Review of offshore wind turbine failures and fault prognostic methods

Wind electricity is a highly promoted energy source all around the world. The number of offshore wind farms, increases gradually because of the high capability of power generation. However, the cost of manufacturing, logistics, installation, grid control and maintenance of offshore wind turbine is high. According to the Condition Monitoring of Offshore Wind Turbine (CONMOW) report of Energy Research Centre in the Netherlands, the investment costs for future offshore wind farms built of larger units are expected to be 1.4 to 2.0 k€/kW. The Operation and Maintenance (O&M) costs 30 to 50 €/kW per year. To enhance a cost effective maintenance strategy and higher quality design, Prognostics and System Health Management (PHM) is applied. In this paper, major failures of wind turbine will be discussed and possible prognostic methods for the failures will be introduced.

[1]  N. Zerhouni,et al.  Hidden Markov Models for failure diagnostic and prognostic , 2011, 2011 Prognostics and System Health Managment Confernece.

[2]  Michael Pecht,et al.  Data‐Driven Approaches for PHM , 2008 .

[3]  D. Rubin,et al.  Maximum likelihood from incomplete data via the EM - algorithm plus discussions on the paper , 1977 .

[4]  L. Rabiner,et al.  An introduction to hidden Markov models , 1986, IEEE ASSP Magazine.

[5]  George J. Vachtsevanos,et al.  Impact of Input Uncertainty on Failure Prognostic Algorithms: Extending the Remaining Useful Life of Nonlinear Systems , 2010 .

[6]  Sheldon M. Ross,et al.  Probability Models for Computer Science , 2001 .

[7]  Van Nostrand,et al.  Error Bounds for Convolutional Codes and an Asymptotically Optimum Decoding Algorithm , 1967 .

[8]  Andrew Ball,et al.  Fault Prognosis and Diagnosis of an Automotive Rear Axle Gear Using a RBF-BP Neural Network , 2011 .

[9]  Hannele Holttinen,et al.  Analysing failure statistics of wind turbines in Finland , 2010 .

[10]  K. Loparo,et al.  Online tracking of bearing wear using wavelet packet decomposition and probabilistic modeling : A method for bearing prognostics , 2007 .

[11]  Richard Kithil.  Case Study of Lightning Damage to Wind Turbine Blade , 2008 .

[12]  Lionel Tarassenko,et al.  Neural network models for breast cancer prognosis , 2005, Neural Computing & Applications.

[13]  M.G. Pecht,et al.  Prognostics and health management of electronics , 2008, IEEE Transactions on Components and Packaging Technologies.

[14]  James F. Manwell,et al.  Condition monitoring and prognosis of utility scale wind turbines , 2006 .

[15]  Lawrence R. Rabiner,et al.  A tutorial on hidden Markov models and selected applications in speech recognition , 1989, Proc. IEEE.

[16]  G. Vachtsevanos,et al.  Particle filter based anomaly detection for aircraft actuator systems , 2009, 2009 IEEE Aerospace conference.

[17]  Larry P. Heck,et al.  Mechanical system monitoring using hidden Markov models , 1991, [Proceedings] ICASSP 91: 1991 International Conference on Acoustics, Speech, and Signal Processing.

[18]  E G Strangas,et al.  Prognosis of electrical faults in permanent magnet AC machines using the hidden Markov model , 2010, IECON 2010 - 36th Annual Conference on IEEE Industrial Electronics Society.