Bearing temperature monitoring of a Wind Turbine using physics-based model

Purpose The purpose of this paper is to propose a method to monitor a Wind Turbine’s (WT) main bearing, based on the difference between the temperature as measured by the Supervisory Control and Data Acquisition system (SCADA). Design/methodology/approach The monitoring of the main bearing is based on the difference between the measured temperature and the estimated temperature obtained from a dynamic model. The model used is based on the law of energy conservation. Several validation metrics have suggested that this model is accurate. Findings The Exponentially Weighted Moving Average control chart for two cases studies is used for the monitoring for the main bearing; this method has shown great potential for industrial applications. A failure was detected three weeks before the current actual alarm settings used by SCADA were able to identify the issue. Originality/value The proposed method is a monitoring method that can be used on most industrial wind farms and provide important information on the condition of the WTs’ main bearing.

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

[2]  Christophe Bérenguer,et al.  Using SCADA Data for Fault Detection in Wind Turbines: Local Internal Model Versus Distance to a Wind Farm Reference , 2014 .

[3]  S. W. Roberts.  Control chart tests based on geometric moving averages , 2000 .

[4]  Zijun Zhang,et al.  Wind turbine gearbox failure monitoring based on SCADA data analysis , 2016, 2016 IEEE Power and Energy Society General Meeting (PESGM).

[5]  Ming-Hung Shu,et al.  A comparative study of the monitoring performance for weighted control charts , 2009 .

[6]  Zijun Zhang,et al.  Fault Analysis and Condition Monitoring of the Wind Turbine Gearbox , 2012, IEEE Transactions on Energy Conversion.

[7]  Charles W. Champ,et al.  The Performance of Exponentially Weighted Moving Average Charts With Estimated Parameters , 2001, Technometrics.

[8]  Y. Amirat,et al.  Wind turbine bearing failure detection using generator stator current homopolar component ensemble empirical mode decomposition , 2012, IECON 2012 - 38th Annual Conference on IEEE Industrial Electronics Society.

[9]  Hoo Sang Ko,et al.  Artificial Neural Network and EWMA-based Fault Prediction in Wind Turbines , 2014 .

[10]  S. Steiner.  EWMA Control Charts with Time-Varying Control Limits and Fast Initial Response , 1999 .

[11]  Andrew Kusiak,et al.  Analyzing bearing faults in wind turbines: A data-mining approach , 2012 .

[12]  Wei Jiang,et al.  A One-Sided EWMA Control Chart for Monitoring Process Means , 2007, Commun. Stat. Simul. Comput..

[13]  Mohamed Benbouzid,et al.  A Brief Status on Condition Monitoring and Fault Diagnosis in Wind Energy Conversion Systems , 2009 .

[14]  James M. Lucas,et al.  Exponentially weighted moving average control schemes: Properties and enhancements , 1990 .

[15]  Zhong Guo Bian,et al.  Wind Turbine On-Line Monitoring System Based on Vibration Mechanics , 2012 .

[16]  Tomasz Barszcz,et al.  Diagnostics of bearings in presence of strong operating conditions non-stationarity—A procedure of load-dependent features processing with application to wind turbine bearings , 2014 .

[17]  Simon J. Watson,et al.  Physics of Failure approach to wind turbine condition based maintenance , 2009 .

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

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

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

[21]  Sung-Hoon Ahn,et al.  Condition monitoring and fault detection of wind turbines and related algorithms: A review , 2009 .

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