Multi-turbine Associative Model for Wind Turbine Performance Monitoring



Onder Uluyol Girija Parthasarathy


Comparing the performance parameters of a set of wind turbines in a single region will provide insights that prevent raising unnecessary alarm, while confirming actual faults. Wind turbines operating in a wind farm experience similar operating and environmental conditions that could indicate either normality for that group or failures that manifest in those conditions. These norms and failures are an orthogonal set of data rich in information that can be utilized in performance monitoring algorithms to supply better prediction accuracy and low false positives. In this paper, we describe the use of an associative model (AM) for fault detection in a population. An associative model maps system parameters to an identical set of virtual parameters. The AM-based approach can be used to capture the underlying correlation of an observable system, such as performance parameters of a set of wind turbines in a wind farm. The residuals between the model output and the input can then be used to detect anomalies and isolate faults.

How to Cite

Uluyol, O. ., & Parthasarathy, G. . (2012). Multi-turbine Associative Model for Wind Turbine Performance Monitoring. Annual Conference of the PHM Society, 4(1).
Abstract 40 | PDF Downloads 32



Wind Turbine, Associative Model, Performance Monitoring, Wind Farm, SCADA

Bell, M. B. & Foslien, W. K. (2005). Early event detection- results from a prototype implementation. In 17th Annual Ethylene Producers‘ Conference, Session TA006-Ethylene Plant Process Control. Spring National Meeting (pp. 727-741), Apr. 10-14, Atlanta, GA.

Gorinevsky, D., Dittmar, K., Mylaraswamy, D. & Nwadiogbu, E. (2002). Model-based diagnostics for an aircraft auxiliary power unit. IEEE Conference on Control Applications. (pp 215-220), Sept 18–20, Glasgow, Scotland.

Kim, K. & Mylaraswamy, D. (2006). Fault Diagnosis and Prognosis of Gas Turbine Engines Based on Qualitative Modeling. In ASME TurboExpo. (881–889), May 8–11, Barcelona, Spain.

Kim, K., Parthasarathy, G., Uluyol, O., Foslien, W., Sheng, S., Fleming, P., (2011), Use of SCADA Data for Failure Detection in Wind Turbines, Proceedings of 2011 Energy Sustainability Conference and Fuel Cell Conference, August 7-10, 2011, Washington DC, USA.

Kramer, M. A., (1992) Autoassociative neural networks, Computers Chem. Eng., Vol. 16, No. 4, 313-328.

Kusiak, A., & Li, W. (2011). The prediction and diagnosis of wind turbine faults. Renewable Energy, 36, pp 16-23. Uluyol, O., Buczak, A.L., Nwadiogbu, E., (2001), Neural Networks Based Sensor Validation and Recovery Methodology for Advanced Aircraft Engines, Proceedings of AeroSense 2001, SPIE Vol. 4389, pp.102-109, Orlando, Florida..

Uluyol, O., Kim, K., Wrest, D., Nwadiogbu, E., (2003), Sensor Validation and Recovery through Iterative Association Models, Proceedings of the IEEE Sensors 2003, Oct. 22-24.

Uluyol, O., Parthasarathy, G., Foslien, W., Kim, K., (2011), Power curve analytic for wind turbine performance monitoring and prognostics, Annual Conference of the Prognostics and Health Management Society, Montreal, Canada.

Ye, X., Yan, Y. and Osadciw, L., (2010). Learning Decision Rules by Particle Swarm Optimization (PSO) for Wind Turbine Fault Diagnosis, Annual Conference of the Prognostics and Health Management Society, Oct 10- 16, 2010, Portland, OR.

Zaher, A., McArthur, S.D.J. & Infield, D.G., (2009), Online wind turbine fault detection through automated SCADA data analysis, wind energy. Published online in Wiley Interscience DOI: 10.1002/we.319.
Technical Papers