On the use of high-frequency SCADA data for improved wind turbine performance monitoring

SCADA-based condition monitoring of wind turbines facilitates the move from costly corrective repairs towards more proactive maintenance strategies. In this work, we advocate the use of high-frequency SCADA data and quantile regression to build a cost effective performance monitoring tool. The benefits of the approach are demonstrated through the comparison between state-of-the-art deterministic power curve modelling techniques and the suggested probabilistic model. Detection capabilities are compared for low and high-frequency SCADA data, providing evidence for monitoring at higher resolutions. Operational data from healthy and faulty turbines are used to provide a practical example of usage with the proposed tool, effectively achieving the detection of an incipient gearbox malfunction at a time horizon of more than one month prior to the actual occurrence of the failure.

[1]  Ian Witten,et al.  Data Mining , 2000 .

[2]  Nicolai Meinshausen,et al.  Quantile Regression Forests , 2006, J. Mach. Learn. Res..

[3]  Ioannis Antoniou,et al.  The influence of the wind speed profile on wind turbine performance measurements , 2009 .

[4]  Andrew Kusiak,et al.  On-line monitoring of power curves , 2009 .

[5]  B. K. Panigrahi,et al.  ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE , 2010 .

[6]  B. Stephen,et al.  Wind Turbine Condition Assessment Through Power Curve Copula Modeling , 2012, IEEE Transactions on Sustainable Energy.

[7]  Mayorkinos Papaelias,et al.  Condition monitoring of wind turbines: Techniques and methods , 2012 .

[8]  M. Lydia,et al.  Advanced Algorithms for Wind Turbine Power Curve Modeling , 2013, IEEE Transactions on Sustainable Energy.

[9]  Andrew Kusiak,et al.  Prediction, operations, and condition monitoring in wind energy , 2013 .

[10]  M. Schlechtingen,et al.  Using Data-Mining Approaches for Wind Turbine Power Curve Monitoring: A Comparative Study , 2013, IEEE Transactions on Sustainable Energy.

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

[12]  อนิรุธ สืบสิงห์,et al.  Data Mining Practical Machine Learning Tools and Techniques , 2014 .

[13]  Allan May,et al.  Economic analysis of condition monitoring systems for offshore wind turbine sub-systems , 2014 .

[14]  Jin Zhou,et al.  Modeling of wind turbine power curve based on Gaussian process , 2014, 2014 International Conference on Machine Learning and Cybernetics.

[15]  K. Fristrup,et al.  A geospatial model of ambient sound pressure levels in the contiguous United States. , 2012, The Journal of the Acoustical Society of America.

[16]  Yingning Qiu,et al.  Wind turbine condition monitoring: technical and commercial challenges , 2014 .

[17]  Daniel Karlsson.  Wind Turbine Performance Monitoring using Artificial Neural Networks With a Multi-Dimensional Data Filtering Approach , 2015 .

[18]  Julio J. Melero,et al.  SCADA alarms processing for wind turbine component failure detection , 2016 .

[19]  Bri-Mathias Hodge,et al.  A data-driven method to characterize turbulence-caused uncertainty in wind power generation , 2016 .

[20]  Julio J. Melero,et al.  Wind Turbine Failures - Tackling current Problems in Failure Data Analysis , 2016 .

[21]  Antoine Tahan,et al.  Power curve monitoring using weighted moving average control charts , 2016 .

[22]  Rik Van de Walle,et al.  Data-driven multivariate power curve modeling of offshore wind turbines , 2016, Eng. Appl. Artif. Intell..

[23]  Mostafa Modiri-Delshad,et al.  Development of an enhanced parametric model for wind turbine power curve , 2016 .

[24]  David McMillan,et al.  Availability, operation and maintenance costs of offshore wind turbines with different drive train configurations , 2017 .

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