An insight into wind turbine planet bearing fault prediction using SCADA data

Condition based maintenance is being adopted into the decision making process of wind farms, in order to reduce operation costs. SCADA systems are integrated in wind turbines, providing  low frequency operational data and are increasingly being used in condition monitoring. The aim of this paper is to explore how can wind turbine gearbox components be monitored using SCADA data. The proposed methodology utilises 10-minute averaged data. Data preprocessing is applied using a clustering filter in order to improve prediction confidence. Normal behaviour models are used to predict potential faults. The efficacy of the proposed methodology is demonstrated with a case study using SCADA data from three operating wind turbines that have a double planetary stage gearbox. Historic data is collected for more than a year before the occurrence of a bearing failure on a planet of the first planetary stage. The case study results indicate the potential importance of generator speed estimation for planet bearing faults. A successful prediction of the bearing health state can be performed through this model and some insight is given into into the optimal SCADA sensors utilization for this type of failure mode.

[1]  Yingning Qiu,et al.  Monitoring wind turbine gearboxes , 2013 .

[2]  J. R. McDonald,et al.  A multi-agent condition monitoring architecture to support transmission and distribution asset management , 2005 .

[3]  A. Kusiak,et al.  Monitoring Wind Farms With Performance Curves , 2013, IEEE Transactions on Sustainable Energy.

[4]  Yingning Qiu,et al.  Use of SCADA and CMS signals for failure detection and diagnosis of a wind turbine gearbox , 2011 .

[5]  Simon J. Watson,et al.  Using SCADA data for wind turbine condition monitoring – a review , 2017 .

[6]  David Infield,et al.  Online wind turbine fault detection through automated SCADA data analysis , 2009 .

[7]  Wenxian Yang,et al.  Wind turbine condition monitoring by the approach of SCADA data analysis , 2013 .

[8]  Simon J. Watson,et al.  A model-based approach to wind turbine condition monitoring using SCADA data , 2009 .

[9]  Meik Schlechtingen,et al.  Comparative analysis of neural network and regression based condition monitoring approaches for wind turbine fault detection , 2011 .

[10]  Lionel Tarassenko,et al.  Novelty detection for the identification of abnormalities , 2000, Int. J. Syst. Sci..

[11]  Miguel Ángel Sanz Bobi,et al.  SIMAP: Intelligent System for Predictive Maintenance: Application to the health condition monitoring of a windturbine gearbox , 2006 .

[12]  Lior Rokach,et al.  Data Mining And Knowledge Discovery Handbook , 2005 .

[13]  Vladimir N. Vapnik,et al.  The Nature of Statistical Learning Theory , 2000, Statistics for Engineering and Information Science.

[14]  Jason Weston,et al.  Support vector machines for multi-class pattern recognition , 1999, ESANN.

[15]  Paul Fleming,et al.  Use of SCADA Data for Failure Detection in Wind Turbines , 2011 .

[16]  Lior Rokach,et al.  Clustering Methods , 2005, The Data Mining and Knowledge Discovery Handbook.

[17]  Michael Wilkinson,et al.  Comparison of methods for wind turbine condition monitoring with SCADA data , 2014 .

[18]  Pramod Bangalore,et al.  An artificial neural network‐based condition monitoring method for wind turbines, with application to the monitoring of the gearbox , 2017 .