Condition monitoring systems: a systematic literature review on machine-learning methods improving offshore-wind turbine operational management

Figures & data

Figure 1. The types of machine learning. This is achieved by supervised learning, unsupervised learning, semisupervised learning, or reinforcement learning. Both Supervised and unsupervised can be further distinguished with classification and regression for supervised learning. Finally clustering, dimensionality reduction and Clustering in unsupervised learning.

Figure 2. The transformation from input data into feature space for a greater fit (Gholami and Fakhari 2017).

Table 1. Summary of references relating to the machine learning methods used in the specific types of monitoring and maintenance technique.

	ANN	SVR	K-NN	DBN	GP	Other
Vibrational	Feng, Qin, and Liang (2016)	Ziaja et al. (2016)	Fernández-Francos et al. (2013)			Qiao and Lu (2015b); Sheng (2013); Geropp (1997); Koukoura, Carroll, and Mcdonald (2017); Bach-Andersen, Rømer-Odgaard, and Winther (2018); Ha et al. (2017); Teng, Ding, et al. (2016); Nejad et al. (2014); Zhang, Verma, and Kusiak (2012); Zhu et al. (2018); Lee and Lee (2014); Bouzid et al. (2015)
Trending	Hackell et al. (2016); Wang et al. (2018); Liu et al. (2016)	Kang, Zhang, and Jin (2015)	Kang, Zhang, and Jin (2015)		Skrimpas et al. (2015); Saidi et al. (2018)	Yang, Court, and Jiang (2013); Yang et al. (2014)
Clustering	Catmull (2011); Kim et al. (2011); de Moura et al. (2016); Mazidi et al. (2016); Yu et al. (2019)	Hang, Zhang, and Cheng (2016); Djeziri, Benmoussa, and Sanchez (2018); Zhao et al. (2019)	Möller, Langenkämper, and Nattkemper (2019); Teng, Wang, et al. (2016)	Herp, Pedersen, and Nadimi (2016); Wang, Wang, et al. (2019)		Djeziri, Benmoussa, and Sanchez (2018); Neu et al. (2017)
Normal behavour modelling	Ciulla et al. (2019); Garcia et al. (2006); Bi, Zhou, and Hepburn (2017); Schlechtingen, Santos, and Achiche (2013)				Aamer Bilal Asghar Xiaodong Liu (2019); Tabib et al. (2017)
Damage Modelling	Bangalore and Tjernberg (2015); Dervilis et al. (2014)	Li, Liu, and Shu (2019); Regan, Beale, and Inalpolat (2017); Regan et al. (2016)	Ziegler et al. (2019)	Rocher et al. (2014)	Cao et al. (2016); Sarrafi et al. (2018)	Qiu et al. (2015); Borchersen and Kinnaert (2016); Feng and Liang (2014); Joshuva and Sugumaran (2017); Shafiee (2015)
Alarm Assesment	Pliego Marugán and García Márquez (2019); Jlassi et al. (2015); Yang et al. (2019)	Leahy et al. (2016); Yang, Huang, and Yang (2015)		Wang et al. (2014); Zhao et al. (2018)		Qiu and Feng (2020); Fernandez-Canti et al. (2015); Gonzalez, Reder, and Melero (2016)
Performance Monitoring	Sales-Setién and Peñarrocha-Alós (2020)				Pedersen and Fossen (2012); Rogers et al. (2020); Saravanakumar and Jena (2013); Pedersen and Fossen (2012); Song et al. (2018); Astolfi (2018); Simani (2015)

Table 2. Summary of the benefits and limitations for the 5 individual regression machine learning methods.

Method	Capabilities	Limitations
ANN	No Prior knowledge needed: since the algorithm is based only on historical data. Processing incomplete data: A trained network can still produce results with incomplete knowledge. The accuracy is dependent on the importance of the information. Can be updated in real-time: The program can run while updating the firmware reducing downtime.	Unexpected behaviour: One of the major drawbacks of an ANN. When an ANN produces a probing result there is no insight on how these anomalous results are produced. Hardware dependence: ANNs accuracy is directly dependent on the amount of information used to train the network. The network requires a large amount to learn correctly. Black Box: it is incredibly difficult to understand the network within this type of model.
SVM	Rationalisation and training efficiency: As opposed to other methods the probability of local optima during training is unlikely since Quadratic programming is formulated in the development. This is rewarded with the goodness of fit with unseen information. Outlier Suppression: Unlike other methods, SVRs consider trade-off parameters when processing information	Parameter selection: One of the major drawbacks for SVRs is the correct implementation of the Kernel function. The function represents the data in the Hilbert space. Other parameters need to be adjusted to reach the desired fitting. Computational Effort: SVRs usually have good performance with limited data. With an increased magnitude of data, the time required to solve the dual optimisation problem and Lagrange multipliers increases significantly.
K-NN	Simple and effective: This is a well understood methodology. The decision rule is extensively researched. The number of classes reduces the error twice that of a Bayes probability. No assumptions: Unlike other methods K-NN is a non-parametric therefore requires no presumptions to be made. No training necessary: This methodology does not explicitly build a model. It uses previous information to infer new data.	Slow algorithm: As the dataset increases the inverse will happen to the efficiency. Especially with increased dimensionality, the accuracy of the algorithm declines. Outlier sensitivity: The K-NN algorithm is hypersensitive to outliers as the neighbours are selected based on the selected distance criteria. Unkonwn amount of clusters: It is difficult to determine the right amount that produces the most meaningful results.
DBN	Overfitting control: Since Bayesian statistical methods are encapsulated in the model local maximums can be avoided. Unaffected by parameterisation: DBN looks for interdependence hence they are not adversely affected with more variables.	Unknown amount of arcs: For many cases the number of arcs and nodes could be in the thousands hence a closed-form solution cannot be achievable.
GP	Directly captures uncertainty: in regression models the prediction is given as a value and a distribution. This is not directly captured in other methods. Prior knowledge implementation: when designing the model, if the path of the trend is known a specific kernel function that correlates can be implemented.	Computationally demanding: For more than a few hundred data points the time to process this information is longer than other methods due to the cubic inversion issue.

Gholami, Raoof, and Nikoo Fakhari. 2017. “Chapter 27 – Support Vector Machine: Principles, Parameters, and Applications.” In Handbook of Neural Computation, edited by Pijush Samui, Sanjiban Sekhar, and Valentina E. Balas, 515–535. Academic Press. ISBN 9780128113189.

 Google Scholar

Feng, Zhipeng, Sifeng Qin, and Ming Liang. 2016. “Time–Frequency Analysis Based on VoldKalman Filter and Higher Order Energy Separation for Fault Diagnosis of Wind Turbine Planetary Gearbox Under Nonstationary Conditions.” Renewable Energy 85: 45–56. ISSN 0960-1481, doi:https://doi.org/10.1016/j.renene.2015.06.041 (http://www.sciencedirect.com/science/article/pii/S0960148115300641).

 Web of Science ®Google Scholar

Ziaja, A., I. Antoniadou, T. Barszcz, W. J. Staszewski, and K. Worden. 2016. “Fault Detection in Rolling Element Bearings Using Wavelet-Based Variance Analysis and Novelty Detection.” Journal of Vibration and Control 22 (2): 396–411. doi:https://doi.org/10.1177/1077546314532859 (cit. on p. 10).

 Web of Science ®Google Scholar

Fernández-Francos, D., D. Martínez-Rego, O. Fontenta-Romero, and A. Alonso-Betanzos. 2013. “Automatic Bearing Fault Diagnosis Based on one-Class ν-SVM.” Computers & Industrial Engineering 64 (1): 357–365.

 Web of Science ®Google Scholar

Qiao, W., and D. Lu. 2015b. “A Survey on Wind Turbine Condition Monitoring and Fault Diagnosis – Part I: Components and Subsystems.” IEEE Transactions on Industrial Electronics 62 (10): 6536–6545. doi:https://doi.org/10.1109/TIE.2015.2422112 (cit. on pp. 7, 9).

 Web of Science ®Google Scholar

Sheng, S.2013. Report on Wind Turbine Subsystem Reliability – A Survey of Various Databases. Technical Report. NREL/PR-5000-59111. National Renewable Energy Laboratory. https://www.nrel.gov/docs/fy13osti/59111.pdf.

 Google Scholar

Geropp, B. 1997. “Envelope Analysis - A Signal Analysis Technique for Early Detection and Isolation of Machine Faults.” IFAC Proceedings Volumes 30 (18): 977–981. doi:https://doi.org/10.1016/S1474-6670(17)42527-4 (cit. on p. 9).

 Google Scholar

Koukoura, S., J. Carroll, and A. Mcdonald. 2017. “Wind Turbine Intelligent Gear Fault Identification.” Annual Conference of the PHM Society, St. Petersburg, USA, pp. 1–7 (cit. on p. 10).

 Google Scholar

Bach-Andersen, M., B. Rømer-Odgaard, and O. Winther. 2018. “Deep Learning for Automated Drive Train Fault Detection.” Wind Energy 21: 29–41. doi:https://doi.org/10.1002/we.2142.

 Web of Science ®Google Scholar

Ha, J. M., H. Oh, J. Park, and B. D. Youn. 2017. “Classification of Operating Conditions of Wind Turbines for a Class-Wise Condition Monitoring Strategy.” Renewable Energy 103: 594–605. doi:https://doi.org/10.1016/j.renene.2016.10.071 (cit. on p. 10).

 Web of Science ®Google Scholar

Teng, W., X. Ding, X. Zhang, Y. Liu, and Z. Ma. 2016. “Multi-fault Detection and Failure Analysis of Wind Turbine Gearbox Using Complex Wavelet Transform.” Renewable Energy 93: 591–598.

 Web of Science ®Google Scholar

Nejad, A. R., P. F. Odgaard, Z. Gao, and T. Moan. 2014. “A Prognostic Method for Fault Detection in Wind Turbine Drivetrains.” Engineering Failure Analysis 42: 324–336.

 Web of Science ®Google Scholar

Zhang, Z., A. Verma, and A. Kusiak. 2012. “Fault Analysis and Condition Monitoring of the Wind Turbine Gearbox.” IEEE Transactions on Energy Conversion 27 (2): 526–535.

 Web of Science ®Google Scholar

Zhu, W. J., W. Z. Shen, E. Barlas, F. Bertagnolio, and J. N. Sørensen. 2018. “Wind Turbine Noise Generation and Propagation Modeling at DTU Wind Energy: A Review.” Renewable and Sustainable Energy Reviews 88: 133–150.

 Web of Science ®Google Scholar

Lee, S., and S. Lee. 2014. “Numerical and Experimental Study of Aerodynamic Noise by a Small Wind Turbine.” Renewable Energy 65: 108–112.

 Web of Science ®Google Scholar

Bouzid, O. M., G. Y. Tian, K. Cumanan, and D. Moore. 2015. “Structural Health Monitoring of Wind Turbine Blades: Acoustic Source Localization Using Wireless Sensor Networks.” Journal of Sensors 2015: 139695.

 Web of Science ®Google Scholar

Hackell, M. W., R. Rolfes, M. B. Kane, and J. P. Lynch. 2016. “Three-Tier Modular Structural Health Monitoring Framework Using Environmental and Operational Condition Clustering for Data Normalization: Validation on an Operational Wind Turbine System.” Proceedings of the IEEE 104 (8): 1632–1646.

 Web of Science ®Google Scholar

Wang, Y., Y. Liu, L. Li, D. Infield, and S. Han. 2018. “Short-term Wind Power Forecasting Based on Clustering pre-Calculated CFD Method.” Energies 11 (4): 854.

 Web of Science ®Google Scholar

Liu, X., M. Li, S. Qin, X. Ma, and W. Wang. 2016. “A Predictive Fault Diagnose Method of Wind Turbine Based on K-Means Clustering and Neural Networks.” Journal of Internet Technology 17 (7): 1521–1528.

 Web of Science ®Google Scholar

Kang, J., X. Zhang, and T. Jin. 2015. “Tracking Gearbox Degradation based on Stable Distribution Parameters: A Case Study.” 2015 IEEE Conference on Prognostics and Health Management: Enhancing Safety, Efficiency, Availability, and Effectiveness of Systems Through PHAf Technology and Application, PHM.

 Google Scholar

Skrimpas, G. A., C. W. Sweeney, K. S. Marhadi, B. B. Jensen, N. Mijatovic, and J. Holbøll. 2015. “Employment of Kernel Methods on Wind Turbine Power Performance Assessment.” IEEE Transactions on Sustainable Energy 6 (3): 698–706.

 Web of Science ®Google Scholar

Saidi, L., J. Ben Ali, M. Benbouzid, and E. Bechhofer. 2018. “An Integrated Wind Turbine Failures Prognostic Approach Implementing Kalman Smoother with Confidence Bounds.” Applied Acoustics 138: 199–208.

 Web of Science ®Google Scholar

Yang, W., R. Court, and J. Jiang. 2013. “Wind Turbine Condition Monitoring by the Approach of SCADA Data Analysis.” Renewable Energy 53: 365–376.

 Web of Science ®Google Scholar

Yang, W., P. J. Tavner, C. J. Crabtree, Y. Feng, and Y. Qiu. 2014. “Wind Turbine Condition Monitoring: Technical and Commercial Challenges.” Wind Energy 17 (5): 673–693.

 Web of Science ®Google Scholar

Catmull, S. 2011. “Self-Organising Map Based Condition Monitoring of Wind Turbines.” EWEA Annual Conference 2011.

 Google Scholar

Kim, K., G. Parthasarathy, O. Uluyol, W. Foslien, S. Sheng, and P. Fleming. 2011. “Use of SCADA Data for Failure Detection in Wind Turbines.” ASME 5th International Conference on Energy Sustainability.

 Google Scholar

de Moura, E. P., F. E. de Abreu Melo Junior, F. F. Rocha Damasceno, L. C. Campos Figueiredo, C. F. de Andrade, M. S. de Almeida, and P. Alexandre Costa Rocha. 2016. “Classification of Imbalance Levels in a Scaled Wind Turbine Through Detrended Fluctuation Analysis of Vibration Signals.” Renewable Energy 96: 993–1002.

 Web of Science ®Google Scholar

Mazidi, P., M. Du, L. Bertling Tjernberg, and M. A. S. Bobi. 2016. “A Performance and Maintenance Evaluation Framework for Wind Turbines.” 2016 International Conference on Probabilistic Methods Applied to Power Systems.

 Google Scholar

Yu, R., J. Gao, M. Yu, W. Lu, T. Xu, M. Zhao, J. Zhang, R. Zhang, and Z. Zhang. 2019. “LSTM-EFG for Wind Power Forecasting Based on Sequential Correlation Features.” Future Generation Computer Systems 93: 33–42.

 Web of Science ®Google Scholar

Hang, J., J. Zhang, and M. Cheng. 2016. “Application of Multi-Class Fuzzy Support Vector Machine Classifier for Fault Diagnosis of Wind Turbine.” Fuzzy Sets and Systems 297: 128–140.

 Web of Science ®Google Scholar

Djeziri, M. A., S. Benmoussa, and R. Sanchez. 2018. “Hybrid Method for Remaining Useful Life Prediction in Wind Turbine Systems.” Renewable Energy 116: 173–187.

 Web of Science ®Google Scholar

Zhao, H., Y. Gao, H. Liu, and L. Li. 2019. “Fault Diagnosis of Wind Turbine Bearing Based on Stochastic Subspace Identification and Multi-Kernel Support Vector Machine.” Journal of Modern Power Systems and Clean Energy 7 (2): 350–356.

 Web of Science ®Google Scholar

Möller, T., D. Langenkämper, and T. Nattkemper. 2019. “Wind Turbine Segmentation Performing KNN-Clustering on Superpixel Segmentations.” Proceedings of SPIE – The International Society for Optical Engineering.

 Google Scholar

Teng, W., X. Wang, C. Dang, and W. Shi. 2016. “Dynamic Equvalent Model of the Wind Farm Based on the K Nearest Neighbor.” Asia-Pacific Power and Energy Engineering Conference.

 Google Scholar

Herp, J., N. L. Pedersen, and E. S. Nadimi. 2016. “Wind Turbine Performance Analysis Based on Multivariate Higher Order Moments and Bayesian Classifiers.” Control Engineering Practice 49: 204–211.

 Web of Science ®Google Scholar

Wang, H., H. Wang, G. Jiang, J. Li, and Y. Wang. 2019. “Early Fault Detection of Wind Turbines Based on Operational Condition Clustering and Optimized Deep Belief Network Modeling.” Energies 12 (6): 984.

 Web of Science ®Google Scholar

Neu, E., F. Janser, A. A. Khatibi, and A. C. Orifici. 2017. “Fully Automated Operational Modal Analysis Using Multi-Stage Clustering.” Mechanical Systems and Signal Processing 84: 308–323.

 Web of Science ®Google Scholar

Ciulla, Giuseppina, Antonino D’Amico, V. Dio, and V. Lo Brano. 2019. “Modelling and Analysis of Real-World Wind Turbine Power Curves: Assessing Deviations from Nominal Curve by Neural Networks.” Renewable Energy 140: 477–492. doi:https://doi.org/10.1016/j.renene.2019.03.075

 Google Scholar

Garcia, M. C., M. A. Sanz-Bobi, and J. del Pico. 2006. “SIMAP: Intelligent System for Predictive Maintenance Application to the Health Condition Monitoring of a Wind Turbine Gearbox.” Computers in Industry 57 (6): 552–568.

 Web of Science ®Google Scholar

Bi, R., C. Zhou, and D. M. Hepburn. 2017. “Detection and Classification of Faults in Pitchregulated Wind Turbine Generators Using Normal Behaviour Models Based on Performance Curves.” Renewable Energy 105: 674–688.

 Web of Science ®Google Scholar

Schlechtingen, Meik, Ilmar Ferreira Santos, and Sofiane Achiche. 2013. “Wind Turbine Condition Monitoring Based on SCADA Data Using Normal Behavior Models. Part 1: System Description.” Applied Soft Computing 13 (1): 259–270. ISSN 1568-4946. doi:https://doi.org/10.1016/j.asoc.2012.08.033

 Web of Science ®Google Scholar

Astolfi, D. 2019. “A Study of the Impact of Pitch Misalignment on Wind Turbine Performance.” Machines 7 (1): 8.

 Web of Science ®Google Scholar

Tabib, Mandar, M. Salman Siddiqui, Adil Rasheed, and Trond Kvamsdal. 2017. “Industrial Scale Turbine and Associated Wake Development -Comparison of RANS Based Actuator Line Vs Sliding Mesh Interface Vs Multiple Reference Frame Method.” Energy Procedia 137: 487–496. ISSN 1876-6102. doi:https://doi.org/10.1016/j.egypro.2017.10.377

 Google Scholar

Bangalore, P., and L. B. Tjernberg. 2015. “An Artificial Neural Network Approach for Early Fault Detection of Gearbox Bearings.” IEEE Transactions on Smart Grid 6 (2): 980–987.

 Web of Science ®Google Scholar

Dervilis, N., M. Choi, S. G. Taylor, R. J. Barthorpe, G. Park, C. R. Farrar, and K. Worden. 2014. “On Damage Diagnosis for a Wind Turbine Blade Using Pattern Recognition.” Journal of Sound and Vibration 333 (6): 1833–1850.

 Web of Science ®Google Scholar

Li, Y., S. Liu, and L. Shu. 2019. “Wind Turbine Fault Diagnosis Based on Gaussian Process Classifiers Applied to Operational Data.” Renewable Energy 134: 357–366.

 Web of Science ®Google Scholar

Regan, T., C. Beale, and M. Inalpolat. 2017. “Wind Turbine Blade Damage Detection Using Supervised Machine Learning Algorithms”, Journal of Vibration and Acoustics.” Transactions of the ASME 139 (6): 061010.

 Google Scholar

Regan, T., R. Canturk, E. Slavkovsky, C. Niezrecki, and M. Inalpolat. 2016. “Wind Turbine Blade Damage Detection using Various Machine Learning Algorithms.” Proceedings of the ASME Design Engineering Technical Conference.

 Google Scholar

Ziegler, L., N. Cosack, A. Kolios, and M. Muskulus. 2019. “Structural Monitoring for Lifetime Extension of Offshore Wind Monopiles: Verification of Strain-Based Load Extrapolation Algorithm.” Marine Structures 66: 154–163.

 Web of Science ®Google Scholar

Rocher, B., F. Schoefs, M. Fraņcois, and A. Salou. 2014. “Bayesian Updating of Probabilistic Time-Dependent Fatigue Model: Application to Jacket Foundations of Wind Turbines.” 7th European Workshop on Structural Health Monitoring, EWSHM 2014 – 2nd European Conference of the Prognostics and Health Management (PHM) Society, pp. 1264.

 Google Scholar

Cao, M., Y. Qiu, Y. Feng, H. Wang, and D. Li. 2016. “Study of Wind Turbine Fault Diagnosis Based on Unscented Kalman Filter and SCADA Data.” Energies 9: 10.

 Web of Science ®Google Scholar

Sarrafi, A., Z. Mao, C. Niezrecki, and P. Poozesh. 2018. “Vibration-based Damage Detection in Wind Turbine Blades Using Phase-Based Motion Estimation and Motion Magnification.” Journal of Sound and Vibration 421: 300–318.

 Web of Science ®Google Scholar

Qiu, Y., W. Zhang, M. Cao, Y. Feng, and D. Infield. 2015. “An Electro-Thermal Analysis of a Variable-Speed Doubly-Fed Induction Generator in a Wind Turbine.” Energies 8 (5): 3386–3402.

 Web of Science ®Google Scholar

Borchersen, A. B., and M. Kinnaert. 2016. “Model-based Fault Detection for Generator Cooling System in Wind Turbines Using SCADA Data.” Wind Energy 19 (4): 593–606. doi:https://doi.org/10.1002/we.1852 (cit. on pp. 28, 72).

 Web of Science ®Google Scholar

Feng, Z., and M. Liang. 2014. “Fault Diagnosis of Wind Turbine Planetary Gearbox Under Nonstationary Conditions via Adaptive Optimal Kernel Time-Frequency Analysis.” Renewable Energy 66: 468–477.

 Web of Science ®Google Scholar

Joshuva, A., and V. Sugumaran. 2017. “A Data Driven Approach for Condition Monitoring of Wind Turbine Blade Using Vibration Signals Through Best-First Tree Algorithm and Functional Trees Algorithm: A Comparative Study.” ISA Transactions 67: 160–172.

 PubMed Web of Science ®Google Scholar

Shafiee, M. 2015. “A Fuzzy Analytic Network Process Model to Mitigate the Risks Associated with Offshore Wind Farms.” Expert Systems with Applications 42 (4): 2143–2152.

 Web of Science ®Google Scholar

Pliego Marugán, A., and F. P. García Márquez. 2019. “Advanced Analytics for Detection and Diagnosis of False Alarms and Faults: A Real Case Study.” Wind Energy 22: 1622–1635. doi:https://doi.org/10.1002/we.2393

 Web of Science ®Google Scholar

Jlassi, I., J. O. Estima, S. Khojet El Khil, N. Mrabet Bellaaj, and A. J. Marques Cardoso. 2015. “Multiple Open-Circuit Faults Diagnosis in Back-to-Back Converters of PMSG Drives for Wind Turbine Systems.” IEEE Transactions on Power Electronics 30 (5): 2689–2702.

 Web of Science ®Google Scholar

Yang, C., J. Liu, Y. Zeng, and G. Xie. 2019. “Real-time Condition Monitoring and Fault Detection of Components Based on Machine-Learning Reconstruction Model.” Renewable Energy 133: 433–441.

 Web of Science ®Google Scholar

Leahy, K., R. L. Hu, I. C. Konstantakopoulos, C. J. Spanos, and A. M. Agogino. 2016. “Diagnosing Wind Turbine Faults Using Machine Learning Techniques Applied to Operational Data.” 2016 IEEE International Conference on Prognostics and Health Management, ICPHM 2016.

 Google Scholar

Yang, H.-H., M.-L. Huang, and S.-W. Yang. 2015. “Integrating Auto-Associative Neural Networks with Hotelling T2 Control Charts for Wind Turbine Fault Detection.” Energies 8 (10): 12100–12115.

 Web of Science ®Google Scholar

Wang, Y., D. G. Infield, B. Stephen, and S. J. Galloway. 2014. “Copula-based Model for Wind Turbine Power Curve Outlier Rejection.” Wind Energy 17 (11): 1677–1688.

 Web of Science ®Google Scholar

Zhao, H., H. Liu, W. Hu, and X. Yan. 2018. “Anomaly Detection and Fault Analysis of Wind Turbine Components Based on Deep Learning Network.” Renewable Energy 127: 825–834.

 Web of Science ®Google Scholar

Qiu, Yingning, and Yanhui Feng. 2020. “David Infield, Fault Diagnosis of Wind Turbine with SCADA Alarms Based Multidimensional Information Processing Method.” Renewable Energy 145: 1923–1931. ISSN 0960-1481. doi:https://doi.org/10.1016/j.renene.2019.07.110

 Web of Science ®Google Scholar

Fernandez-Canti, R. M., J. Blesa, S. Tornil-Sin, and V. Puig. 2015. “Fault Detection and Isolation for a Wind Turbine Benchmark Using a Mixed Bayesian/Set-Membership Approach.” Annual Reviews in Control 40: 59–69.

 Web of Science ®Google Scholar

Gonzalez, E., M. Reder, and J. J. Melero. 2016. “SCADA Alarms Processing for Wind Turbine Component Failure Detection.” Journal of Physics: Conference Series 753 (7): 072019.

 Google Scholar

Sales-Setién, Ester, and Ignacio Peñarrocha-Alós. 2020. “Robust Estimation and Diagnosis of Wind Turbine Pitch Misalignments at a Wind Farm Level.” Renewable Energy 146: 1746–1765. ISSN 0960-1481. doi:https://doi.org/10.1016/j.renene.2019.07.133

 Web of Science ®Google Scholar

Pedersen, Morten D., and Thor I. Fossen. 2012. “Efficient Nonlinear Wind-Turbine Modeling For Control Applications.” IFAC Proceedings Volumes 45 (2): 264–269. ISSN 1474-6670. ISBN 9783902823236. doi:https://doi.org/10.3182/20120215-3-AT3016.00046

 Google Scholar

Rogers, T. J., P. Gardner, N. Dervilis, K. Worden, A. E. Maguire, E. Papatheou, and E. J. Cross. 2020. “Probabilistic Modelling of Wind Turbine Power Curves with Application of Heteroscedastic Gaussian Process Regression.” Renewable Energy 148: 1124–1136. ISSN 0960-1481. doi:https://doi.org/10.1016/j.renene.2019.09.145.

 Web of Science ®Google Scholar

Saravanakumar, R., and D. Jena. 2013. “Nonlinear Estimation and Control of Wind Turbine.” 2013 IEEE International Conference on Electronics, Computing and Communication Technologies, Bangalore, 1–6. doi:https://doi.org/10.1109/CONECCT.2013.6469307

 Google Scholar

Song, Dongran, Jian Yang, Xinyu Fan, Yao Liu, Anfeng Liu, Guo Chen, and Young Hoon Joo. 2018. “Maximum Power Extraction for Wind Turbines Through a Novel Yaw Control Solution Using Predicted Wind Directions.” Energy Conversion and Management 157: 587–599. ISSN 0196-8904. doi:https://doi.org/10.1016/j.enconman.2017.12.019

 Web of Science ®Google Scholar

Asghar, Aamer Bilal, and Xiaodong Liu. 2018. “School of Control Science and Engineering, Faculty of Electronic Information and Electrical Engineering”, Dalian University of Technology, Dalian 116024, P.R. China.

 Google Scholar

Simani, S. 2015. “Overview of Modelling and Advanced Control Strategies for Wind Turbine Systems.” Energies 8 (12): 13395–13418.

 Web of Science ®Google Scholar