Hydraulic fault detection of wind turbine generators using artificial neural networks

Year 2024, Volume: 8 Issue: 4, 331 - 340, 20.12.2024

Tacettin Ahmet Döndüren , Mustafa Yağcı

https://doi.org/10.26701/ems.1577643

Abstract

In the current context where fossil resources are diminishing globally, and carbon emissions are increasing daily, the importance of green energy, particularly wind energy, is growing significantly. The increasing of wind turbines will not only reduce the carbon footprint but also decrease dependence on external resources. To increase the installed capacity of wind turbines, it is crucial to reduce not only installation costs but also operational costs. The largest proportion of operational costs is service, and maintenance costs. One of the most critical approaches to reducing service, and maintenance costs is preventive maintenance activities. The objective of preventive maintenance activities is to minimize or ideally eliminate production losses through scheduled turbine shutdowns before failures occur. In this study, artificial neural network-based algorithms that predict potential hydraulic failures during the operational period were utilized. For this purpose, data from the turbine SCADA system over a period of two years, considering the equipment, and sensors connected to hydraulic systems, were compiled. The study was conducted using the WEKA program, comparing Multilayer Perceptron (MLP), Radial Basis Function Classifier (RBF Classifier), SMOreg (Support Vector Machines for Regression) algorithms. Result of the study, the MLP algorithm was applied with a percentage split of 66% for training, and 33% for testing, achieving a prediction accuracy of 96.32%

Keywords

ARTIFICIAL NEURAL NETWORKS, WIND TURBINE GENERATORS, FAULT DETECTION, Predictive Maintenance

Ethical Statement

Ethical approval not required.

Supporting Institution

Necmettin Erbakan University Scientific Research Projects Coordinatorship

Project Number

23YL19008.

Thanks

Necmettin Erbakan Üniversitesi BAP koordinatörlüğüne teşekkür ederiz.

References

• Tang, M., Zhao, Q., Wu, H., Wang, Z., Meng, C., & Wang, Y. (2021). Review and perspectives of machine learning methods for wind turbine fault diagnosis. Frontiers in Energy Research, 9. https://doi.org/10.3389/fenrg.2021.751066
• Zhang, F., Chen, M., Zhu, Y., Zhang, K., & Li, Q. (2023). A review of fault diagnosis, status prediction, and evaluation technology for wind turbines. Energies, 16(3). https://doi.org/10.3390/en16031125
• Tezer, D. (2024). Comparison of classification success of artificial neural network factor analysis Hybrit model and artificial neural network models (Doctoral dissertation). Osmangazi University.
• Korkmaz, E. (2022). Analysis of solar radiation with artificial neural networks and machine learning: Example of Bursa and Çanakkale (Master’s thesis). Onyedi Eylul University.
• Sarıkaya, T. A. (2023). FPGA based artificial neural network motor control of PM assisted synchronous reluctance motor in washers (Master’s thesis). Istanbul Technical University.
• Yüksel, F. Ş. (2023). Estimation of passenger demand in Turkey according to airline carrier models using multiple linear regression, ANFIS and YSA techniques (Doctoral dissertation). Cukurova University.
• Geçmez, A. (2022). Estimation of production values in solar and wind power plants with artificial intelligence methods based on climate parameters and production estimation by developing solar energy feasibility software (Doctoral dissertation). Fırat University.
• Kiriş, Z. N. (2021). Wind speed load forecasting models and an application in Yalova (Master’s thesis). Istanbul Technical University.
• Shakiba, F. M. (2022). Artificial neural networks and their applications to intelligent fault diagnosis of power transmission lines (Order No. 28971262) [Doctoral dissertation, ProQuest Dissertations & Theses Global].
• Zhang, Y., Liu, Q., Liu, W., & Zheng, W. (2022). Deployable lightweight ANN-based approach for wind turbine fault detection. In Proceedings of the 13th International Conference on Reliability, Maintainability, and Safety: Reliability and Safety of Intelligent Systems (pp. 28–34). https://doi.org/10.1109/ICRMS55680.2022.9944585
• Bangalore, P., & Tjernberg, L. B. (2015). An artificial neural network approach for early fault detection of gearbox bearings. IEEE Transactions on Smart Grid, 6(2), 980–987. https://doi.org/10.1109/TSG.2014.2386305
• Samawi, V. W., Yousif, S. A., & Al-Saidi, N. M. G. (2022). Intrusion detection system: An automatic machine learning algorithms using Auto-WEKA. In Proceedings of the 2022 IEEE 13th Control and System Graduate Research Colloquium (pp. 42–46). https://doi.org/10.1109/ICSGRC55096.2022.9845166
• Işık, M. A. (2024). Ranking of machine learning algorithms used to detect bug-containing software modules with multi-criteria decision making methods (Master’s thesis). Baskent University.
• Syahrini, Z., Priyadi, Y., & Herdiani, A. (2023). Validity of cosine similarity measurement of functional requirements and steps performed using Cohen Kappa on SRS scenery artifacts. In Proceedings of the International Conference on Electrical Engineering, Computer Science and Informatics (pp. 631–636). https://doi.org/10.1109/EECSI59885.2023.10295586
• Femi, D., & Thylashri, S. (2022). Human voice emotion recognition using multilayer perceptron. In Proceedings of the 2022 International Conference on Innovative Computing, Intelligent Communication and Smart Electrical Systems (pp. 1–6). https://doi.org/10.1109/ICSES55317.2022.9914335
• Aryan, B.K., Sobhana, O., Prabhakar, G.C., & Reddy, N.A.(2022). Fault detection and classification in micro grid using AI technique.In Proceedings - 2022 International Conference on Recent Trends in Microelectronics Automation Computing and Communications Systems (pp517-522) https://doi.org/10..1109/ICMACC54824..10093359
• Fu, X., & Wang, L. (2003). Data Dimensionality Reduction with Application to Simplifying RBF Network Structure and Improving Classification Performance. IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics, 33(3), 399–409. https://doi.org/10.1109/TSMCB.2003.810911