A Review of machine learning techniques for wind turbine's fault detection, diagnosis, and prognosis

Abstract

Wind turbines are becoming increasingly important in the generation of clean, renewable energy worldwide. To ensure their dependable and accessible operation, advanced real-time condition monitoring technology must be implemented to guarantee efficient wind power generation and financial viability. Machine learning (ML) has emerged as a crucial technique for condition monitoring in wind power systems in recent years. This is especially relevant because dedicated condition monitoring systems, primarily focused on vibration measurements, are prohibitively expensive. Preventive maintenance is the most effective way to detect and address issues before they impact performance. This article provides a comprehensive and up-to-date review of the latest condition monitoring technologies for fault detection, diagnosis, and prognosis in wind turbines, with a particular focus on ML algorithms for critical faults and failure modes, preprocessing methods, and evaluation metrics. Numerous references have been analyzed to evaluate past, present, and potential future research and development trends in this field. Most of these references are based on recent journal articles, theses, and reports found in the open literature.