Operation and maintenance (O&M) activities represent a significant share of the total expenditure of a wind farm. Of these expenses, costs associated with unexpected failures account for the highest percentage. Therefore, it is clear that early detection of wind turbine (WT) failures, which can be achieved through appropriate condition monitoring (CM), is critical to reduce O&M costs. The use of Supervisory Control and Data Acquisition (SCADA) data has recently been recognized as an effective solution for CM since most modern WTs record large amounts of parameters using their SCADA systems. Artificial intelligence (AI) techniques can convert SCADA data into information that can be used for early detection of WT failures. This work presents a systematic literature review (SLR) with the aim to assess the use of SCADA data and AI for CM of WTs. To this end, we formulated four research questions as follows: (i) What are the current challenges of WT CM? (ii) What are the WT components to which CM has been applied? (iii) What are the SCADA variables used? and (iv) What AI techniques are currently under research? Further to answering the research questions, we identify the lack of accessible WT SCADA data towards research and the need for its standardization. Our SLR was developed by reviewing more than 95 scientific articles published in the last three years.

The growth of installed wind power worldwide and its significant contribution to the energy market is mainly due to the evolution of wind turbines (WTs) and their ability to withstand a wide range of dynamic loads. WT failures can be costly and lead to extended downtime. Early detection of such failures is critical in reducing the costs associated with operation and maintenance (O&M) tasks and unscheduled shutdowns of WTs. This paper applies two Deep Learning (DL) models based on the Transformer model to predict failures in the IGBT module of WTs at an onshore wind farm in Ecuador. To this end, SCADA (Supervisory Control and Data Acquisition) operational and alarm data are used, together with the maintenance record (MR). These data are analyzed and processed, applying different feature selection methods. The results show that the two proposed models perform well, with high accuracy and an approximate prediction of 4.25 months before failure occurrence. The results are promising due to the possibility of using SCADA data for early and accurate identification of faults in different components of WTs.