Combination of Model-based Observer and Support Vector Machines for Fault Detection of Wind Turbines

Nassim Laouti Sami Othman Mazen Alamir Nida Sheibat-Othman

Nassim Laouti, Sami Othman, Mazen Alamir, Nida Sheibat-Othman. Combination of Model-based Observer and Support Vector Machines for Fault Detection of Wind Turbines[J]. 国际自动化与计算杂志(英)/International Journal of Automation and Computing, 2014, 11(3): 274-287. doi: 10.1007/s11633-014-0790-9
引用本文: Nassim Laouti, Sami Othman, Mazen Alamir, Nida Sheibat-Othman. Combination of Model-based Observer and Support Vector Machines for Fault Detection of Wind Turbines[J]. 国际自动化与计算杂志(英)/International Journal of Automation and Computing, 2014, 11(3): 274-287. doi: 10.1007/s11633-014-0790-9
Nassim Laouti, Sami Othman, Mazen Alamir and Nida Sheibat-Othman. Combination of Model-based Observer and Support Vector Machines for Fault Detection of Wind Turbines. International Journal of Automation and Computing, vol. 11, no. 3, pp. 274-287, 2014 doi:  10.1007/s11633-014-0790-9
Citation: Nassim Laouti, Sami Othman, Mazen Alamir and Nida Sheibat-Othman. Combination of Model-based Observer and Support Vector Machines for Fault Detection of Wind Turbines. International Journal of Automation and Computing, vol. 11, no. 3, pp. 274-287, 2014 doi:  10.1007/s11633-014-0790-9

Combination of Model-based Observer and Support Vector Machines for Fault Detection of Wind Turbines

doi: 10.1007/s11633-014-0790-9
详细信息
    作者简介:

    Nassim Laouti received his M. Sc. degree in electronics engineering from University of Science and Technology Houari Boumediene, Algiers in 2006, and in automatic control from University of Lyon, France in 2008. He received his Ph. D. degree in automatic control from University of Lyon, France in 2012. Since 2013 he has been an associate professor at the University of Science and Technology Houari Boumediene. His research interests include artificial intelligence, machine learning, support vector machines, statistical signal processing, nonlinear system identification and control, wind turbines, wastewater treatment plant and data mining. E-mail: nassimlat@yahoo.fr

Combination of Model-based Observer and Support Vector Machines for Fault Detection of Wind Turbines

  • 摘要: Support vector machines and a Kalman-like observer are used for fault detection and isolation in a variable speed horizontal-axis wind turbine composed of three blades and a full converter. The support vector approach is data-based and is therefore robust to process knowledge. It is based on structural risk minimization which enhances generalization even with small training data set and it allows for process nonlinearity by using flexible kernels. In this work, a radial basis function is used as the kernel. Different parts of the process are investigated including actuators and sensors faults. With duplicated sensors, sensor faults in blade pitch positions, generator and rotor speeds can be detected. Faults of type stuck measurements can be detected in 2 sampling periods. The detection time of offset/scaled measurements depends on the severity of the fault and on the process dynamics when the fault occurs. The converter torque actuator fault can be detected within 2 sampling periods. Faults in the actuators of the pitch systems represents a higher difficulty for fault detection which is due to the fact that such faults only affect the transitory state (which is very fast) but not the final stationary state. Therefore, two methods are considered and compared for fault detection and isolation of this fault: support vector machines and a Kalman-like observer. Advantages and disadvantages of each method are discussed. On one hand, support vector machines training of transitory states would require a big amount of data in different situations, but the fault detection and isolation results are robust to variations in the input/operating point. On the other hand, the observer is model-based, and therefore does not require training, and it allows identification of the fault level, which is interesting for fault reconfiguration. But the observability of the system is ensured under specific conditions, related to the dynamics of the inputs and outputs. The whole fault detection and isolation scheme is evaluated using a wind turbine benchmark with a real sequence of wind speed.
  • [1] Y. Amirat, M. E. H. Benbouzid, E. Al-Ahmar, B. Bensaker, S. Turri. A brief status on condition monitoring and fault diagnosis in wind energy conversion systems. Renewable and Sustainable Energy Reviews, vol. 13, no. 9, pp. 2629-2639, 2009.
    [2] Z. Hameed, Y. S. Hong, Y. M. Cho, S. H. Ahn, C. K. Song. Condition monitoring and fault detection of wind turbines and related algorithms: A review. Renewable and Sustainable Energy Reviews, vol. 13, no. 1, pp. 1-39, 2009.
    [3] B. Lu, Y. Y. Li, X.Wu, Z. Zang. A review of recent advances in wind turbine condition monitoring and fault diagnosis. In Proceedings of the Power Electronics and Machines in Wind Applications, IEEE, Lincoln, NE, USA, pp. 1-7, 2009.
    [4] P. F. Odgaard, J. Stoustrup, R. Nielsen, C. Damgaard. Observer based detection of sensor faults in wind turbines. In Proceedings of European Wind Energy Conference, Marseille, France, 2009.
    [5] K. Rothenhagen, F. W. Fuchs. Current sensor fault detection and reconfiguration for a doubly fed induction generator. In Proceedings of IEEE Power Electronics Specialists Conference (PESC), IEEE, Orlando, FL, USA, pp. 27322738, 2007.
    [6] P. Poure, P. Weber, D. Theilliol, S. Saadate. Fault-tolerant power electronic converters: Reliability analysis of active power filter. In Proceedings of IEEE International Symposium on Industrial Electronics ISIE, IEEE, Vigo, Spain, pp. 3174-3179, 2007.
    [7] S. H. Li, D. C. Wunsch, E. A. O0Hair, M. G. Giesselmann. Using neural networks to estimate wind turbine power generation. IEEE Transactions on Energy Conversion, vol. 16, no. 3, pp. 276-282, 2001.
    [8] M. Schlechtingen, I. F. Santos. Comparative analysis of neural network and regression based condition monitoring approaches for wind turbine fault detection. Mechanical Systems and Signal Processing, vol. 25, no. 5, pp. 1849-1875, 2011.
    [9] P. F. Odgaard, J. Stoustrup. Estimation of uncertainty bounds for the future performance of a power plant. IEEE Transactions on Control Systems Technology, vol. 17, no. 1, pp. 199-206, 2009.
    [10] A. Kusiak, W. Y. Li. The prediction and diagnosis of wind turbine faults. Renewable Energy, vol. 36, no. 1, pp. 16-23, 2011.
    [11] T. Barszcz, R. B. Randall. Application of spectral kurtosis for detection of a tooth crack in the planetary gear of a wind turbine. Mechanical Systems and Signal Processing, vol. 23, no. 4, pp. 1352-1365, 2009.
    [12] P. F. Odgaard, J. Stoustrup, M. Kinnaert. Fault tolerant control of wind turbines: A benchmark model. In Proceedings of the 7th IFAC Symposium on Fault Detection, Supervision and Safety of Technical Processes, IFAC, Barcelona, Spain, pp. 155-160, 2009.
    [13] N. Laouti, N. Sheibat-Othman, S. Othman. Support vector machines for fault detection in wind turbines. In Proceedings of the 18th IFAC World Congress, IFAC, Universitá Cattolica del Sacro Cuore, Milan, Italy, pp. 7067-707, 2011.
    [14] X. Zhang, Q. Zhang, S. Zhao, R. M. G. Ferrari, M. M. Polycarpou, T. Parisini. Fault detection and isolation of the wind turbine benchmark: An estimation-based approach. In Proceedings of the 18th IFAC World Congress, IFAC, Universitá Cattolica del Sacro Cuore, Milan, Italy, pp. 8295-8300, 2011.
    [15] A. A. Ozdemir, P. Seiler, G. J. Balas. Wind turbine fault detection using counter-based residual thresholding. In Proceedings of the 18th IFAC World Congress, IFAC, Universitá Cattolica del Sacro Cuore, Milan, Italy, pp. 8289-8294, 2011.
    [16] P. L. Negre, V. Vicenc Puig, I. Pineda. Fault detection and isolation of a real wind turbine using LPV observers. In Proceedings of the 18th IFAC World Congress, IFAC, Universitat Politècnica de Catalunya, Milan, Italy, pp. 1237212379, 2011.
    [17] S. Simani, P. Castaldi, M. Bonf. Hybrid model-based fault detection of wind turbine sensors. In Proceedings of the 18th IFAC World Congress, IFAC, Universitá Cattolica del Sacro Cuore, Milan, Italy, pp. 7061-7066, 2011.
    [18] B. Ayalew, P. Pisu. Robust fault diagnosis for a horizontal axis wind turbine. In Proceedings of the 18th IFAC World Congress, IFAC, Universitá Cattolica del Sacro Cuore, Milan, Italy, pp. 7055-7060, 2011.
    [19] J. F. Dong, M. Verhaegen. Data driven fault detection and isolation of a wind turbine benchmark. In Proceedings of the 18th IFAC World Congress, IFAC, Universitá Cattolica del Sacro Cuore, Milan, Italy, pp. 7086-7091, 2011.
    [20] W. Chen, S. X. Ding, A. H. A. Sari, A. Naik, A. Q. Khan, S. Yin. Observer-based FDI schemes for wind turbine benchmark. In Proceedings of 18th IFAC World Congress, IFAC, Universitá Cattolica del Sacro Cuore, Milan, Italy, pp. 7073-7078, 2011.
    [21] X. Sun, H. J. Marquez, T. Chen, M. Riaz. An improved PCA method with application to boiler leak detection. ISA Transactions, vol. 44, no. 3, pp. 379-397, 2005.
    [22] S. X. Ding. Model-based Fault Diagnosis Techniques, Berlin: Springer, 2008.
    [23] S. Simani, C. Fantuzzi, R. J. Patton. Model-based Fault Diagnosis in Dynamic Systems Using Identification Techniques, XIV, 298. Series: Advances in Industrial Control. London: Springer-Verlag, 2002.
    [24] R. Isermann. Fault-diagnosis Systems from Fault Detection to Fault Tolerance, New York: Springer Verlag, 2006.
    [25] O. A. Z. Sotomayor, D. Odloak. Observer-based fault diagnosis in chemical plants. Chemical Engineering Journal, vol. 112, no. 1-3, pp. 93-108, 2005.
    [26] R. J. Patton, J. Chen. On eigenstructure assignment for robust fault diagnosis. International Journal of Robust Nonlinear Control, vol. 10, no. 14, pp. 1193-1208, 2000.
    [27] C. Edwards, S. K. Spurgeon, R. J. Patton. Sliding mode observers for fault detection and isolation. Automatica, vol. 36, no. 4, pp. 541-553, 2000.
    [28] Y. J. Huang, G. V. Reklaitis, V. A. Venkatasubramanian. Heuristic extended Kalman filter based estimator for fault identification in a fluid catalytic cracking unit. Industrial & Engineering Chemistry Research, vol. 42, no. 14, pp. 33613371, 2003.
    [29] P. M. Frank. Fault diagnosis in dyanmic systems using analytical and knowledge-based redundancy A survey and some new results. Automatica, vol. 26, no. 3, pp. 459-474, 1990.
    [30] E. A. Garcia, P. M. Frank. Deterministic nonlinear observer-based approaches to fault diagnosis: A survey. Control Engineering Practice, vol. 5, no. 5, pp. 663-670, 1997.
    [31] H. Hammouri, P. Kaboré, S. Othman, J. Biston. Failure diagnosis and nonlinear observers: Application to a hydraulic process. Journal of the Franklin Institute, vol. 339, no. 4-5, pp. 455-478, 2002.
    [32] P. Kaboré, S. Othman, T. F. McKenna, H. Hammouri. Observer based fault diagnosis for a class of non-linear systems: Application to a free radical copolymerisation reaction. International Journal of Control, vol. 73, no. 9, pp. 787-803, 2000.
    [33] C. De Persis, A. Isidori. A geometric approach to nonlinear fault detection and isolation. IEEE Transactions of Automatic Control, vol. 46, no. 6, pp. 853-865, 2001.
    [34] V. N. Vapnik, A. Chervonenkis. A note on one class of perceptrons. Automation & Remote Control, vol. 25, pp. 821837, 1964.
    [35] B. E. Boser, I. M. Guyon, V. N. Vapnik. A training algorithm for optimal margin classifiers. In Proceedings of the 5th Workshop on Computational Learning Theory, ACM Press, Pittsburgh, PA, USA, pp. 144-152, 1992.
    [36] V. N. Vapnik. The Nature of Statistical Learning Theory, New York: Springer-Verlag, 1995.
    [37] A. Widodo, B. S. Yang. Support vector machine in machine condition monitoring and fault diagnosis. Mechanical Systems and Signal Processing, vol. 21, no. 6, pp. 2560-2574, 2007.
    [38] L. Meng, Q. H. Wu. Fast training of support vector machines using error-center-based optimization. International Journal of Automation and Computing, vol. 2, no. 1, pp. 612, 2005.
    [39] X. Chen, T. Limchimchol. Monitoring grinding wheel redress-life using support vector machines. International Journal of Automation and Computing, vol. 3, no. 1, pp. 5662, 2006.
    [40] X. H. Huang, X. J. Zeng, M. Wang. SVM-based identification and un-calibrated visual servoing for micromanipulation. International Journal of Automation and Computing, vol. 7, no. 1, pp. 47-54, 2010.
    [41] H. Hammouri, G. Bornard. A high gain observer for a class of uniformly observable systems. In Proceedings of the 30th IEEE Conference on Decision and Control, IEEE, Brighton UK, pp. 1494-1496, 1991.
    [42] V. Cherkassky, Y. Ma. Practical selection of SVM parameters and noise estimation for SVM regression. Neural Networks, vol. 17, no. 1, pp. 113-126, 2004.
    [43] H. Hammouri, J. De Leon Morales. Observer synthesis for state-affine systems. In Proceedings of the 29th IEEE Conference on Decision and Control, IEEE, Honolulu, Hawaii, USA, pp. 784-785, 1990.
  • [1] Fu-Tian Wang, Li Yang, Jin Tang, Si-Bao Chen, Xin Wang.  DLA+: A Light Aggregation Network for Object Classification and Detection . International Journal of Automation and Computing, 2021, 18(): 1-10. doi: 10.1007/s11633-021-1287-y
    [2] Lu-Jie Zhou, Jian-Wu Dang, Zhen-Hai Zhang.  Fault Classification for On-board Equipment of High-speed Railway Based on Attention Capsule Network . International Journal of Automation and Computing, 2021, (): 1-12. doi: 10.1007/s11633-021-1291-2
    [3] Soni Lanka Karri, Liyanage Chandratilak De Silva, Daphne Teck Ching Lai, Shiaw Yin Yong.  Identification and Classification of Driving Behaviour at Signalized Intersections Using Support Vector Machine . International Journal of Automation and Computing, 2021, 18(): 1-12. doi: 10.1007/s11633-021-1295-y
    [4] Erphan A. Bhuiyan, Md. Maeenul Azad Akhand, Sajal K. Das, Md. F. Ali, Z. Tasneem, Md. R. Islam, D. K. Saha, Faisal R. Badal, Md. H. Ahamed, S. I. Moyeen.  A Survey on Fault Diagnosis and Fault Tolerant Methodologies for Permanent Magnet Synchronous Machines . International Journal of Automation and Computing, 2020, 17(6): 763-787. doi: 10.1007/s11633-020-1250-3
    [5] Derradji Nada, Mounir Bousbia-Salah, Maamar Bettayeb.  Multi-sensor Data Fusion for Wheelchair Position Estimation with Unscented Kalman Filter . International Journal of Automation and Computing, 2018, 15(2): 207-217. doi: 10.1007/s11633-017-1065-z
    [6] Fusaomi Nagata, Keigo Watanabe, Maki K. Habib.  Machining Robot with Vibrational Motion and 3D Printer-like Data Interface . International Journal of Automation and Computing, 2018, 15(1): 1-12. doi: 10.1007/s11633-017-1101-z
    [7] Jie Bao, Hong Yue, William E. Leithead, Ji-Qiang Wang.  Feedforward Control for Wind Turbine Load Reduction with Pseudo-LIDAR Measurement . International Journal of Automation and Computing, 2018, 15(2): 142-155. doi: 10.1007/s11633-017-1103-x
    [8] Yu Zhang, Chris Bingham, Mike Garlick, Michael Gallimore.  Applied Fault Detection and Diagnosis for Industrial Gas Turbine Systems . International Journal of Automation and Computing, 2017, 14(4): 463-473. doi: 10.1007/s11633-016-0967-5
    [9] Philip Cross, Xiandong Ma.  Model-based and Fuzzy Logic Approaches to Condition Monitoring of Operational Wind Turbines . International Journal of Automation and Computing, 2015, 12(1): 25-34. doi: 10.1007/s11633-014-0863-9
    [10] Zhi-Guo Ding, Da-Jun Du, Min-Rui Fei.  An Isolation Principle Based Distributed Anomaly Detection Method in Wireless Sensor Networks . International Journal of Automation and Computing, 2015, 12(4): 402-412. doi: 10.1007/s11633-014-0847-9
    [11] Qing-Yu Su, Yan-Cheng Li, Xing-Ze Dai, Jian Li.  Fault Detection for a Class of Impulsive Switched Systems . International Journal of Automation and Computing, 2014, 11(2): 223-230. doi: 10.1007/s11633-014-0784-7
    [12] Teerawat Sangpet, Suwat Kuntanapreeda, Rüdiger Schmidt.  Hysteretic Nonlinearity Observer Design Based on Kalman Filter for Piezo-actuated Flexible Beams with Control Applications . International Journal of Automation and Computing, 2014, 11(6): 627-634. doi: 10.1007/s11633-014-0817-2
    [13] An Imperfect-debugging Fault-detection Dependent-parameter Software . International Journal of Automation and Computing, 2007, 4(4): 325-328. doi: 10.1007/s11633-007-0325-8
    [14] Marek Kowal,  Józef Korbicz.  Fault Detection under Fuzzy Model Uncertainty . International Journal of Automation and Computing, 2007, 4(2): 117-124. doi: 10.1007/s11633-007-0117-1
    [15] Ping Zhang,  Steven X. Ding.  A Model-free Approach to Fault Detection of Continuous-time Systems Based on Time Domain Data . International Journal of Automation and Computing, 2007, 4(2): 189-194. doi: 10.1007/s11633-007-0189-y
    [16] Bibhrajit Halder,  Nilanjan Sarkar.  Robust Nonlinear Analytic Redundancy for Fault Detection and Isolation in Mobile Robot . International Journal of Automation and Computing, 2007, 4(2): 177-182. doi: 10.1007/s11633-007-0177-2
    [17] Mohamed-Faouzi Harkat,  Salah Djelel,  Noureddine Doghmane,  Mohamed Benouaret.  Sensor Fault Detection, Isolation and Reconstruction Using Nonlinear Principal Component Analysis . International Journal of Automation and Computing, 2007, 4(2): 149-155. doi: 10.1007/s11633-007-0149-6
    [18] Min-Ze Chen,  Qi Zhao,  Dong-Hua Zhou.  A Robust Fault Detection Approach for Nonlinear Systems . International Journal of Automation and Computing, 2006, 3(1): 23-28. doi: 10.1007/s11633-006-0023-y
    [19] Xun Chen,  Thitikorn Limchimchol.  Monitoring Grinding Wheel Redress-life Using Support Vector Machines . International Journal of Automation and Computing, 2006, 3(1): 56-62. doi: 10.1007/s11633-006-0056-2
    [20] L. Meng,  Q. H. Wu.  Fast Training of Support Vector Machines Using Error-Center-Based Optimization . International Journal of Automation and Computing, 2005, 2(1): 6-12. doi: 10.1007/s11633-005-0006-4
  • 加载中
计量
  • 文章访问数:  5721
  • HTML全文浏览量:  52
  • PDF下载量:  3429
  • 被引次数: 0
出版历程
  • 收稿日期:  2013-02-22
  • 修回日期:  2013-11-15

Combination of Model-based Observer and Support Vector Machines for Fault Detection of Wind Turbines

doi: 10.1007/s11633-014-0790-9
    作者简介:

    Nassim Laouti received his M. Sc. degree in electronics engineering from University of Science and Technology Houari Boumediene, Algiers in 2006, and in automatic control from University of Lyon, France in 2008. He received his Ph. D. degree in automatic control from University of Lyon, France in 2012. Since 2013 he has been an associate professor at the University of Science and Technology Houari Boumediene. His research interests include artificial intelligence, machine learning, support vector machines, statistical signal processing, nonlinear system identification and control, wind turbines, wastewater treatment plant and data mining. E-mail: nassimlat@yahoo.fr

摘要: Support vector machines and a Kalman-like observer are used for fault detection and isolation in a variable speed horizontal-axis wind turbine composed of three blades and a full converter. The support vector approach is data-based and is therefore robust to process knowledge. It is based on structural risk minimization which enhances generalization even with small training data set and it allows for process nonlinearity by using flexible kernels. In this work, a radial basis function is used as the kernel. Different parts of the process are investigated including actuators and sensors faults. With duplicated sensors, sensor faults in blade pitch positions, generator and rotor speeds can be detected. Faults of type stuck measurements can be detected in 2 sampling periods. The detection time of offset/scaled measurements depends on the severity of the fault and on the process dynamics when the fault occurs. The converter torque actuator fault can be detected within 2 sampling periods. Faults in the actuators of the pitch systems represents a higher difficulty for fault detection which is due to the fact that such faults only affect the transitory state (which is very fast) but not the final stationary state. Therefore, two methods are considered and compared for fault detection and isolation of this fault: support vector machines and a Kalman-like observer. Advantages and disadvantages of each method are discussed. On one hand, support vector machines training of transitory states would require a big amount of data in different situations, but the fault detection and isolation results are robust to variations in the input/operating point. On the other hand, the observer is model-based, and therefore does not require training, and it allows identification of the fault level, which is interesting for fault reconfiguration. But the observability of the system is ensured under specific conditions, related to the dynamics of the inputs and outputs. The whole fault detection and isolation scheme is evaluated using a wind turbine benchmark with a real sequence of wind speed.

English Abstract

Nassim Laouti, Sami Othman, Mazen Alamir, Nida Sheibat-Othman. Combination of Model-based Observer and Support Vector Machines for Fault Detection of Wind Turbines[J]. 国际自动化与计算杂志(英)/International Journal of Automation and Computing, 2014, 11(3): 274-287. doi: 10.1007/s11633-014-0790-9
引用本文: Nassim Laouti, Sami Othman, Mazen Alamir, Nida Sheibat-Othman. Combination of Model-based Observer and Support Vector Machines for Fault Detection of Wind Turbines[J]. 国际自动化与计算杂志(英)/International Journal of Automation and Computing, 2014, 11(3): 274-287. doi: 10.1007/s11633-014-0790-9
Nassim Laouti, Sami Othman, Mazen Alamir and Nida Sheibat-Othman. Combination of Model-based Observer and Support Vector Machines for Fault Detection of Wind Turbines. International Journal of Automation and Computing, vol. 11, no. 3, pp. 274-287, 2014 doi:  10.1007/s11633-014-0790-9
Citation: Nassim Laouti, Sami Othman, Mazen Alamir and Nida Sheibat-Othman. Combination of Model-based Observer and Support Vector Machines for Fault Detection of Wind Turbines. International Journal of Automation and Computing, vol. 11, no. 3, pp. 274-287, 2014 doi:  10.1007/s11633-014-0790-9
参考文献 (43)

目录

    /

    返回文章
    返回