Performance Assessment of a Wind Turbine Using SCADA based Gaussian Process Model

##plugins.themes.bootstrap3.article.main##

##plugins.themes.bootstrap3.article.sidebar##

Published Nov 19, 2020
Ravi Kumar Pandit David Infield

Abstract

Loss of wind turbine power production identified through performance assessment is a useful tool for effective condition monitoring of a wind turbine. Power curves describe the nonlinear relationship between power generation and hub height wind speed and play a significant role in analyzing the performance of a turbine.
Performance assessment using nonparametric models is gaining popularity. A Gaussian Process is a nonlinear, non-parametric probabilistic approach widely used for fitting models and forecasting applications due to its flexibility and mathematical simplicity. Its applications extended to both classification and regression related problems. Despite promising results, Gaussian Process application in wind turbine condition monitoring is limited.
In this paper, a model based on a Gaussian Process developed for assessing the performance of a turbine. Here, a reference power curve using SCADA datasets from a healthy turbine is developed using a Gaussian Process and then was compared with a power curve from an unhealthy turbine. Error due to yaw misalignment is a standard issue with a wind turbine, which causes underperformance. Hence it is used as case study to test and validate the algorithm effectiveness.

Abstract 35 | PDF Downloads 32

##plugins.themes.bootstrap3.article.details##

Keywords

condition monitoring, Wind Turbine, power curve, Gaussian Processes, Predictive Models Evaluation, nonparametric models, performance assessments

References
Hyers, R. W et al.,2006. Condition Monitoring and Prognosis of Utility Scale Wind Turbines. Energy Materials, vol. 1, no. 3. pp. 187-203.
Zaher, A et al.,2009. Online wind turbine fault detection through automated SCADA data analysis. Wind Energy., 12: 574–593. doi:10.1002/we.319.
Martin, R et al., 2016.Sensitivity analysis of offshore wind farm operation and maintenance cost and availability. Renewable Energy, 85, pp. 1226-1236.
M. Lydia et al., 2014. A comprehensive review on wind turbine power curve modeling techniques. Renew. Sustain. Energy Rev., 30, pp. 452-460.
S. Shokrzadeh et al., 2014. Wind Turbine Power Curve Modeling Using Advanced Parametric and Nonparametric Methods. IEEE Transactions on Sustainable Energy, vol.5, no.4, pp.1262-269.doi: 10.1109/TSTE.2014.2345059.
Thapar V et al.,2011. Critical analysis of methods for mathematical modelling of wind turbines. Renew Energy,36:3166–77. http://dx.doi.org/10.1155/2016/8519785.
Leszek Romański et al.,2017. Estimation of operational parameters of the counter-rotating wind turbine with artificial neural networks. Archives of Civil and Mechanical Engineering, Volume 17, Issue 4, Pages 1019-1028.
Lorenzo Dambrosio.,2017. Data-based Fuzzy Logic Control Technique Applied to a Wind System. Energy Procedia, Volume 126, Pages 690-697.
Raik Becker et al.,2017. Completion of wind turbine datasets for wind integration studies applying random forests and k-nearest neighbors. Applied Energy, Volume 208, Pages 252-262.
T. Ouyanga et al.,2017. Modelling wind-turbine power curve: a data partitioning and mining approach Renew. Energy, 01102 (A), pp. 1-8.
Y. Wang & D. Infield.,2013. Supervisory control and data acquisition data-based non-linear state estimation technique for wind turbine gearbox condition monitoring. IET Renewable Power Generation, vol. 7, no. 4, pp. 350-358, doi: 10.1049/iet-rpg.2012.0215.
Y. Si et al.,2017, A data-driven approach for fault detection of offshore wind turbines using random forests. IECON 2017 - 43rd Annual Conference of the IEEE Industrial Electronics Society, Beijing, China, pp. 3149-3154. doi: 10.1109/IECON.2017.8216532.
R. K. Pandit & D. Infield.,2017. Using Gaussian Process theory for wind turbine power curve analysis with emphasis on the confidence intervals. 6th International Conference on Clean Electrical Power (ICCEP), Santa Margherita Ligure, pp.744-749. doi: 10.1109/ICCEP.2017.8004774.
Neal, R. M.,1994. Bayesian Learning for Neural Networks. PhD thesis, University of Toronto, Canada.
C. E. Rasmussen & C. K. I. Williams., 2006.Gaussian Processes for Machine Learning, the MIT Press, ISBN 026218253X.
Xueru Wang et al.,2014. Wind turbine gearbox forecast using Gaussian Process model. Control and Decision Conference, The 26th Chinese.
Niya Chen et al.,2013. Short-Term Wind Power Forecasting Using Gaussian Processes, Twenty-Third International Joint Conference on Artificial Intelligence.
Kim K et al., 2011. Use of SCADA data for failure detection in wind turbines. Energy Sustainability Conference and Fuel Cell Conference, NREL/CP-5000-51653.
Kusiak A & Zhang Z., 2010. Analysis of wind turbine vibrations based on SCADA data. J Sol Energy Eng. doi:10.1115/1.4001461.
P. Dao et al.,2018. Condition monitoring and fault detection in wind turbines based on cointegration analysis of SCADA data. Renew. Energy, 116 (Part B), pp. 107-122.
Zaher AS et al., 2007.A multi-agent fault detection system for wind turbine defect recognition and diagnosis. IEEE Lausanne Power Tech, pp:22–27.
M. Schlechngen & I. F. Santos.,2011. Comparative analysis of neural network and regression based condition monitoring approaches for wind turbine fault detection. Mech. Syst. Signal Process., vol. 25, no. 5, pp. 1849–1875.
IEC 61400-12-1., 2006.Wind Turbines—Part 12-1: Power Performance Measurements of Electricity Producing Wind Turbines, British Standard,
Vaishali Sohoni et al.,2016. A Critical Review of Wind Turbine Power Curve Modelling Techniques and Their Applications in Wind Based Energy Systems. Journal of Energy, Article ID 8519785, 18 pages, doi:10.1155/2016/8519785.
Avent lidar technology., 2013. Flexible solutions to optimize turbine performance. Available online at http://www.aventlidartechnology.com/en/applications/yaw-error-correction_116.html.
J. G. Schepers.,2007. Dynamic Inflow effects at fast pitching steps on a wind turbine placed in the NASA-Ames wind tunnel. ECN Reports.
K. Boorsma., 2012.Power and loads for yawed flow conditions. ECN Reports.
M. Spencer et al.,2013. Predictive yaw control of a 5MW wind turbine model. AIAA Aerospace Sciences Meeting Including the New Horizons Forum and Aerospace Exposition.
K. A. Kragh & P. Fleming., 2012.Rotor speed dependent yaw control of wind turbines based on empirical data. AIAA Aerospace Sciences Meeting Including the New Horizons Forum and Aerospace Exposition.
Song, D et al., 2017. Wind direction prediction for yaw control of wind turbines. Int. J. Control Autom. Syst. 15: 1720. https://doi.org/10.1007/s12555-017-0289-6.
PMO Gebraad et al.,2016. Wind plant power optimization through yaw control using a parametric model for wake effects—a cfd simulation study. Wind Energy, 19(1):95–114.
Jinkyoo Park & Kincho H Law., 2015. A Bayesian optimization approach for wind farm power maximization. In SPIE Smart Structures and Materials+ Nondestructive Evaluation and Health Monitoring, pp 943608– 943608. International Society for Optics and Photonics.
Ping Li & Songcan Chen., 2016.Gaussian Process Latent Variable Models. CAAI Transactions on Intelligence Technology. Volume 1, Issue 4, pp 366-376.
J. Hartikainen et al., 2010.Kalman filtering and smoothing solutions to temporal Gaussian Process regression models. IEEE International Workshop on Machine Learning for Signal Processing.
S. Sarkka et al., 2013.Spatiotemporal learning via infinite-dimensional Bayesian filtering and smoothing. IEEE Signal Processing Magazine, vol. 30, no. 4, pp. 51–61.
Jie Chen & Nannan Cao., 2013.Parallel Gaussian Process Regression with Low-Rank Covariance Matrix Approximations. Proceedings of the Twenty-Ninth Conference on Uncertainty in Artificial Intelligence (UAI2013). https://arxiv.org/abs/1408.2060.
Neyman, J., 1937.Outline of a Theory of Statistical Estimation Based on the Classical Theory of Probability. Philosophical Transactions of the Royal Society A. 236: 333–380. doi:10.1098/rsta.1937.0005.
Alain Bensoussan et al., 2014.Confidence intervals for annual wind power production. ESAIM: Proc., 44,pp 150-158. doi: https://doi.org/10.1051/proc/201444009.
Breno Menezes.,2014. Creating Confidence Intervals for Reservoir Computing’s Wind Power Forecast Use of Maximum Likelihood Method and the Distribution-based Method. COGNITIVE 2014: The Sixth International Conference on Advanced Cognitive Technologies and Applications.
Andrew McHutchon & Carl Edward Rasmussen.,2011. Gaussian Process Training with Input Noise. http://mlg.eng.cam.ac.uk/mchutchon/papers/NIGP.pdf.
Section
Technical Papers