Data-Driven Predictive Maintenance of Wind Turbine Based on SCADA Data

• Published in: IEEE access Vol. 9; pp. 162370 - 162388
• Main Authors: Udo, Wisdom, Muhammad, Yar
• Format: Journal Article
• Language: English
• Published: Piscataway IEEE 2021; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Anomalies; Critical components; Data analysis; Data collection; extreme gradient boosting (XGBoost); fault detection; Gearboxes; Generators; long short-term memory (LSTM); Maintenance costs; Maintenance engineering; Monitoring; Offshore; Offshore energy sources; Optimization; Predictive maintenance; Process controls; Sensor systems; Sensors; Statistical process control; statistical process control (SPC); Supervisory control and data acquisition; supervisory control and data acquisition (SCADA); Wind farms; Wind power; Wind turbine; Wind turbines
• ISSN: 2169-3536; 2169-3536
• DOI: 10.1109/ACCESS.2021.3132684

Rystad Energy's analysis shows that installed offshore wind capacity will rise to 27.5 GW in 2026 from 10.5 GW in 2020. This report indicates that increasingly complex maintenance needs must be met for wind turbines(WTs). IRENA report shows that offshore wind operation and maintenance (O&M) costs typically constitute 16-25% of the cost of electricity for offshore wind farms deployed in the G20 countries. Data collection and analytics, predictive maintenance, and production output optimisation of WTs must be explored to increase operational reliability and reduce maintenance costs of WTs. Predictive maintenance in wind turbines can be achieved by analysing data obtained by sensors already equipped with the WT. This network of sensors forms part of a Supervisory Control and Data Acquisition (SCADA) system. We developed a method for monitoring and detecting anomalies in the WT critical components, such as the gearbox and the generator. The proposed approach is based on the historical SCADA data that is common in most wind farms. We developed models using extreme gradient boosting (XGBoost) and Long Short-Term Memory (LSTM) to build the characteristics behaviour of critical WT components, and Statistical Process Control (SPC) was used to evaluate its anomalous behaviour. The proposed method was tested on two real case studies regarding six different WT to determine its effectiveness and applicability.