AUTHORS: Mohamed Lamine Fadda, Abdelkrim Moussaoui

Download as PDF

ABSTRACT: In this papers, a new approach for faults detection and diagnosis in observable data system wind turbine - permanent magnet synchronous generator (WT-PMSG), the studying objective, illustrate the combination (SOM- PCA) to build Multi-local-PCA models faults detection in system (WT-PMSG), the performance of the method suggested to faults detection and diagnostic in experimental data, finding good results in simulation experiment.

KEYWORDS: WT, PMSG , FDI, Diagnostic, SOM, PCA, Multi-PCA, FFT

REFERENCES:

[1] Kimball R, a rational look at renewable energy and the implications of intermittent power. Ed 1.2, Deseret Power, South Jordan, USA, 11- 2010.

[2] Amirat Y, Benbouzid M, Al-Ahmar E. A brief status on condition monitoring and fault diagnosis in wind energy conversion systems. Renew Sust Energ Rev 2009; 3(9): 2629–2636.

[3] Brandao RFM, Beleza-Carvalho JA, Barbosa FPM. Forecast of faults in a wind turbine gearbox. In: IEEE Proceedings of 9th International Conference ELEKTRO’2012, 21- 22 May 2012; Rajeck Teplice, Slovakia. New York, NY, USA: IEEE. pp. 170 –173.

[4] J. R. Babu, S. V. Jithesh, ―Breakdown risks in wind energy turbines, Pravartak, the journal of Insurance and risk Management from National Insurance Academy, Pun, Volume III, Issue 3, April – June 2008.

[5] Pierre Tchakoua, René Wamkeue, Mohand Ouhrouche, Fouad Slaoui-Hasnaoui, Tommy Andy Tameghe, Gabriel Ekemb, Wind Turbine Condition Monitoring: State-of-the-Art Review, New Trends, and Future Challenges’, Energies, April 2014 pp 2595-2630. Fig 15. spectrum of signal without fault. Fig 16. SPE spectrum without fault. Fig 17. SPE spectrum with out-race fault. Fig 18. SPE spectrum with inner-race fault. Fig 19. SPE spectrum of signal with ball fault. Fig 20. Fault diagnosis and classification using SOM-PCA.

[6] Afrooz P, Ghavameddin N, Acoustic emission condition monitoring : an application for wind turbine fault detection, IJRET, 2013; 2(5) pp 907–918.

[7] Michael P, Bill C P L, Eden W M M; Review of offshore wind turbine failures and fault prognostic methods. Proceedings of the IEEE 2012 Prognostics and System Health Management Conference (PHM-2012 Beijing), pages 1–5, 2012.

[8] Hahn, B.; Durstewitz, M.; Rohrig, K. Reliability of Wind Turbines. In Wind Energy; Springer: Berlin/Heidelberg, Germany, 2007; pp. 329–332.

[9] Yang Y, Lu N, Wang F, Ma L, Chang Y. Statistical process monitoring using multiple PCA models. In: Proceedings of the American Control Conference IEEE 2002, 8-10 May 2002, Anchorage, Alaska, USA: IEEE, Vol 6, pp.5072 – 5073.

[10] Muyeen SM, Tamura J, Murata T. Stability Augmentation of a Grid-connected Wind Farm. Springer, London, 2009.

[11] Munteanu I, Bratcu A, Cutuluslis N, Ceanga E, Ceanga E, Optimal Control of Wind Energy Systems;Toward a Global Approach. SpringerVerlag, London Limited, 2008.

[12] Eisenhut C, Krug F, Schram C, Klockl B. Wind-Turbine Model for System Simulations Near Cut-In Wind Speed. IEEE T Energy Conver 2007; 22(2): 414 – 420.

[13] Pierre S, Nichita C, Brossard J, Jo CH. Concept development of real time emulators for offshore wind power (OWP) and tidal current power (TCP) hybrid system. In: IEEE 17th International Conference System Theory Control and Computing (ICSTCC’2013), 11-13 October 2013, Sinaia, România. New York, NY, USA: IEEE. pp. 416 - 421.

[14] Yang, W, Condition monitoring and fault diagnosis of a wind turbine synchronous generator drive train, IET Renew Pow Gen 2009; 3(2): 630–636.

[15] Dunia R, Qin SJ, Subspace approach to multidimensional fault identification and reconstruction. AIChEJ 1998; 44 (8): 1813– 1831.

[16] Dunia R, Qin SJ, Edgar TF, Identification of faulty sensors using principal component analysis, AIChE J 1996; 42(10): 2797–2812.

[17] Ouni K, Dhouibi H, Nabli L, Hassani Messaoud. New monitoring method based principal component analysis and fuzzy clustering. Int J Phys Sci 2013; 8(18): 901– 914.

[18] Kohonen T. Self-organizing maps. 3rd edition. NewYork, USA: Springer Series in Information Sciences, 30, 2001.

[19] Reusch DB, Alley R B, Hewitson BC, Relative performance of self-organizing maps and principal component analysis in pattern extraction from synthetic climatological data. Polar Geogr Geol 2005; 29, 3: 188–212.

[20] Yang BS, Han T, An J L. ART-KOHONEN neural network for fault diagnosis of rotating machinery. Mech Syst Signal Pr 2004; 18(3): 645–657.

[21] Saxena A, Saad A, Fault Diagnosis in Rotating Mechanical Systems Using Self-Organizing Maps. In: Artificial Neural Networks in Engineering Conference (ANNIE’2004), 7-10 November 2004, St. Louis, Missouri, USA.

[22] ZHU Q, LI C. Dimensionality Reduction with Input Training Neural Network and its Application in Chemical Process Modelling. Chinese J Chem Eng 2006; 14(5) 597–603.

[23] Verbeek, JJ, Vlassis N, Kröse BJA. A ksegments algorithm for finding principal curves. Pattern Recogn Lett 2002; 23(8): 1009– 1017.

[24] Zhongqing Wei, Jinji Gao, Xin Zhong, Zhinong Jiang, Bo Ma, Incipient fault diagnosis of rolling element bearing based on wavelet packet transform and energy operator, WSEAS TRANSACTIONS on SYSTEMS, Issue 3, Volume 10, March 2011, pp 81-90.

[25] Ramahaleomiarantsoa JF, Sambatra EJR, Héraud N, Razafimahenina JM. Performances of the PCA Method in Electrical Machines Diagnosis Using Matlab. In: Katsikis V, editor. MATLAB – A Fundamental Tool for Scientific Computing and Engineering Applications – Chapitre 4. Rijeka, Croatia: InTech, 2012. 1. pp. 69–88.

[26] http://csegroups.case.edu/bearingdatacenter/pag es/12k-drive-end-bearing-fault-data

[27] Jason R. Stack, Thomas G. Habetler and Ronald G. Harley, Fault Classification and Fault Signature Production for Rolling Element Bearings in Electric Machines, IEEE Transactions on Industry applications, Vol. 40, No. 3, pp. 735 -739, May/June 2004.