Fault Diagnosis of a Wind Turbine Benchmark via Statistical and Support Vector Machine

Abstract:

This paper addresses the problem of fault detection and isolation (FDI) in wind turbine benchmark model using data driven and multi-class support vector machine (SVM) approach. Since, the fault detection is fundamental for any active system, isolation is similarly vital, and identification is decisive for fault reconfiguration as well as maintenance addition to monitoring purposes. The need for man-made dynamic system to work automatically when sensor, actuator, or system faults occur was constantly developed in order to increase reliability and decrease unavailability and maintenance costs. The key step of our approach based on extraction of mean features from sensors measurements by applying the statistical methods such as moving standard deviation and the exponential weighted moving average (EWMA). The fault detection step is invoked later based on the multi-class SVM classifier that decides the presence or not of the fault. Another important contribution of this paper is the simulation of combined sensor and actuator faults simultaneously for the first time in wind turbine benchmark model. The FDI performances are illustrated through simulation study for seven different scenario tests. The results demonstrate clearly the effectiveness of statistical and SVM approach to detect and isolate single, multiple sensor and actuator faults and outperforms many results reported in the literature for solving this problem.

• Periodical: International Journal of Engineering Research in Africa (Volume 37)
• Pages: 29-42
• DOI: https://doi.org/10.4028/www.scientific.net/JERA.37.29
• Online since: August 2018
• Authors: Abderrahmane Mokhtari*, Mohammed Belkheiri
• Keywords: Exponential Weighted Moving Average, Fault Diagnosis, Statistical Analysis, Support Vector Machine, Wind Turbine Benchmark Model

References

[1] N. L. Panwar, S. C. Kaushik, S. Kothari. Role of renewable energy sources in environmental protection: a review. Renewable and Sustainable Energy Reviews, vol. 15, no 3, pp.1513-1524, (2011).

DOI: 10.1016/j.rser.2010.11.037

[2] T. Ackermann. Wind power in power systems. John Wiley & Sons, (2005).

[3] F. Blaabjerg, K. Ma. Future on power electronics for wind turbine systems. IEEE Journal of Emerging and Selected Topics in Power Electronics, vol. 1, no 3, pp.139-152, (2013).

DOI: 10.1109/jestpe.2013.2275978

[4] C. C. Ciang, J. R. Lee, H. J. Bang. Structural health monitoring for a wind turbine system: a review of damage detection methods. Measurement Science and Technology, vol. 19, no 12, p.122001, (2008).

DOI: 10.1088/0957-0233/19/12/122001

[5] C. Svärd, M. Nyberg, Automated Design of an FDI-System for the Wind Turbine Benchmark. Presented at the Proceedings of the 18th IFAC World Congress, 2011, Milano, Italy, pp.8307-8315.

DOI: 10.3182/20110828-6-it-1002.00618

[6] R. M. Fernandez-canti,., J. Blesa, S. Tornil-sin, Sebastian, V. Puig. Fault detection and isolation for a wind turbine benchmark using a mixed Bayesian/Set-membership approach. Annual Reviews in Control, 2015, vol. 40, pp.59-69.

DOI: 10.1016/j.arcontrol.2015.08.002

[7] Z. Zhao, C. Wang, Y. Zhang, et al.  Latest progress of fault detection and localization in complex Electrical Engineering. Journal of Electrical Engineering, vol. 65, no 1, pp.55-59, (2014).

DOI: 10.2478/jee-2014-0008

[8] O. Benzineb, F. TAIBI, T.M LALEG-KIRATI, et al. Control and fault diagnosis based sliding mode observer of a multicellular converter: Hybrid approach. Journal of Electrical Engineering, vol. 64, no 1, pp.20-30, (2013).

DOI: 10.2478/jee-2013-0003

[9] W. Teng, X. Ding, Y. Zhang, A. Kusiak . Application of cyclic coherence function to bearing fault detection in a wind turbine generator under electromagnetic vibration. Mechanical Systems and Signal Processing, vol. 87, pp.279-293, (2017).

DOI: 10.1016/j.ymssp.2016.10.026

[10] R. Bi, C. Zhou, and D. M. Hepburn.  Detection and classification of faults in pitch-regulated wind turbine generators using normal behavior models based on performance curves. Renewable Energy, (2016).

DOI: 10.1016/j.renene.2016.12.075

[11] H. Badihia, Y. Zhanga, H. Hong. Fault-tolerant cooperative control in an offshore wind farm using model-free and model-based fault detection and diagnosis approaches. Applied Energy, vol. 181, (2017).

DOI: 10.1016/j.apenergy.2016.12.096

[12] M. Khireddine and A. Boutarfa. Reconfigurable control for a scara robot using RBF networks. Journal of Electrical Engineering, vol. 61, no 2, pp.100-106, (2010).

DOI: 10.2478/v10187-010-0014-7

[13] S. Pourmohammad and A. Fekih. Fault-Tolerant control of wind turbine systems-A review. In : IEEE Green Technologies Conference (IEEE-Green). IEEE, pp.1-6, (2011).

DOI: 10.1109/green.2011.5754880

[14] J. Lan, R.J. Patton, and X. Zhu. Fault-tolerant wind turbine pitch control using adaptive sliding mode estimation. Renewable Energy, (2016).

DOI: 10.1016/j.renene.2016.12.005

[15] F. Shi, F. Patton. An active fault tolerant control approach to an offshore wind turbine model. Renewable Energy, vol. 75, pp.788-798, (2015).

DOI: 10.1016/j.renene.2014.10.061

[16] P. F. Odgaard, J. Stoustrup and M. Kinnaert. Fault-tolerant control of wind turbines: A benchmark model. IEEE Transactions on Control Systems Technology, vol. 21, no 4, pp.1168-1182, (2013).

DOI: 10.1109/tcst.2013.2259235

[17] J. J. Gertler. Survey of model-based failure detection and isolation in complex plants. IEEE Control systems magazine, vol. 8, no 6, pp.3-11, (1988).

DOI: 10.1109/37.9163

[18] P. F. Odgaard, and J. Stoustrup. Unknown input observer based scheme for detecting faults in a wind turbine converter. Presented at IFAC Proceedings Volumes, vol. 42, no 8, pp.161-166, (2009).

DOI: 10.3182/20090630-4-es-2003.00027

[19] P. L. Negre, V. Puig, and I. Pineda. Fault detection and isolation of a real wind turbine using LPV observers. Presented at IFAC Proceedings Volumes, vol. 44, no 1, pp.12372-12379, (2011).

DOI: 10.3182/20110828-6-it-1002.02742

[20] F. Pöschke, S. Georg, and H. Schulte. Fault reconstruction using a Takagi-Sugeno sliding mode observer for the wind turbine benchmark. In : Control, UKACC International Conference on. IEEE. pp.456-461, (2014).

DOI: 10.1109/control.2014.6915183

[21] S. Simani, S. Farsoni, and P. Castaldi. Fault diagnosis of a wind turbine benchmark via identified fuzzy models,. IEEE Transactions on Industrial Electronics, vol. 62, no 6, pp.3775-3782, (2015).

DOI: 10.1109/tie.2014.2364548

[22] X. Zhang, Q. Zhang, S. Zhao, and al. Fault detection and isolation of the wind turbine benchmark: An estimation-based approach. Presented at IFAC Proceedings Volumes, vol. 44, no 1, pp.8295-8300, (2011).

DOI: 10.3182/20110828-6-it-1002.02808

[23] J. Blesa, V. Puig, J. Romera, and al. Fault diagnosis of wind turbines using a set-membership approach. Presented at IFAC Proceedings Volumes, vol. 44, no 1, pp.8316-8321, (2011).

DOI: 10.3182/20110828-6-it-1002.01167

[24] A. Mokhtari, M. Mohammed. An adaptive observer based FDI for wind turbine benchmark model. Presented at the 8th ICMIC (IEEE Explore), (2017).

DOI: 10.1109/icmic.2016.7804210

[25] N. Laouti, O.S. Nida, and S. Othman. Support vector machines for fault detection in wind turbines. Presented at IFAC Proceedings Volumes, vol. 44 Networks, vol. 13, no 2, pp.415-425, 2002., no 1, pp.7067-7072, (2011).

DOI: 10.3182/20110828-6-it-1002.02560

[26] N. Laouti, S. Othman, M. Alamir, N. Sheibat-Othman, Combination of modelbased observer and support vector machines for fault detection of wind turbines, Int. J. Autom. Comput. Vol. 11 no 3 pp.274-287, (2014).

DOI: 10.1007/s11633-014-0790-9

[27] J. Dong and M. Verhaegen. Data driven fault detection and isolation of a wind turbine benchmark. Presented at IFAC Proceedings Volumes, vol. 44, no 1, pp.7086-7091, (2011).

DOI: 10.3182/20110828-6-it-1002.00546

[28] J. C. Platt, N. Cristianini, and J. Shawe-Taylor, Large margin DAG's for multiclass classification, Advances in Neural Information Processing Systems. Cambridge, MA: MIT Press, vol. 12, p.547–553, (2000).

[29] J. V. Debessa, R. M. Palhares, M. F. S. V D'angelo, and al. Data-driven fault detection and isolation scheme for a wind turbine benchmark. Renewable Energy, vol. 87, pp.634-645, (2016).

DOI: 10.1016/j.renene.2015.10.061

[30] S. H. Steiner. EWMA control charts with time-varying control limits and fast initial response. Journal of Quality Technology, vol. 31, no 1, p.75, (1999).

DOI: 10.1080/00224065.1999.11979899

[31] A. K. Patel and J. Divecha. Modified exponentially weighted moving average (EWMA) control chart for an analytical process data. Journal of Chemical Engineering and Materials Science, vol. 2, no 1, pp.12-20, (2011).

[32] L. Bottou, C. Cortes, J. Denker, H. Drucker, I. Guyon, L. Jackel, Y. LeCun, U. Muller, E. Sackinger, P. Simard, and V. Vapnik, Comparison of classifier methods: A case study in handwriting digit recognition, Proc. Int. Conf. Pattern Recognition, p.77–87, (1994).

DOI: 10.1109/icpr.1994.576879

[33] C.W. Hsu and C. J. Lin. A comparison of methods for multiclass support vector machines. IEEE transactions on Neural.

[34] H. E. Merritt, Hydraulic Control Systems. New York, NY, USA: Wiley, (1967).

[35] C. Gardiner. Stochastic methods. Berlin : springer, (2009).

[36] S. Tufféry. Data mining and statistics for decision making. John Wiley & Sons, (2011).

[37] S. Knerr, L. Personnaz and G. Dreyfus, Single-layer learning revisited: a stepwise procedure for building and training a neural network. In: Neurocomputing. Springer Berlin Heidelberg. pp.41-50, (1990).

DOI: 10.1007/978-3-642-76153-9_5

[38] P. F. Odgaard and J. Stoustrup. Results of a wind turbine FDI competition. Presented at IFAC Proceedings Volumes, vol. 45, no 20, pp.102-107, (2012).

DOI: 10.3182/20120829-3-mx-2028.00015

[39] A. A. Ozdemir, P. Seiler, and G. J. Balas,. Wind turbine fault detection using counter-based residual thresholding. Presented at IFAC Proceedings Volumes, vol. 44, no 1, pp.8289-8294, (2011).

DOI: 10.3182/20110828-6-it-1002.01758

[40] W. Chen, S. X. Ding, A. H. A. Sari, A. Naik, A. Q. Khan, and S. Yin, Observer-based FDI schemes for wind turbine benchmark, in Proc. IFAC World Congr, p.7073–7078, (2011).

DOI: 10.3182/20110828-6-it-1002.03469