Anomaly Detection Techniques for the Condition Monitoring of Tidal Turbines



Grant S. Galloway Victoria M. Catterson Craig Love Andrew Robb


Harnessing the power of currents from the sea bed, tidal power has great potential to provide a means of renewable energy generation more predictable than similar technologies such as wind power. However, the nature of the operating environment provides challenges, with maintenance requiring a lift operation to gain access to the turbine above water. Failures of system components can therefore result in prolonged periods of downtime while repairs are completed on the surface, removing the system’s ability to produce electricity and damaging revenues. The utilization of effective condition monitoring systems can therefore prove particularly beneficial to this industry.This paper explores the use of the CRISP-DM data mining process model for identifying key trends within turbine sensor data, to define the expected response of a tidal turbine. Condition data from an operational 1 MW turbine, installed off the coast of Orkney, Scotland, was used for this study. The effectiveness of modeling techniques, including curve fitting, Gaussian mixture modeling, and density estimation are explored, using tidal turbine data in the absence of faults. The paper shows how these models can be used for anomaly detection of live turbine data, with anomalies indicating the possible onset of a fault within the system.

How to Cite

S. Galloway, G. ., M. Catterson, V. ., Love, C. ., & Robb, A. . (2014). Anomaly Detection Techniques for the Condition Monitoring of Tidal Turbines. Annual Conference of the PHM Society, 6(1).
Abstract 230 | PDF Downloads 180



Condition Monitoring, Anomaly Detection, Tidal Generation, Gaussian Mixture Models, Density Estimation

Abdi, H. & Williams, L. (2010). Principle Component Analysis. Wiley Interdisciplinary Reviews: Computational Statistics, 2(4), pp. 433-459

Aly, H. H. H., El-Hawary, M. E. (2011). State of the Art for Tidal Currents Electric Energy Resources. 24th Canadian Conference on Electrical and Computer Engineering (CCECE) (1119-1124), May 8-11, Niagra Falls, ON. doi:10.1109/CCECE.2011.6030636

Bilmes, J. (1998). A Gentle Tutorial of the EM algorithm and its Application to Parameter Estimation for Gaussian Mixture and Hidden Markov Models.Technical Report ICSI-TR-97-021, University of Berkeley

Cao. Y. (2013). Bivariant Kernel Density Estimation (V2.1). e/19280-bivariant-kernel-density-estimation-v2- 1/content/html/gkde2test.html

Chen, H., Ait-Ahmed, N., Zaim, E. & Machmoum, M. (2012). Marine Tidal Current Systems: state of the art. 2012 IEEE International Symposium on Industrial Electronics (1431-1437), May 28-31, Hangzhou, China. doi:10.1109/ISIE.2012.6237301

Chen, Q., Goulding, P., Sandoz, D. & Wynne R. (1998). The Application of Kernel Density Estimates to Condition Monitoring for Process Industries. Proceedings of the American Control Conference (pp 3312-3316). June 1998, Philadelphia, PA. doi: 10.1109/ACC.1998.703187

Dempster, A. P., Laird, N. M. & Rubin, D. B. (1997). Maximum-likelihood from incomplete data via the EM algorithm. Journal of the Royal Statistical Society, Series B, 39(1), pp. 1-38. doi:

Duhaney, J., Khoshgoftaar, T. M., Sloan, J. C., Alhalabi, B. & Beaujean, B. (2011). A Dynamometer for an Ocean Turbine Prototype – Reliability through Automated Monitoring. 2011 IEEE 13th International Symposium on High-Assurance Systems in Engineering (pp 244- 251). November 10-12, Boca Raton, FL. doi: 10.1109/HASE.2011.61

European Union Committee (2008). The EU’s Target for Renewable Energy: 20% by 2020, 27th Report of Session 2007-08

Hung, J. (2012). Energy Optimization of a Diatomic System. University of Washington, Seattle, WA. -thesis.pdf

Killick, R. & Eckley, I. A. (2013). Changepoint: An R Package for Changepoint Analysis. Lancaster University, UK.

King, J. & Tryfonas, T. (2009). Tidal Stream Power Technology – State of the Art. OCEANS 2009 – EUROPE (1-8). May 11-14, Bremen. doi:10.1109/OCEANSE.2009.5278329

Mahfuz, H. & Akram, M. W. (2011). Life Prediction of Composite Turbine Blades under Random Ocean Current and Velocity Shear. OCEANS 2011 IEEE – SPAIN (1-7). June 6-9, Santander. doi:10.1109/Oceans- Spain.2011.6003526

Maimon, O., Rokach, L. (2005). Data Mining and Knowledge Discovery Handbook. New York, NY: Springer

Olson, D. L., Delen, D. (2008). Advanced Data Mining Techniques. Heidelberg: Springer

Pearson, K. (1901). On Lines and Planes of Closest Fit to Systems of Points in Space. Philosophical Magazine, 2(11), pp. 559-572.

Prickett, P., Grosvenor, R., Byrne, C., Jones, A. M., Morris, C., O’Doherty, D. & O’Doherty, T. (2011). Consideration of the Condition Based Maintenance of Marine Tidal Turbines. 9th European Wave and Tidal Energy Conference. September 5-9, Southampton UK.

Rodgers, J. L. & Nicewander, W. A. (1988). Thirteen Ways to Look at the Correlation Coefficient. The American Statistician, 42(1), pp. 59-66

Wald, R., Khoshgoftaar, T. M., Beaujean, B. & Sloan, J. C. (2010). A Review of Prognostics and Health Monitoring Techniques for Autonomous Ocean Systems. 16th ISSAT International Conference Reliability and Quality in Design.
August 5-7, Washington, D.C.

Winter, A. I. (2011). Differences in Fundamental Design Drivers for Wind and Tidal Turbines. OCEANS, 2011 IEEE – SPAIN (1-10), June 6-9, Santander. doi: 10.1109/Oceans-Spain.2011.6003647

Wirth, R. & Hipp, J. (2000). CRISP-DM: Towards a standard process model for data mining. Proceedings of the Fourth International Conference on the Practical Application of Knowledge Discovery and Data Mining (29-39), Manchester, UK.

Zucchi, W. (2003). Applied Smoothing Techniques, Part 1: Kernel Density Estimation. Philadelphia, Pa: Temple University
Poster Presentations