Learning Decision Rules by Particle Swarm Optimization (PSO) for Wind Turbine Fault Diagnosis

##plugins.themes.bootstrap3.article.main##

##plugins.themes.bootstrap3.article.sidebar##

Published Oct 10, 2010
Xiang Ye Yanjun Yan Lisa Ann Osadciw

Abstract

The next generation wind turbine systems become more and more complex, which requires a more accurate fault detection method to ensure their efficiency. On a wind farm, sibling turbines should see similar wind speed if they both work normally. Based on this, we design wind speed difference tests to detect both hard failures and soft failures, including anemometer faults. In such tests, it is crucial to determine the decision boundary optimally to tell apart the abnormal state from the normal state. We propose a Particle Swarm Optimization (PSO) based approach to learn from historical data to decide the location and size of the boundary. This procedure is adaptable to each turbine using SCADA (Supervisory Control And Data Acquisition) data only. Our approach is advantageous in its applicability and data-driven nature to monitor a large wind farm. The test result has verified the effectiveness of our approach, and we have observed the anemometer aging in data.

How to Cite

Ye, X. ., Yan, Y. ., & Ann Osadciw , L. . (2010). Learning Decision Rules by Particle Swarm Optimization (PSO) for Wind Turbine Fault Diagnosis. Annual Conference of the PHM Society, 2(1). https://doi.org/10.36001/phmconf.2010.v2i1.1758
Abstract 190 | PDF Downloads 165

##plugins.themes.bootstrap3.article.details##

Keywords

wind energy, Diagnosis and fault isolation methods, Asset health management, Data-driven detection methodologies

References
Bennouna, O., Heraud, N., Chafouk, H., & Notton, G. (2009, jul.). Influence of model parameters on the diagnosis of the wind turbine generator. In (p. 1 -5).
Burton, T., Sharpe, D., Jenkins, N., & Bossanyi, E. (2001). Wind Energy Handbook. Wiley.
Chen, Z., & Blaabjerg, F. (2006). Wind Energy the worlds fastest growing energy source. IEEE Power Electron Soc Newslett, 18(3).
Chen, Z., Lian, X., Yu, H., & Bao, Z. (2009, nov.). Algorithm of Data Mining and its Application in Fault Diagnosis for Wind Turbine. In (Vol. 2, p. 240 -243).
Gao, F., & Tong, H. (2006). Differential Evolution: An Efficient Method in Optimal PID Tuning and on– line Tuning. In Proceedings of the First International Conference on Complex Systems and Applications. Wuxi, China.
Hansen, N. (March 7, 2010). The CMA Evolution Strategy: A Tutorial (Tech. Rep.). Available from http://www.lri.fr/ ̃hansen/ cmatutorial.pdf
Hisada, K., & Arizino, F. (2002, sep.). Reliability tests for Weibull distribution with varying shape- parameter, based on complete data. Reliability, IEEE Transactions on, 51(3), 331 - 336.
Kennedy, J., & Eberhart, R. (1995). Particle Swarm Optimization. In Proc. IEEE Int’l. Conf. on Neural Networks (Perth, Australia) (Vol. IV, p. 1942- 1948). IEEE Service Center, Piscataway, NJ. Lu, B., Li, Y., Wu, X., & Yang, Z. (2009, jun.). A review of recent advances in wind turbine condition monitoring and fault diagnosis. In (p. 1 -7).
Ribrant, J. (2006). Reliability performance and maintenance - a survey of failures in wind power systems. Unpublished doctoral dissertation, XR-EE-EEK.
Ribrant, J., & Bertling, L. M. (2007, mar.). Survey of Failures in Wind Power Systems With Focus on Swedish Wind Power Plants During 1997 ndash;2005. Energy Conversion, IEEE Transactions on, 22(1), 167 -173.
Robb, D. (20045). Gearbox design for wind turbines improving but still face challenges. Windstat Newsletter, 18(3).
Stefani, A., Bellini, A., & Filippetti, F. (2009, nov.). Diagnosis of Induction Machines’ Rotor Faults in Time-Varying Conditions. Industrial Electronics, IEEE Transactions on, 56(11), 4548 -4556.
Tindal, A., Johnson, C., LeBlanc, M., Harman, K., Rareshide, E., & Graves, A. (2008). Site-Specific Adjustments to Wind Turbine Power Curves. In AWEA WINDPOWER Conference. Houston, TX, USA.
Yan, Y., Kamath, G., Osadciw, L. A., Benson, G., Legac, P., Johnson, P., et al. (2009, July). Fusion for Modeling Wake Effects on Wind Turbines. In Proceedings of 12th International Conference on Information Fusion. Seattle,Washington, USA.
Yan, Y., Osadciw, L. A., Benson, G., & White, E. (2009, May). Inverse Data Transformation for Change Detection in Wind Turbine Diagnostics. In Proceedings of 22nd IEEE Canadian Conference on Electrical and Computer Engineering. Delta St. Johns, Newfoundland and Labrador, Canada.
Yang, W., Tavner, P., Crabtree, C., & Wilkinson, M. (2010, jan.). Cost-Effective Condition Monitoring for Wind Turbines. Industrial Electronics, IEEE Transactions on, 57(1), 263 -271.
Ye, X., Veeramachaneni, K., Yan, Y., & Osadciw, L. A. (2009, July). Unsupervised Learning and Fusion for Failure Detection in Wind Turbines. In Proceedings of 12th International Conference on Information Fusion. Seattle,Washington, USA.
Yeh, T.-H., & Wang, L. (2008, jun.). A Study on Generator Capacity for Wind Turbines Under Various Tower Heights and Rated Wind Speeds Using Weibull Distribution. Energy Conversion, IEEE Transactions on, 23(2), 592 -602.
Zaher, A., & McArthur, S. (2007, jul.). A Multi-Agent Fault Detection System for Wind Turbine Defect Recognition and Diagnosis. In (p. 22 -27).
Section
Technical Research Papers