Researchers from the Universidad Autónoma de Nuevo León in Mexico have proposed a new method for detecting faults in wind turbine blades using computational learning techniques. The study, published in the journal Energy Reports, evaluates two models to identify fault-related patterns and improve system reliability in wind energy infrastructure.
The first model employs logistic regression, which outperformed other methods like neural networks, decision trees, and the naive Bayes method. This indicates that logistic regression is effective in identifying fault-related patterns in wind turbine blades. The second model leverages clustering, a type of unsupervised learning, and achieves superior performance in terms of precision and data segmentation. The results suggest that clustering may better capture the underlying data characteristics compared to supervised methods.
The proposed methodology offers a new approach to early fault detection in wind turbine blades. Early detection of faults can lead to timely maintenance, reducing downtime and increasing the overall efficiency of wind turbines. The use of accessible tools like Orange Data Mining underscores the practical application of these advanced solutions within the wind energy sector.
Future work will focus on combining these methods to improve detection accuracy further. The researchers also aim to extend the application of these techniques to other critical components in energy infrastructure, potentially benefiting the broader energy sector. This research highlights the potential of integrating different computational learning techniques to enhance system reliability and efficiency in the wind energy industry.
This article is based on research available at arXiv.