Articles | Volume 8, issue 6
https://doi.org/10.5194/wes-8-893-2023
© Author(s) 2023. This work is distributed under
the Creative Commons Attribution 4.0 License.
the Creative Commons Attribution 4.0 License.
https://doi.org/10.5194/wes-8-893-2023
© Author(s) 2023. This work is distributed under
the Creative Commons Attribution 4.0 License.
the Creative Commons Attribution 4.0 License.
Review article
| 
05 Jun 2023
Review article |
| 05 Jun 2023
| 05 Jun 2023
Overview of normal behavior modeling approaches for SCADA-based wind turbine condition monitoring demonstrated on data from operational wind farms
Xavier Chesterman
CORRESPONDING AUTHOR
Artificial Intelligence Lab, Vrije Universiteit Brussel, Pleinlaan 9, 3rd floor, 1050 Brussels, Belgium
Timothy Verstraeten
Artificial Intelligence Lab, Vrije Universiteit Brussel, Pleinlaan 9, 3rd floor, 1050 Brussels, Belgium
Pieter-Jan Daems
AVRG, Vrije Universiteit Brussel, Pleinlaan 3, 1050 Brussels, Belgium
Ann Nowé
Artificial Intelligence Lab, Vrije Universiteit Brussel, Pleinlaan 9, 3rd floor, 1050 Brussels, Belgium
Jan Helsen
AVRG, Vrije Universiteit Brussel, Pleinlaan 3, 1050 Brussels, Belgium
Related authors
Ivo Vervlimmeren, Xavier Chesterman, Timothy Verstraeten, Ann Nowé, and Jan Helsen
Wind Energ. Sci. Discuss., https://doi.org/10.5194/wes-2025-49, https://doi.org/10.5194/wes-2025-49, 2025
Revised manuscript under review for WES
Short summary
Short summary
We introduce a new method to refine failure prediction for wind turbines, leading to better and more efficient alarming. We do this by filtering detected anomalies based on the anomalies from the whole fleet. We compare submethods and find one that removes up to 65 % of detected anomalies while leaving the failure-predicting ones. We also detail how we trained the model that generated these anomalies and discuss the construction of the scalable pipeline that was used to deploy such models.
Simon Daenens, Timothy Verstraeten, Pieter-Jan Daems, Ann Nowé, and Jan Helsen
Wind Energ. Sci., 10, 1137–1152, https://doi.org/10.5194/wes-10-1137-2025, https://doi.org/10.5194/wes-10-1137-2025, 2025
Short summary
Short summary
This study presents a novel model for predicting wind turbine power output at a high temporal resolution in wind farms using a hybrid graph neural network (GNN) and long short-term memory (LSTM) architecture. By modeling the wind farm as a graph, the model captures both spatial and temporal dynamics, outperforming traditional power curve methods. Integrated with a normal behavior model (NBM) framework, the model effectively identifies and analyzes power loss events.
Ivo Vervlimmeren, Xavier Chesterman, Timothy Verstraeten, Ann Nowé, and Jan Helsen
Wind Energ. Sci. Discuss., https://doi.org/10.5194/wes-2025-49, https://doi.org/10.5194/wes-2025-49, 2025
Revised manuscript under review for WES
Short summary
Short summary
We introduce a new method to refine failure prediction for wind turbines, leading to better and more efficient alarming. We do this by filtering detected anomalies based on the anomalies from the whole fleet. We compare submethods and find one that removes up to 65 % of detected anomalies while leaving the failure-predicting ones. We also detail how we trained the model that generated these anomalies and discuss the construction of the scalable pipeline that was used to deploy such models.
Stijn Ally, Timothy Verstraeten, Pieter-Jan Daems, Ann Nowé, and Jan Helsen
Wind Energ. Sci., 10, 779–812, https://doi.org/10.5194/wes-10-779-2025, https://doi.org/10.5194/wes-10-779-2025, 2025
Short summary
Short summary
Wind farms are crucial for a sustainable energy future. However, their power can fluctuate significantly due to changing weather conditions, which complexly affect their power generation. This paper presents a novel machine-learning-based method to enhance wind farm power predictions, enabling improved power scheduling, trading and grid balancing. This makes wind power more valuable and easier to integrate into the energy system.
Konstantinos Vratsinis, Rebeca Marini, Pieter-Jan Daems, Lukas Pauscher, Jeroen van Beeck, and Jan Helsen
Wind Energ. Sci. Discuss., https://doi.org/10.5194/wes-2025-32, https://doi.org/10.5194/wes-2025-32, 2025
Preprint under review for WES
Short summary
Short summary
Using data collected over 13 months at an offshore wind farm, our study shows that a wind turbine’s position within the farm influences its energy output at a given wind speed. Front-row turbines respond differently to similar wind speeds and turbulence than those further back. This finding suggests that current methods for characterizing inflow conditions may not fully capture actual wind behavior, underscoring the need for improved performance analysis techniques.
Jakob Gebel, Ashkan Rezaei, Adithya Vemuri, Veronica Liverud Krathe, Pieter-Jan Daems, Jens Jo Matthys, Jonathan Sterckx, Konstantinos Vratsinis, Kayacan Kestel, Amir R. Nejad, and Jan Helsen
Wind Energ. Sci. Discuss., https://doi.org/10.5194/wes-2024-173, https://doi.org/10.5194/wes-2024-173, 2025
Preprint under review for WES
Short summary
Short summary
A simulation model of a deployed offshore wind turbine was developed using real-world measurement data. The method shows how to obtain, update and validate a simulation model and allows to improve the efficiency and longevity of offshore wind turbines and support operation and maintenance decisions. Simulations were conducted to analyze the effects of turbulence and wind patterns on turbine lifespan, providing insights to improve maintenance planning and reduce operational costs.
Rebeca Marini, Konstantinos Vratsinis, Kayacan Kestel, Jonathan Sterckx, Jens Matthys, Pieter-Jan Daems, Timothy Verstraeten, and Jan Helsen
Wind Energ. Sci. Discuss., https://doi.org/10.5194/wes-2025-9, https://doi.org/10.5194/wes-2025-9, 2025
Revised manuscript not accepted
Short summary
Short summary
This work evaluated the wind profile in a Belgian offshore zone. The estimated wind profile was made using measurements that allow for reconstruction at heights along the rotor area. The IEC standard defines these profiles as a 1/7th power law, which is proven not to occur 100 % of the time. It is also possible to infer that there will be differences when using different wind profiles for load assessment, as more realistic profiles can lead to a better assessment of the wind turbine's lifetime.
Faras Jamil, Cédric Peeters, Timothy Verstraeten, and Jan Helsen
Wind Energ. Sci. Discuss., https://doi.org/10.5194/wes-2024-114, https://doi.org/10.5194/wes-2024-114, 2024
Revised manuscript accepted for WES
Short summary
Short summary
A hybrid fault detection method is proposed, which combines physical domain knowledge with machine learning models to automatically detect mechanical faults in wind turbine drivetrain components. It offers detailed insights for experts while giving operators a high-level overview of the machine's health to assist in planning effective maintenance strategies. It was validated on multiple years of wind farm data and the potential faults were accurately predicted, which was confirmed by experts.
Diederik van Binsbergen, Pieter-Jan Daems, Timothy Verstraeten, Amir R. Nejad, and Jan Helsen
Wind Energ. Sci., 9, 1507–1526, https://doi.org/10.5194/wes-9-1507-2024, https://doi.org/10.5194/wes-9-1507-2024, 2024
Short summary
Short summary
Wind farm yield assessment often relies on analytical wake models. Calibrating these models can be challenging due to the stochastic nature of wind. We developed a calibration framework that performs a multi-phase optimization on the tuning parameters using time series SCADA data. This yields a parameter distribution that more accurately reflects reality than a single value. Results revealed notable variation in resultant parameter values, influenced by nearby wind farms and coastal effects.
Adithya Vemuri, Sophia Buckingham, Wim Munters, Jan Helsen, and Jeroen van Beeck
Wind Energ. Sci., 7, 1869–1888, https://doi.org/10.5194/wes-7-1869-2022, https://doi.org/10.5194/wes-7-1869-2022, 2022
Short summary
Short summary
The sensitivity of the WRF mesoscale modeling framework in accurately representing and predicting wind-farm-level environmental variables for three extreme weather events over the Belgian North Sea is investigated in this study. The overall results indicate highly sensitive simulation results to the type and combination of physics parameterizations and the type of the weather phenomena, with indications that scale-aware physics parameterizations better reproduce wind-related variables.
Amir R. Nejad, Jonathan Keller, Yi Guo, Shawn Sheng, Henk Polinder, Simon Watson, Jianning Dong, Zian Qin, Amir Ebrahimi, Ralf Schelenz, Francisco Gutiérrez Guzmán, Daniel Cornel, Reza Golafshan, Georg Jacobs, Bart Blockmans, Jelle Bosmans, Bert Pluymers, James Carroll, Sofia Koukoura, Edward Hart, Alasdair McDonald, Anand Natarajan, Jone Torsvik, Farid K. Moghadam, Pieter-Jan Daems, Timothy Verstraeten, Cédric Peeters, and Jan Helsen
Wind Energ. Sci., 7, 387–411, https://doi.org/10.5194/wes-7-387-2022, https://doi.org/10.5194/wes-7-387-2022, 2022
Short summary
Short summary
This paper presents the state-of-the-art technologies and development trends of wind turbine drivetrains – the energy conversion systems transferring the kinetic energy of the wind to electrical energy – in different stages of their life cycle: design, manufacturing, installation, operation, lifetime extension, decommissioning and recycling. The main aim of this article is to review the drivetrain technology development as well as to identify future challenges and research gaps.
Related subject area
Thematic area: Materials and operation | Topic: Operation and maintenance, condition monitoring, reliability
A machine-learning-based approach for active monitoring of blade pitch misalignment in wind turbines
On the modeling errors of digital twins for load monitoring and fatigue assessment in wind turbine drivetrains
Leveraging Signal Processing and Machine Learning for Automated Fault Detection in Wind Turbine Drivetrains
Machine-learning-based virtual load sensors for mooring lines using simulated motion and lidar measurements
Unsupervised anomaly detection of permanent-magnet offshore wind generators through electrical and electromagnetic measurements
Full-scale wind turbine performance assessment using the turbine performance integral (TPI) method: a study of aerodynamic degradation and operational influences
Operation and maintenance cost comparison between 15 MW direct-drive and medium-speed offshore wind turbines
Sensitivity of fatigue reliability in wind turbines: effects of design turbulence and the Wöhler exponent
Active trailing edge flap system fault detection via machine learning
Grand challenges in the digitalisation of wind energy
Assessing the rotor blade deformation and tower–blade tip clearance of a 3.4 MW wind turbine with terrestrial laser scanning
Introducing a data-driven approach to predict site-specific leading-edge erosion from mesoscale weather simulations
Population Based Structural Health Monitoring: Homogeneous Offshore Wind Model Development
Wind turbine main-bearing lubrication – Part 2: Simulation-based results for a double-row spherical roller main bearing in a 1.5 MW wind turbine
Reduction of wind-turbine-generated seismic noise with structural measures
Very low frequency IEPE accelerometer calibration and application to a wind energy structure
Sabrina Milani, Jessica Leoni, Stefano Cacciola, Alessandro Croce, and Mara Tanelli
Wind Energ. Sci., 10, 497–510, https://doi.org/10.5194/wes-10-497-2025, https://doi.org/10.5194/wes-10-497-2025, 2025
Short summary
Short summary
In this paper, we propose a novel machine-learning framework for pitch misalignment detection in wind turbines. Using a minimal set of standard sensors, our method detects misalignments as small as 0.1° and localizes the affected blades. It combines signal processing with a hierarchical classification structure and linear regression for precise severity quantification. Evaluation results validate the approach, showing notable accuracy in misalignment classification, regression, and localization.
Felix C. Mehlan and Amir R. Nejad
Wind Energ. Sci., 10, 417–433, https://doi.org/10.5194/wes-10-417-2025, https://doi.org/10.5194/wes-10-417-2025, 2025
Short summary
Short summary
A digital twin is a virtual representation that mirrors the wind turbine's real behavior through simulation models and sensor measurements and can assist in making key decisions such as planning the replacement of parts. These models and measurements are, of course, not perfect and only give an incomplete picture of the real behavior. This study investigates how large the uncertainty of such models and measurements is and to what extent it affects the decision-making process.
Faras Jamil, Cédric Peeters, Timothy Verstraeten, and Jan Helsen
Wind Energ. Sci. Discuss., https://doi.org/10.5194/wes-2024-114, https://doi.org/10.5194/wes-2024-114, 2024
Revised manuscript accepted for WES
Short summary
Short summary
A hybrid fault detection method is proposed, which combines physical domain knowledge with machine learning models to automatically detect mechanical faults in wind turbine drivetrain components. It offers detailed insights for experts while giving operators a high-level overview of the machine's health to assist in planning effective maintenance strategies. It was validated on multiple years of wind farm data and the potential faults were accurately predicted, which was confirmed by experts.
Moritz Gräfe, Vasilis Pettas, Nikolay Dimitrov, and Po Wen Cheng
Wind Energ. Sci., 9, 2175–2193, https://doi.org/10.5194/wes-9-2175-2024, https://doi.org/10.5194/wes-9-2175-2024, 2024
Short summary
Short summary
This study explores a methodology using floater motion and nacelle-based lidar wind speed measurements to estimate the tension and damage equivalent loads (DELs) on floating offshore wind turbines' mooring lines. Results indicate that fairlead tension time series and DELs can be accurately estimated from floater motion time series. Using lidar measurements as model inputs for DEL predictions leads to similar accuracies as using displacement measurements of the floater.
Ali Dibaj, Mostafa Valavi, and Amir R. Nejad
Wind Energ. Sci., 9, 2063–2086, https://doi.org/10.5194/wes-9-2063-2024, https://doi.org/10.5194/wes-9-2063-2024, 2024
Short summary
Short summary
This study emphasizes the need for effective condition monitoring in permanent magnet offshore wind generators to tackle issues like demagnetization and eccentricity. Utilizing a machine learning model and high-resolution measurements, we explore methods of early fault detection. Our findings indicate that flux monitoring with affordable, easy-to-install stray flux sensors with frequency information offers a promising fault detection strategy for large megawatt-scale offshore wind generators.
Tahir H. Malik and Christian Bak
Wind Energ. Sci., 9, 2017–2037, https://doi.org/10.5194/wes-9-2017-2024, https://doi.org/10.5194/wes-9-2017-2024, 2024
Short summary
Short summary
We explore the effect of blade modifications on offshore wind turbines' performance through a detailed analysis of 12 turbines over 12 years. Introducing the turbine performance integral method, which utilises time-series decomposition that combines various data sources, we uncover how blade wear, repairs and software updates impact efficiency. The findings offer valuable insights into improving wind turbine operations, contributing to the enhancement of renewable energy technologies.
Orla Donnelly, Fraser Anderson, and James Carroll
Wind Energ. Sci., 9, 1345–1362, https://doi.org/10.5194/wes-9-1345-2024, https://doi.org/10.5194/wes-9-1345-2024, 2024
Short summary
Short summary
We collate the latest reliability data in operations and maintenance (O&M) for offshore wind turbines, specifically large turbines of 15 MW. We use these data to model O&M of an offshore wind farm at three different sites. We compare two industry-dominant drivetrain configurations in terms of O&M cost for 15 MW turbines and determine if previous results for smaller turbines still hold true. Comparisons between drivetrains are topical within industry, and we produce cost comparisons for them.
Shadan Mozafari, Paul Veers, Jennifer Rinker, and Katherine Dykes
Wind Energ. Sci., 9, 799–820, https://doi.org/10.5194/wes-9-799-2024, https://doi.org/10.5194/wes-9-799-2024, 2024
Short summary
Short summary
Turbulence is one of the main drivers of fatigue in wind turbines. There is some debate on how to model the turbulence in normal wind conditions in the design phase. To address such debates, we study the fatigue load distribution and reliability following different models of the International Electrotechnical Commission 61400-1 standard. The results show the lesser importance of load uncertainty due to turbulence distribution compared to the uncertainty of material resistance and Miner’s rule.
Andrea Gamberini and Imad Abdallah
Wind Energ. Sci., 9, 181–201, https://doi.org/10.5194/wes-9-181-2024, https://doi.org/10.5194/wes-9-181-2024, 2024
Short summary
Short summary
Active trailing edge flaps can potentially reduce wind turbine (WT) loads. To monitor their performance, we present two methods based on machine learning that identify flap health states, including degraded performance, in normal power production and idling condition. Both methods rely only on sensors commonly available on WTs. One approach properly detects all the flap states if a fault occurs on only one blade. The other approach can identify two specific flap states in all fault scenarios.
Andrew Clifton, Sarah Barber, Andrew Bray, Peter Enevoldsen, Jason Fields, Anna Maria Sempreviva, Lindy Williams, Julian Quick, Mike Purdue, Philip Totaro, and Yu Ding
Wind Energ. Sci., 8, 947–974, https://doi.org/10.5194/wes-8-947-2023, https://doi.org/10.5194/wes-8-947-2023, 2023
Short summary
Short summary
Wind energy creates huge amounts of data, which can be used to improve plant design, raise efficiency, reduce operating costs, and ease integration. These all contribute to cheaper and more predictable energy from wind. But realising the value of data requires a digital transformation that brings
grand challengesaround data, culture, and coopetition. This paper describes how the wind energy industry could work with R&D organisations, funding agencies, and others to overcome them.
Paula Helming, Alex Intemann, Klaus-Peter Webersinke, Axel von Freyberg, Michael Sorg, and Andreas Fischer
Wind Energ. Sci., 8, 421–431, https://doi.org/10.5194/wes-8-421-2023, https://doi.org/10.5194/wes-8-421-2023, 2023
Short summary
Short summary
Using renewable energy such as wind energy is vital. To optimize the energy yield from wind turbines, they have increased in size, leading to large blade deformations. This paper measures these deformations for different wind loads and the distance between the blade and the tower from 170 m away from the wind turbine. The paper proves that the blade deformation increases in the wind direction with increasing wind speed, while the distance between the blade and the tower decreases.
Jens Visbech, Tuhfe Göçmen, Charlotte Bay Hasager, Hristo Shkalov, Morten Handberg, and Kristian Pagh Nielsen
Wind Energ. Sci., 8, 173–191, https://doi.org/10.5194/wes-8-173-2023, https://doi.org/10.5194/wes-8-173-2023, 2023
Short summary
Short summary
This paper presents a data-driven framework for modeling erosion damage based on real blade inspections and mesoscale weather data. The outcome of the framework is a machine-learning-based model that can predict and/or forecast leading-edge erosion damage based on weather data and user-specified wind turbine characteristics. The model output fits directly into the damage terminology used by the industry and can therefore support site-specific maintenance planning and scheduling of repairs.
Innes Murdo Black, Moritz Werther Häckell, and Athanasios Kolios
Wind Energ. Sci. Discuss., https://doi.org/10.5194/wes-2022-93, https://doi.org/10.5194/wes-2022-93, 2022
Revised manuscript accepted for WES
Short summary
Short summary
Population based structural health monitoring is a low-cost monitoring campaign. The cost reduction from this type of digital enabled asset management tool is manifested by sharing information, in this case a wind farm foundation, within the population. By sharing the information in the wind farm this reduces the amount of sensors and physical model updating, reducing the cost of the monitoring campaign.
Edward Hart, Elisha de Mello, and Rob Dwyer-Joyce
Wind Energ. Sci., 7, 1533–1550, https://doi.org/10.5194/wes-7-1533-2022, https://doi.org/10.5194/wes-7-1533-2022, 2022
Short summary
Short summary
This paper is the second in a two-part study on lubrication in wind turbine main bearings. Investigations are conducted concerning lubrication in the double-row spherical roller main bearing of a 1.5 MW wind turbine. This includes effects relating to temperature, starvation, grease-thickener interactions and possible non-steady EHL effects. Results predict that the modelled main bearing would be expected to operate under mixed lubrication conditions for a non-negligible proportion of its life.
Rafael Abreu, Daniel Peter, and Christine Thomas
Wind Energ. Sci., 7, 1227–1239, https://doi.org/10.5194/wes-7-1227-2022, https://doi.org/10.5194/wes-7-1227-2022, 2022
Short summary
Short summary
In order to find consensus between wind energy producers and seismologists, we study the possibility of reducing wind turbine noise recorded at seismological stations. We find that drilling half-circular holes in front of the wind turbines helps to reduce the seismic noise. We also study the influence of topographic effects on seismic noise reduction.
Clemens Jonscher, Benedikt Hofmeister, Tanja Grießmann, and Raimund Rolfes
Wind Energ. Sci., 7, 1053–1067, https://doi.org/10.5194/wes-7-1053-2022, https://doi.org/10.5194/wes-7-1053-2022, 2022
Short summary
Short summary
This work presents a method to use low-noise IEPE sensors in the low-frequency range down to 0.05 Hz. In order to achieve phase and amplitude accuracy with this type of sensor in the low-frequency range, a new calibration procedure for this frequency range was developed. The calibration enables the use of the low-noise IEPE sensors for large structures, such as wind turbines. The calibrated sensors can be used for wind turbine monitoring, such as fatigue monitoring.
Cited articles
Bangalore, P. and Tjernberg, L. B.: Self evolving neural network based algorithm for fault prognosis in wind turbines: A case study, in: 2014 International Conference on Probabilistic Methods Applied to Power Systems (PMAPS), 7–10 July 2014, Durham, 1–6, https://doi.org/10.1109/PMAPS.2014.6960603, 2014. a, b
Bangalore, P. and Tjernberg, L. B.: An Artificial Neural Network Approach for Early Fault Detection of Gearbox Bearings, IEEE T. Smart Grid, 6, 980–987, https://doi.org/10.1109/TSG.2014.2386305, 2015. a, b
Black, I. M., Richmond, M., and Kolios, A.: Condition monitoring systems: a systematic literature review on machine-learning methods improving offshore-wind turbine operational management, International Journal of Sustainable Energy, 40, 923–946, 2021. a
Chesterman, X., Verstraeten, T., Daems, P.-J., Nowé, A., and Helsen, J.: Condition monitoring of wind turbines using machine learning based anomaly detection and statistical techniques for the extraction of “healthy data”, in: Proceedings of the Annual Conference of the PHM Society, 2980, https://doi.org/10.36001/phmconf.2021.v13i1.2980, 2021. a, b, c, d, e, f, g, h
Chesterman, X., Verstraeten, T., Daems, P.-J., Sanjines, F. P., Nowé, A., and Helsen, J.: The detection of generator bearing failures on wind turbines using machine learning based anomaly detection, J. Phys. Conf. Ser., 2265, 032066, https://doi.org/10.1088/1742-6596/2265/3/032066, 2022. a, b, c, d, e, f, g, h, i, j, k, l, m, n
Commission, IEC: Part 12-1: Power performance measurements of electricity producing wind turbines, Wind energy generation systems, 317, IEC 61400-12-1:2022, 2022. a
Cui, Y., Bangalore, P., and Tjernberg, L. B.: An Anomaly Detection Approach Based on Machine Learning and SCADA Data for Condition Monitoring of Wind Turbines, 2018 IEEE International Conference on Probabilistic Methods Applied to Power Systems (PMAPS), 24–28 June 2018, Boise, ID, USA, 1–6, 2018. a, b, c, d
Greco, A., Sheng, S., Keller, J., and Erdemir, A.: Material wear and fatigue in wind turbine systems, Wear, 302, 1583–1591, 2013. a
Helbing, G. and Ritter, M.: Deep Learning for fault detection in wind turbines, Renew. Sust. Energ. Rev., 98, 189–198, 2018. a
Helsen, J.: Review of Research on Condition Monitoring for Improved O&M of Offshore Wind Turbine Drivetrains, Acoust. Aust., 49, 251–258, 2021. a
Jamil, F., Verstraeten, T., Nowé, A., Peeters, C., and Helsen, J.: A deep boosted transfer learning method for wind turbine gearbox fault detection, Renew. Energ., 197, 331–341, 2022. a
Lee, J. and Zhao, F.: Global Wind Report 2022, Global Wind Energy Council, Brussels, 2022. a
Lima, L. A. M., Blatt, A., and Fujise, J.: Wind Turbine Failure Prediction Using SCADA Data, J. Phys. Conf. Ser., 1618, 022017, https://doi.org/10.1088/1742-6596/1618/2/022017, 2020. a
Meyer, A.: Early fault detection with multi-target neural networks, CoRR, arXiv [preprint], https://doi.org/10.48550/arxiv.2106.08957, 2021. a, b, c
Page, E.: A test for a change in a parameter occurring at an unknown point, Biometrika, 42, 523–527, 1955. a
Peng, D., Liu, C., Desmet, W., and Gryllias, K.: Deep Unsupervised Transfer Learning for Health Status Prediction of a Fleet of Wind Turbines with Unbalanced Data, Annual Conference of the PHM Society, 29 November–2 December 2021, 13, 1–11, https://doi.org/10.36001/phmconf.2021.v13i1.3069, 2021. a
Peter, R., Zappalá, D., Schamboeck, V., and Watson, S. J.: Wind turbine generator prognostics using field SCADA data, J. Phys. Conf. Ser., 2265, 032111, https://doi.org/10.1088/1742-6596/2265/3/032111, 2022. a, b, c, d
Pfaffel, S., Faulstich, S., and Rohrig, K.: Performance and Reliability of Wind Turbines: A review, Energies, 10, 1904, 2017. a
Schlechtingen, M., Santos, I. F., and Achiche, S.: Wind turbine condition monitoring based on SCADA data using normal behavior models. Part 1: System description, Appl. Soft Comput., 13, 259–270, 2013. a
Tautz-Weinert, J. and Watson, S. J.: Comparison of different modelling approaches of drive train temperature for the purposes of wind turbine failure detection, J. Phys. Conf. Ser., 753, 1–11, 2016. a
Tautz-Weinert, J. and Watson, S. J.: Using SCADA data for wind turbine condition monitoring – a review, IET Renew. Power Gen., 11, 382–394, 2017. a
Tazi, N., Chatelet, E., and Bouzidi, Y.: Wear Analysis of Wind Turbine Bearings, International Journal of Renewable Energy Research, 7, 2120–2129, 2017. a
van Buren, S. and Groothuis-Oudshoorn, K.: mice: multivariate imputation by chained equations in R, J. Stat. Softw., 45, 1–67, 2011. a
Verstraeten, T., Nowé, A., Keller, J., Guo, Y., Sheng, S., and Helsen, J.: Fleetwide data-enabled reliability improvement of wind turbines, Renew. Sust. Energ. Rev., 109, 428–437, 2019. a
Xiang, L., Yang, X., Hu, A., Su, H., and Wang, P.: Condition monitoring and anomaly detection of wind turbine based on cascaded and bidirectional deep learning networks, Appl. Energ., 305, 117925, https://doi.org/10.1016/j.apenergy.2021.117925, 2022. a, b
Yang, W., Tavner, P. J., Crabtree, C. J., Feng, Y., and Qiu, Y.: Wind turbine condition monitoring: technical and commercial challenges, Wind Energy, 17, 673–693, 2014. a
Zgraggen, J., Ulmer, M., Jarlskog, E., Pizza, G., and Huber, L. G.: Transfer Learning Approaches for Wind Turbine Fault Detection using Deep Learning, PHM Society European Conference, 6, 1–12, 2021. a
Zhongshan, H., Ling, T., Dong, X., Sichao, L., and Yaozhong, W.: Condition monitoring of wind turbine based on copula function and autoregressive neural network, MATEC Web of Conferences, 198, 1–5, 2018. a
Zou, H. and Hastie, T.: Regularization and variable selection via the elastic net, J. Roy. Stat. Soc. B, 67, 301–320, 2005. a
Short summary
This paper reviews and implements several techniques that can be used for condition monitoring and failure prediction for wind turbines using SCADA data. The focus lies on techniques that respond to requirements of the industry, e.g., robustness, transparency, computational efficiency, and maintainability. The end result of this research is a pipeline that can accurately detect three types of failures, i.e., generator bearing failures, generator fan failures, and generator stator failures.
This paper reviews and implements several techniques that can be used for condition monitoring...
Altmetrics
Final-revised paper
Preprint