VHDL-Implemented Neuro-Fuzzy Cascade for Renewable Energy Defect Classification
DOI:
https://doi.org/10.47839/ijc.25.2.4663Keywords:
renewable energy facilities, defect classification, neuro-fuzzy system, cascade architecture, SqueezeNet; Hypersector Fuzzy LVQ, Fuzzy BSB, Wang–Mendel network, FPGA, real-time monitoringAbstract
This paper presents a hardware-oriented neuro-fuzzy cascade for the real-time classification of wind turbine blade defects. A modified SqueezeNet model generates an informative feature vector, which is processed by Hypersector Fuzzy LVQ, Fuzzy BSB, and a modified Wang–Mendel classifier. Hypersector Fuzzy LVQ performs primary classification, whereas the switching logic evaluates the confidence margin and a hardware-efficient feature-variability indicator to select an auxiliary classifier for uncertain samples. The complete classifiers are trained offline, while their compact inference representations and switching logic are implemented in VHDL. Functional verification in Active-HDL demonstrated correct sample-dependent routing and synchronous decision generation. On the test subset, the cascade correctly classified samples, corresponding to an accuracy of 98.33%. The proposed architecture provides low decision latency after CNN feature extraction and can serve as a basis for embedded defect-monitoring systems. Its current limitations include empirical threshold selection, a relatively small test subset, and the absence of physical FPGA synthesis.
References
“Solar panel clean and faulty images,” Kaggle Dataset, [Online]. Available at: https://www.kaggle.com/datasets/pythonafroz/solar-panel-clean-and-faulty-images.
“Wind Turbine YOLOv8 Training,” Kaggle Notebook, [Online]. Available at: https://www.kaggle.com/code/hunhcgiatn/wind-turbine-yolov8-training?select=NordTank586x371.
B. Altice, E. Nazario, M. Davis, M. Shekaramiz, T.K. Moon, M.A.S. Masoum, “Anomaly detection on small wind turbine blades using deep learning algorithms,” Energies, vol. 17, issue 5, article 982, 2024. https://doi.org/10.3390/en17050982.
M. Davis, M. Shekaramiz, M.A.S. Masoum, A. Seibi, “Identification and localization of wind turbine blade defects using YOLO and Mask R-CNN,” Applied Sciences, vol. 14, issue 14, article 6319, 2024. https://doi.org/10.3390/app14146319.
M. Memari, M. Shekaramiz, M.A.S. Masoum, A.C. Seibi, “Data fusion and ensemble learning for advanced anomaly detection using multi-spectral RGB and thermal imaging of small wind turbine blades,” Energies, vol. 17, issue 3, article 673, 2024. https://doi.org/10.3390/en17030673.
A. Rahman, “Solar panel surface defect and dust detection: Deep learning approach,” Journal of Imaging, vol. 11, issue 9, article 287, 2025. https://doi.org/10.3390/jimaging11090287.
A. Karakan, “Detection of defective solar panel cells in electroluminescence images using deep learning,” Sustainability, vol. 17, issue 3, article 1141, 2025. https://doi.org/10.3390/su17031141.
D. Dwivedi, K.V.S.M. Babu, P.K. Yemula, P. Chakraborty, M. Pal, “Identification of surface defects on solar PV panels and wind turbine blades using attention-based deep learning model,” Engineering Applications of Artificial Intelligence, vol. 131, article 107836, 2024. https://doi.org/10.1016/j.engappai.2023.107836.
W. Yaïci, E. Entchev, “Adaptive Neuro-Fuzzy Inference System modelling for performance prediction of solar thermal energy system,” Renewable Energy, vol. 86, pp. 302–315, 2016, https://doi.org/10.1016/j.renene.2015.08.028.
V. Mukhin, V.Zavgorodnii, V.Liskin, et al. “A model for classifying information objects using neural networks and fuzzy logic”. Sci Rep, vol. 15, 15904, 2025. https://doi.org/10.1038/s41598-025-00897-4.
R. Pratt, A. Clark, M.A.S. Masoum, A. Seibi, “Defect detection and classification on wind turbine blades using deep learning with fuzzy voting,” Machines, vol. 13, issue 4, article 283, 2025. https://doi.org/10.3390/machines13040283.
L. Dubchak, “Adaptive cascade bagging of neuro-fuzzy models for the classification of defects in renewable energy facilities,” Advances in Cyber-Physical Systems, vol. 11, issue 1, pp. 26–32, 2026. https://doi.org/10.23939/acps2026.01.026.
E. Lughofer, “Evolving fuzzy and neuro-fuzzy systems: Fundamentals, stability, explainability, useability, and applications,” in: Handbook on Computer Learning and Intelligence, World Scientific, Singapore, 2022, pp. 133–234. doi: 10.1142/9789811247323_0004.
F. M. Siraj, S. T. K. Ayon, M. A. Samad, J. Uddin, K. Choi, “Few-shot lightweight SqueezeNet architecture for induction motor fault diagnosis using limited thermal image dataset,” IEEE Access, vol. 12, pp. 50986–50997, 2024, https://doi.org/10.1109/ACCESS.2024.3385430.
L.-X. Wang, J.M. Mendel, “Generating fuzzy rules by learning from examples,” IEEE Transactions on Systems, Man, and Cybernetics, vol. 22, issue 6, pp. 1414–1427, 1992. https://doi.org/10.1109/21.199466.
A. Hichri et al., “Genetic-algorithm-based neural network for fault detection and diagnosis: Application to grid-connected photovoltaic systems,” Sustainability, vol. 14, issue 17, article 10518, 2022. https://doi.org/10.3390/su141710518.
A. Eskandari, M. Aghaei, J. Milimonfared, A. Nedaei, “A weighted ensemble learning-based autonomous fault diagnosis method for photovoltaic systems using genetic algorithm,” International Journal of Electrical Power & Energy Systems, vol. 144, article 108591, 2023. https://doi.org/10.1016/j.ijepes.2022.108591.
M. Mansouri, K. Dhibi, H. Nounou, M. Nounou, “An effective fault diagnosis technique for wind energy conversion systems based on an improved particle swarm optimization,” Sustainability, vol. 14, issue 18, article 11195, 2022. https://doi.org/10.3390/su141811195.
A. Sabati, R. Bayindir, J. Rahebi, “Photovoltaic panels fault detection with convolutional neural network and Bitterling Fish Optimization (BFO) algorithm,” International Journal of Computational Intelligence Systems, vol. 18, article 239, 2025. https://doi.org/10.1007/s44196-025-00984-4.
L. Dubchak, Y. Bodyanskiy, O. Savenko, V. Kochan, A. Sachenko, “Intelligent system for real-time detection and classification of solar panel defects,” Radioelectronic and Computer Systems, issue 3(115), pp. 111–121, 2025. https://doi.org/10.32620/reks.2025.3.08.
L. Dubchak, B. Rusyn, C. Wolff, T. Ciszewski, A. Sachenko, Y. Bodyanskiy, “Hypersector-based method for real-time classification of wind turbine blade defects,” Energies, vol. 19, issue 2, article 442, 2026. https://doi.org/10.3390/en19020442.
O. Kilincceker, E. Turk, F. Belli, M. Challenger, “Model-based ideal testing of hardware description language programs,” Software and Systems Modeling, vol. 21, pp. 1209–1240, 2022. https://doi.org/10.1007/s10270-021-00934-6.
B. Koonce, ResNet 50, in: Convolutional Neural Networks with Swift for TensorFlow, Apress, Berkeley, 2021. https://doi.org/10.1007/978-1-4842-6168-2_6.
B. Koonce, EfficientNet, in: Convolutional Neural Networks with Swift for TensorFlow, Apress, Berkeley, 2021. https://doi.org/10.1007/978-1-4842-6168-2_10.
P. Jiang, D. Ergu, F. Liu, Y. Cai, B. Ma, “A review of YOLO algorithm developments,” Procedia Computer Science, vol. 199, pp. 1066–1073, 2022. https://doi.org/10.1016/j.procs.2022.01.135.
J. Terven, D.-M. Córdova-Esparza, J.-A. Romero-González, “A comprehensive review of YOLO architectures in computer vision: From YOLOv1 to YOLOv8 and YOLO-NAS,” Machine Learning and Knowledge Extraction, vol. 5, issue 4, pp. 1680–1716, 2023. https://doi.org/10.3390/make5040083.
M. Hussain, “YOLO-v1 to YOLO-v8, the rise of YOLO and its complementary nature toward digital manufacturing and industrial defect detection,” Machines, vol. 11, issue 7, article 677, 2023. https://doi.org/10.3390/machines11070677.
X. Bi, J. Hu, B. Xiao, W. Li, X. Gao, “IEMask R-CNN: Information-enhanced Mask R-CNN,” IEEE Transactions on Big Data, vol. 9, issue 2, pp. 688–700, 2023. https://doi.org/10.1109/TBDATA.2022.31874133.
D. Cock, A. Ramdas, D. Schwyn, M. Giardino, A. Turowski, Z. He, N. Hossle, D. Korolija, M. Licciardello, K. Martsenko, R. Achermann, G. Alonso, T. Roscoe, “Enzian: An open, general, CPU/FPGA platform for systems software research,” Proceedings of the 27th ACM International Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS”‘22), Lausanne, Switzerland, February 28–March 4, 2022, pp. 434–451. https://doi.org/10.1145/3503222.3507742.
R. Neris, A. Rodríguez, R. Guerra, S. López, R. Sarmiento, “FPGA-based implementation of a CNN architecture for the on-board processing of very high-resolution remote sensing images,” IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, vol. 15, pp. 3740–3750, 2022, https://doi.org/10.1109/JSTARS.2022.3169330.
S. S. Lingala, S. Bedekar, P. Tyagi, P. Saha, P. Shahane, “FPGA based implementation of neural network,” Proceedings of the 2022 International Conference on Advances in Computing, Communication and Applied Informatics (ACCAI), Chennai, India, 2022, pp. 1–5, https://doi.org/10.1109/ACCAI53970.2022.9752656.
M. Brenner, N.H. Reyes, T. Susnjak, A.L.C. Barczak, “RGB-D and thermal sensor fusion: A systematic literature review,” IEEE Access, vol. 11, pp. 82410–82442, 2023. https://doi.org/10.1109/ACCESS.2023.3301119.
Y. Wang, H.K. Chu, Y. Sun, “PEAFusion: Parameter-efficient adaptation for RGB-thermal fusion-based semantic segmentation,” Information Fusion, vol. 120, article 103030, 2025. https://doi.org/10.1016/j.inffus.2025.103030.
W. Zhou, S. Dong, C. Xu, Y. Qian, “Edge-aware guidance fusion network for RGB-thermal scene parsing,” Proceedings of the AAAI Conference on Artificial Intelligence, vol. 36, issue 3, pp. 3571–3579, 2022. https://doi.org/10.1609/aaai.v36i3.20269.
Downloads
Published
How to Cite
Issue
Section
License
International Journal of Computing is an open access journal. Authors who publish with this journal agree to the following terms:• Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
• Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
• Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work.
