Fault Identification in Wind Turbines: A Machine Learning Approach
Abstract
The last few years have been marked by the insertion of renewable technologies in the global energy matrix, such as wind and solar energy, considered clean energies with low environmental impact. Wind turbines, responsible for the energy conversion process, are complex, high-cost equipment and susceptible to numerous failures. Monitoring turbine components can help detect failures before they occur, reducing equipment maintenance costs. This work compares data-centric machine-learning techniques in fault detection in wind turbines. Results show the importance of data selection and optimization in the problem context.
Keywords:
fault detection, wind turbine, PCA, SVM, logistic regression, decision tree, KNN
References
ABEEólica (2022). Abeeólica - Associação Brasileira de Energia Eólica. https://abeeolica.org.br/, last accessed on 01/05/22.
Blanco, M. A. et al. (2017). Impact of target variable distribution type over the regression analysis in wind turbine data. IWOBI 2017 - Proceedings.
EDP (2021). EDP - Open Data. https://opendata.edp.com/pages/homepage/, last accessed on 15/08/21.
Garan, M. et al. (2022). A data-centric machine learning methodology: Application on predictive maintenance of wind turbines. Energies, 15:826.
Japa, L. et al. (2023). A population-based hybrid approach for hyperparameter optimization of neural networks. IEEE Access, 11:50752–50768.
Mendes, M. et al. (2020). Wind farm and resource datasets: A comprehensive survey and overview. Energies, 13.
Pandit, R. et al. (2023). Scada data for wind turbine data-driven condition/performance monitoring: A review on state-of-art, challenges and future trends. Wind Engineering, 47(2):422–441.
Qin, S. et al. (2017). Ensemble learning-based wind turbine fault prediction method with adaptive feature selection. Comm. in Computer and Information Science, 728.
Soper, D. S. (2023). Hyperparameter optimization using successive halving with greedy cross validation. Algorithms, 16(1).
Stetco, A. et al. (2019). Machine learning methods for wind turbine condition monitoring: A review. Renewable energy, 133:620–635.
Blanco, M. A. et al. (2017). Impact of target variable distribution type over the regression analysis in wind turbine data. IWOBI 2017 - Proceedings.
EDP (2021). EDP - Open Data. https://opendata.edp.com/pages/homepage/, last accessed on 15/08/21.
Garan, M. et al. (2022). A data-centric machine learning methodology: Application on predictive maintenance of wind turbines. Energies, 15:826.
Japa, L. et al. (2023). A population-based hybrid approach for hyperparameter optimization of neural networks. IEEE Access, 11:50752–50768.
Mendes, M. et al. (2020). Wind farm and resource datasets: A comprehensive survey and overview. Energies, 13.
Pandit, R. et al. (2023). Scada data for wind turbine data-driven condition/performance monitoring: A review on state-of-art, challenges and future trends. Wind Engineering, 47(2):422–441.
Qin, S. et al. (2017). Ensemble learning-based wind turbine fault prediction method with adaptive feature selection. Comm. in Computer and Information Science, 728.
Soper, D. S. (2023). Hyperparameter optimization using successive halving with greedy cross validation. Algorithms, 16(1).
Stetco, A. et al. (2019). Machine learning methods for wind turbine condition monitoring: A review. Renewable energy, 133:620–635.
Published
2023-09-25
How to Cite
PINNA, Danielle R.; TOSO, Rodrigo F.; BELLOZE, Kele; DE SÁ, Fernando; GUERRA, Raphael; BRANDÃO, Diego N..
Fault Identification in Wind Turbines: A Machine Learning Approach. In: BRAZILIAN SYMPOSIUM ON DATABASES (SBBD), 38. , 2023, Belo Horizonte/MG.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2023
.
p. 439-444.
ISSN 2763-8979.
DOI: https://doi.org/10.5753/sbbd.2023.232700.
