SLP Header

Condition Monitoring of Arrow Dynamic and Drive Train in Wind Turbine using Artificial Intelligence

IJCSEC Front Page

In order to be economically competitive, various control systems are used in Wind turbine. These systems makes the wind turbine to work efficiently and produce maximum output at different speed. In this paper an adaptive control based on radial-basis function neural network are used for different operation of variable speed wind turbine including torque control at lower speed, pitch control at higher speed and smooth transition between these two modes. The adaptive neural network control approximates the nonlinear dynamics of wind turbine based on input/output measurement. One of the most important features in the smart gird is to integrate the state-of-the-art communication technologies to increase the electrify generation. In offshore wind farms, data communications would rely on wireless techniques. The wireless communication technology has several advantages over the wires or meter counterpart. However, the impact of atmospheric turbulence on wired must be well understood first. In this project, the performance of wireless links subject to weak influence in generator, turbine is monitored. The metrics are analytically and numerically evaluated.
Keywords:Adaptive control,Generator torque control, MAX232, Tarang Processor,ZigBee wireless network.
Wind power has become the world’s fastest growing renewable energy resource. The worldwide wind capacity is increased upto 120 GW.Wind power becomes as a major utility source, it is complex to understand the operation of power system in order to improve both quantity and quality of wind power generation. In Wind turbine there is a different types of failure. Therefore, before exploring condition monitoring and fault diagnostic methods in wind turbines, the different kinds of failures, as well as their downtime consequences, are reviewed [2-7]. Of course, obtaining high power from wind turbine is complex it requires high performance monitoring-. Monitoring systems collects data from the components of Wind turbine such as Generator, gear box, main bearing, shaft, yaw system.
The purpose is to minimize downtime and maintenance cost while increasing energy availability and extending the lifetime service of wind turbine components. Condition monitoring system monitors all the components with a minimum number of sensors. Manufactures and operators are working hard to develop the advanced condition monitoring system to develop the efficiency and prevent from failures. A wind turbine consists of many components that causes different types of failures, in which some of the them will frequently occurs that can be identified by comparing among them,it is necessary to know downtime. The resultant economic loss which is caused by the downtime of a particular component in this work, the economic losses caused by wind turbine subassemblies are approximated by the downtimes caused by failures. Figure 1.1 gives the annual average downtimes of major wind turbine subassemblies according to the LWK survey of more than 2000 wind turbines for 11 years [10].Neural networks are powerful methods for approximation of input output mappings. Many works [6],[7] suggested that the condition can be monitored by integrating both Trend master Pro and Snapshot offerings is signal processing technology, which can be particularly beneficial. The remainder of this article explores the technology and its benefit in more detail to relate wind turbine. Condition monitoring of Wind turbine frequently gives better maintenance management and increased reliability[2]


  1. Y. Amirat, M. E. H. Benbouzid, B. Bensaker, and R. Wamkeue, “Condition monitoring and fault diagnosis in wind energy conversion systems: a review”, in Proc. 2007 IEEE International Electric Machines and Drives Conference, vol. 2, May 2007, pp. 1434-1439.
  2. C. Hatch, “Improved wind turbine condition monitoring using acceleration enveloping,” Orbit, pp. 58-61, 2004.
  3. R. W. Hyers, J. G. McGowan, K. L. Sullivan, J. F. Manwell, and B.C. Syrett, “Condition monitoring and prognosis of utility scale wind turbines,” Energy Materials, vol. 1, no. 3. pp. 187- 203, Sep. 2006.
  4. D. McMillan and G. W. Ault, “Quantification of condition monitoring benefit for offshore wind turbines,” Wind Engineering, vol. 31, no. 4, pp. 267-285, May 2007.
  5. L. M. Popa, B.-B. Jensen, E. Ritchie, and I. Boldea, “Condition monitoring of wind generators,” in Proc. IAS Annu. Meeting, vol. 3, 2003, pp. 1839-1846.
  6. J. Ribrant and L. M. Bertling, “Survey of failures in wind power systems with focus on swedish wind power plants during 1997–2005”, IEEE Trans. Energy Conversion, vol. 22, no. 1, pp. 167-173, Mar. 2007.
  7. P.J. Tavner, G.J.W. van Bussel and F. Spinato, “Machine and converter reliabilities in wind turbines,” The 3rd IET International Conference on Power Electronics, Machines and Drives, Dublin, Ireland, pp. 127-130, March 2006.
  8. C. A. Walford, “Wind turbine reliability: understanding and minimizing wind turbine operation and maintenance costs,” Sandia National Laboratories, Rep. SAND2006-1100, Mar. 2006.
  9. M. R. Wilkinson, F. Spianto, M. Knowles, and P. J. Tavner,“Towards the zero maintenance wind turbine,” in Proc. 41st International Universities Power Engineering Conference, vol. 1, 2006, pp.74-78.
  10. M. R. Wilkinson, F. Spinato, and P. J. Tavner, “Condition monitoring of generators and other subassemblies in wind turbine drive trains”, in Proc. 2007 IEEE International Symposium on Diagnostics for Electric Machines, Power Electronics and Drives, Sep. 2007, pp. 388-392.
  11. B. Boukhezzar and H. Siguerdidjane, “Nonlinear control with wind estimation of a DFIG variable speed wind turbine for power capture optimization,” Elsevier Ener. Conv. Manag., vol. 50, no. 4, pp. 885–892, 2009.
  12. B. Karimi, M. B. Menhaj, and I. Saboori, “Robust adaptive control of nonaffine systems using radial basis function neural networks,” in Proc.32nd Annu. IEEE Ind. Electron. Conf., Nov. 2006, pp. 495–500.
  13. C. L. Bottaso, Wind Turbine Modeling and Control. Milano, Italy:Politecn. Milano, 2009.
  14. J. Hui and A. Bakhshai, “A new adaptive control algorithm for maximum power point tracking for wind energy conversion systems,” in Proc. IEEE Power Electron. Special. Conf., Jun. 2008, pp. 4003–4007.
  15. S. Lang, Real Analysis. Reading, MA: Addison-Wesley,
  16. J. M. Jonkman and M. L. Buhl, “FAST user’s guide,” Nat. Wind Technol. Center, Nat. Renew. Energy Lab., Golden, CO, Tech. Rep. NREL/EL- 500-38230, Aug. 2005.
  17. J. Jonkman, S. Butterfield, W. Musial, and G. Scott, “Definition of a 5-mw reference wind turbine for offshore system development,” Nat. Renew. Energy Lab., Golden, CO, Tech. Rep. NREL/EL-500-38060,Feb. 2009.
  18. J. Ehlers, A. Diop, and H. Bindner, “Sensor selection and state estimation for wind turbine controls,” in Proc. 45th AIAA Aerosp. Sci. Meeting Exh.,Jan. 2007, pp. 1–10.
  19. K. Z. Ostergaard, P. Brath, and J. Stoustrup, “Estimation of effective wind speed,” J. Phys., vol. 75, pp. 1–9, Jun. 2007.P. Simoes, B. K. Bose, and R. J. Spiegel, “Fuzzy logicbased intelligent control of a variable speed cage machine wind generation system,” IEEE Trans. Power Electron., vol. 12, no. 1, pp. 87–95, Jan. 1997.
  20. B. J. Jonkman and M. L. Buhl, “TurbSim user’s guide,” Nat. Wind Energy Technol. Center, Nat. Renew. Energy Lab., Golden, CO, Tech. Rep. NREL/TP-500-39797, Sep. 2006.