Wind turbines generate a wealth of data which can be effectively used to improve maintenance strategies and drive down operations and maintenance (O&M) costs, which account for 20-25% of the cost of generation of wind energy. Data-driven techniques for enabling prognostic and health management (PHM) technologies have seen many successes in the space. However, managing this data, particularly in the context of an
industrial facility which may have many other data streams, is a challenge. This technical brief describes the schematic of a proposed system for managing turbine data, ahead of an implementation which will see PHM techniques applied to it. The turbine in this case is attached to a manufacturing facility, so the pipeline is designed to be modular and integrate well with an existing pipeline at that facility.
PHM, Wind Turbines, data ingestion
Godwin, J. L., & Matthews, P. (2013). Classification and Detection of Wind Turbine Pitch Faults Through SCADA Data Analysis. International Journal of Prognostics and Health Management, 4, 11.
Hahn, B. (2017). Recommended Practice 17: WIND FARM DATA COLLECTION AND RELIABILITY ASSESSMENT FOR O&M OPTIMIZATION (Tech. Rep.
No. May). IEA Wind.
International Renewable Energy Agency. (2018). Renewable Power Generation Costs in 2017 (Tech. Rep.).
Leahy, K., Gallagher, C., O’Donovan, P., Bruton, K., & O’Sullivan, D. (2018, jul). A Robust Prescriptive Framework and Performance Metric for Diagnosing and Predicting Wind Turbine Faults Based on SCADA and Alarms Data with Case Study. Energies, 11(7), 1738. doi: 10.3390/en11071738
Leahy, K., Hu, R. L., Konstantakopoulos, I. C., Spanos, C. J., Agogino, A. M., & O’Sullivan, D. T. (2018). Diagnosing and Predicting Wind Turbine Faults from SCADA Data Using Support Vector Machines. International Journal of Prognostics and Health Management, 9(1), 1–11.
O’Donovan, P., Leahy, K., Bruton, K., & O’Sullivan, D. T. J. (2015, dec). An industrial big data pipeline for datadriven analytics maintenance applications in largescale smart manufacturing facilities. Journal of Big Data, 2(1), 25. doi: 10.1186/s40537-015-0034-z