Damage Detection of Wind Turbine Blades—A Review. Sensors, 23(11), 4987. DOI: https://doi.org/10.3390/s23114987
[8] Nguyen Quoc, T. M., Nguyen, C. P., Nguyen, T. K., Tran, V. D. & Nguyen, X. T. (2024). Fault detection in wind turbine based on machine learning, J. Mil. Sci. Technol., 94, no. 94, pp. 3–10. DOI: https://doi.org/10.54939/1859-1043.j.mst.94.2024.3-10
[9] Shafiq, M., & Gu, Z. (2022). Deep Residual Learning for Image Recognition: A Survey. Applied Sciences, 12(18), 8972. DOI: https://doi.org/10.3390/app12188972 [10] Chai, J., Zeng, H., Li, A., & Ngai, E. W. (2021). Deep learning in computer vision: A critical review of emerging techniques and application scenarios. Machine Learning with Applications, 6, 100134. https://doi.org/10.1016/j.mlwa.2021.100134.
[11] Qureshi, S. A., Rehman, A. & Khan, A. A. (2025). SqueezeNet: A Lightweight CNN Architecture Deep Learning with Fewer Parameters. DOI: https://doi.org/10.13140/RG.2.2.16403.95521.
[12] Iyavoo, A., Armoogum, V., & Sunhaloo, S. (2024, June). Performance Analysis of Deep Learning's CNN Architectures for Internet of Vehicles Classification. In 2024 1st International Conference on Smart Energy Systems and Artificial Intelligence (SESAI) (pp. 1-6). IEEE. DOI: https://doi.org/10.1109/SESAI61023.2024.10599455.
[13] Ganaie, M. A., Hu, M., Malik, A. K., Tanveer, M., & Suganthan, P. N. (2022). Ensemble deep learning: A review. Engineering applications of artificial intelligence, 115, 105151. DOI: https://doi.org/10.1016/j.engappai.2022.105151
[14] Kim, M. J., Lee, H. M., Jeong, Y., & Kwak, J. Y. (2025). Spiking Neural Network-Based Bidirectional Associative Learning Circuit for Efficient Multibit Pattern Recall in Neuromorphic Systems. Electronics, 14(19), 3971. DOI: https://doi.org/10.3390/electronics14193971
[15] Ahmad, I., Yousaf, M., Yousaf, S., & Ahmad, M. O. (2020). Fake news detection using machine learning ensemble methods. Complexity, 2020(1), 8885861. DOI: https://doi.org/10.1155/2020/8885861
[16] Lughofer, E., Pratama, M., & Škrjanc, I. (2021). Online bagging of evolving fuzzy systems. Information Sciences, 570, 16–33. DOI: https://doi.org/10.1016/j.ins.2021.04.041
[17] Gunasekara, N., Pfahringer, B., Gomes, H.M. et al (2025). Gradient boosted bagging for evolving data stream regression. Data Min Knowl Disc 39, 65. DOI: https://doi.org/10.1007/s10618-025-01147-x
[18] Golenko, M. Yu., Ivanov, D. A., Yefimenko, A. A., & Vorotnikov, V. V. (2023). Analysis of object recognition and image compression methods during aerial photography from unmanned aerial vehicles. Technical Engineering, (1(91), 146–155. DOI: https://doi.org/10.26642/ten-2023-1(91)-146-155 (in Ukrainian)
[19] Arsiriy, O. O., & Holovatyuk, M. Y. (2025). Analysis of intelligent video surveillance methods. Informatics. Culture. Technology, 2, 154–159. DOI: https://doi.org/10.15276/ict.02.2025.22
[20] Muravyov, O. V., et al. (2023). UAV autonomy development prospects. Scientific Notes of TNU, 34(2), 199–205. DOI: https://doi.org/10.32782/2663-5941/2023.2.1/32 (in Ukrainian)
[21] Dorozhko, Y., Sytnyk, O., & Kravchuk, M. (2025). Use of unmanned aerial vehicles (UAVs) for high-precision geodesic surveying. Spatial Development, (11), 597–610. DOI: https://doi.org/10.32347/2786-7269.2025.11.597-610
[22] Gunasekara, N., Pfahringer, B., Gomes, H. M., & Bifet, A. (2025). Gradient boosted bagging for evolving data stream regression. Data Mining and Knowledge Discovery, 39, 65. DOI: https://doi.org/10.1007/s10618-025-01147-x
[23] Lee, J., et al. (2022). Integrated MEMS IMU for UAV navigation. Journal of Microelectromechanical Systems, 31, 456–467. DOI: https://doi.org/10.1109/JMEMS.2022.3157685
[24] Bodyanskiy, Y., Kuzmenko, O., Zaichenko, H., & Zaychenko, Y. (2024). Hybrid system of computational intelligence based on bagging and group method of data handling. System Research and Information Technologies, 1, Article 06. DOI: https://doi.org/10.20535/SRIT.2308-8893.2024.1.06
[25] Dubchak, L., Rusyn, B., Wolff, C., Ciszewski, T., Sachenko, A., & Bodyanskiy, Y. (2026). Hypersector-based method for real-time classification of wind turbine blade defects. Energies, 19, 442. DOI: https://doi.org/10.3390/en19020442
[26] Dubchak, L., Bodyanskiy, Y., Savenko, O., Kochan, V., & Sachenko, A. (2025). Intelligent system for real-time detection of solar panel defects. Radioelectronic and Computer Systems, 3(115), 111–121. DOI: https://doi.org/10.32620/reks.2025.3.08
[27] Dubchak, L., Bodyanskiy, Y., Sachenko, A., Wolff, C., Vivchar, N., & Vasylkiv, N. (2025). Modified neuro-fuzzy system for online classification of wind turbine blade defects. IEEE Access, 13, 166841–166852. DOI: https://doi.org/10.1109/ACCESS.2025.3612267