Wind Turbine Remaining Useful Life Prediction Using Small Dataset and Machine Learning Techniques

Recently, there has been a global shift toward clean energy sources, and wind turbines (WT) play a crucial role as one of the most popular renewable generation sources. Despite their significant potential, WTs incur high operation and maintenance (O &M) costs due to the challenging operational conditions they face, such as pollution and atmospheric discharges. These stresses reduce the life expectancy of such equipment by increasing the occurrence of failures, thereby diminishing wind farm reliability. To mitigate these failure events, the prediction of the remaining useful life (RUL) of WTs is essential. This prediction, specifically direct RUL prediction, is often made by data-driven methods. However, to achieve competitive levels of accuracy, data-driven methods found in the literature often rely on extensive datasets or high-complexity deep learning models, because historical data containing failures in WTs are scarce, which presents challenges in practical implementation. This paper introduces a novel methodology for rotor RUL prediction in WTs. This method achieved an accuracy of over 80 % using simple machine learning algorithms trained with limited data, making it easy to implement and cost-effective. It is expected that this methodology will assist energy companies in optimizing their operation and maintenance planning processes and contribute to the national energy sector’s progress toward achieving global sustainable goals.