Multivariate Anomaly Detection and Early Warning Framework for Wind Turbine Condition Monitoring Using SCADA Data
Publication: Journal of Energy Engineering
Volume 149, Issue 6
Abstract
Wind speed power characteristics are essential in evaluating the state of the wind turbine. The supervisory control and data acquisition (SCADA) data are massively collected and could be important resources for condition monitoring and anomaly detection of wind turbines if properly utilized. A systematic early-stage anomaly detection framework is built in this work consisting of three phases: (1) an improved data cleaning algorithm based on kernel density estimation (KDE) is presented to remove outliers of SCADA data where the constraint of the Gaussian distribution assumption is eliminated for describing the real distribution of power outputs in each wind speed interval; (2) deep neural networks (DNNs) are used to establish a multivariate power curve (MPC) model where the dependencies of multidimensional variables on power output are considered and selected by Pearson correlation analysis; and (3) the sequential probability ratio test (SPRT) is adopted to estimate the distribution of power residuals and used for anomaly detection and early warning. The case studies verified the efficacy of the proposed framework where 91 faults from 38 wind turbines in two wind farms are successfully detected in the early stage.
Get full access to this article
View all available purchase options and get full access to this article.
Data Availability Statement
Some data (including the SCADA data of the Wind turbine 13 in DN wind farm and the SCADA data of Wind turbine 33 in TY wind farm after processing), models, or code that support the findings of this study are available from the corresponding author upon reasonable request.
Acknowledgments
This work was partly supported by the National Natural Science Foundation of China (Grant No. 11802152) and Research and Development Project of Huadian Group (Grant No. CHDKJ-21-01-98).
References
Asghar, A. B., and X. Liu. 2018. “Estimation of wind speed probability distribution and wind energy potential using adaptive neuro-fuzzy methodology.” Neurocomputing 287 (Jan): 58–67. https://doi.org/10.1016/j.neucom.2018.01.077.
Cai, B., L. Cao, Y. Lei, C. Wang, L. Zhang, J. Zhu, and J. Wang. 2021. “China’s carbon emission pathway under the carbon neutrality target.” China Popul. Resour. Environ. 31 (1): 7–14.
Cambron, P., R. Lepvrier, C. Masson, A. Tahan, and F. Pelletier. 2016. “Power curve monitoring using weighted moving average control charts.” Renewable Energy 94 (Mar): 126–135. https://doi.org/10.1016/j.renene.2016.03.031.
Cambron, P., A. Tahan, C. Masson, and F. Pelletier. 2017. “Bearing temperature monitoring of a wind turbine using physics-based model.” J. Qual. Maint. Eng. 23 (4): 479–488.
Dey, S., P. Pisu, and B. Ayalew. 2015. “A comparative study of three fault diagnosis schemes for wind turbines.” IEEE Trans. Control Syst. Technol. 23 (5): 1853–1868. https://doi.org/10.1109/TCST.2015.2389713.
Feng, C., C. Liu, and D. Jiang. 2023. “Unsupervised anomaly detection using graph neural networks integrated with physical-statistical feature fusion and local-global learning.” Renewable Energy 206: 309–323.
Guo, P., and D. Infield. 2018. “Wind turbine power curve modeling and monitoring with Gaussian process and SPRT.” IEEE Trans. Sustainable Energy 11 (1): 107–115. https://doi.org/10.1109/TSTE.2018.2884699.
Han, T., T. Zhou, Y. Xiang, and D. Jiang. 2022. “Cross-machine intelligent fault diagnosis of gearbox based on deep learning and parameter transfer.” Struct. Control Health Monit. 29 (3): e2898. https://doi.org/10.1002/stc.2898.
IRENA (International Renewable Energy Agency). 2023. Renewable capacity statistics 2023. Abu Dhabi, UAE: IRENA.
Kusiak, A., and A. Verma. 2012. “Monitoring wind farms with performance curves.” IEEE Trans. Sustainable Energy 4 (1): 192–199. https://doi.org/10.1109/TSTE.2012.2212470.
Li, Y., X. Wei, Y. Li, Z. Dong, and M. Shahidehpour. 2022a. “Detection of false data injection attacks in smart grid: A secure federated deep learning approach.” IEEE Trans. Smart Grid 13 (6): 4862–4872. https://doi.org/10.1109/TSG.2022.3204796.
Li, Y., M. Zhang, and C. Chen. 2022b. “A deep-learning intelligent system incorporating data augmentation for short-term voltage stability assessment of power systems.” Appl. Energy 308 (14): 118347. https://doi.org/10.1016/j.apenergy.2021.118347.
Liang, G., Y. Su, F. Chen, H. Long, Z. Song, and Y. Gan. 2020. “Wind power curve data cleaning by image thresholding based on class uncertainty and shape dissimilarity.” IEEE Trans. Sustainable Energy 12 (2): 1383–1393. https://doi.org/10.1109/TSTE.2020.3045782.
Liu, W., W. Zhu, C. Li, G. Guan, D. Zhang, Y. Xiao, and L. Zheng. 2015. “Thermal degradation mechanism of poly (hexamethylene carbonate).” Polym. Degrad. Stab. 112 (Jun): 70–77. https://doi.org/10.1016/j.polymdegradstab.2014.12.013.
Long, H., L. Sang, Z. Wu, and W. Gu. 2019. “Image-based abnormal data detection and cleaning algorithm via wind power curve.” IEEE Trans. Sustainable Energy 11 (2): 938–946. https://doi.org/10.1109/TSTE.2019.2914089.
Lydia, M., S. Suresh Kumar, A. Immanuel Selvakumar, and G. Edwin Prem Kumar. 2018. “Wind farm power prediction based on wind speed and power curve models.” In Intelligent and efficient electrical systems, 15–24. Berlin: Springer.
Muñoz, C. Q. G., F. P. G. Márquez, and J. M. S. Tomás. 2016. “Ice detection using thermal infrared radiometry on wind turbine blades.” Measurement 93 (Nov): 157–163. https://doi.org/10.1016/j.measurement.2016.06.064.
Odgaard, P. F., and J. Stoustrup. 2014. “A benchmark evaluation of fault tolerant wind turbine control concepts.” IEEE Trans. Control Syst. Technol. 23 (3): 1221–1228. https://doi.org/10.1109/TCST.2014.2361291.
Papatheou, E., N. Dervilis, A. E. Maguire, C. Campos, I. Antoniadou, and K. Worden. 2017. “Performance monitoring of a wind turbine using extreme function theory.” Renewable Energy 113 (Jul): 1490–1502. https://doi.org/10.1016/j.renene.2017.07.013.
Parzen, E. 1962. “On estimation of a probability density function and mode.” Ann. Math. Stat. 33 (3): 1065–1076.
Rosenblatt, M. 1956. “Remarks on some nonparametric estimates of a density function.” Ann. Math. Stat. 27 (3): 832–837.
Scott, D. W. 2015. Nonparametric estimation criteria. New York: Wiley.
Shen, X., X. Fu, and C. Zhou. 2018. “A combined algorithm for cleaning abnormal data of wind turbine power curve based on change point grouping algorithm and quartile algorithm.” IEEE Trans. Sustainable Energy 10 (1): 46–54. https://doi.org/10.1109/TSTE.2018.2822682.
Soua, S., P. Van Lieshout, A. Perera, T. H. Gan, and B. Bridge. 2013. “Determination of the combined vibrational and acoustic emission signature of a wind turbine gearbox and generator shaft in service as a pre-requisite for effective condition monitoring.” Renewable Energy 51 (Aug): 175–181. https://doi.org/10.1016/j.renene.2012.07.004.
Sun, Q., C. Liu, and C. Zhen. 2019. “Abnormal detection of wind turbine operating conditions based on state curves.” J. Energy Eng. 145 (5): 06019001. https://doi.org/10.1061/(ASCE)EY.1943-7897.0000612.
Taylor, C. 1997. “Classification and kernel density estimation.” Vistas Astron. 41 (3): 411–417. https://doi.org/10.1016/S0083-6656(97)00046-9.
Wald, A. 1945. “Sequential tests of statistical hypotheses.” Ann. Math. Stat. 16: 117–186.
Wang, Y., Q. Hu, L. Li, A. M. Foley, and D. Srinivasan. 2019. “Approaches to wind power curve modeling: A review and discussion.” Renewable Sustainable Energy Rev. 116 (Jun): 109422. https://doi.org/10.1016/j.rser.2019.109422.
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. https://doi.org/10.1002/we.1661.
Wang, Z., and C. Liu. 2021. “Wind turbine condition monitoring based on a novel multivariate state estimation technique.” Measurement 168 (Aug): 108388. https://doi.org/10.1016/j.measurement.2020.108388.
Wang, Z., L. Wang, and C. Huang. 2020. “A fast abnormal data cleaning algorithm for performance evaluation of wind turbine.” IEEE Trans. Instrum. Meas. 70 (2): 1–12. https://doi.org/10.1109/TIM.2020.3044719.
Xiang, L., P. Wang, X. Yang, A. Hu, and H. Su. 2021. “Fault detection of wind turbine based on SCADA data analysis using CNN and LSTM with attention mechanism.” Measurement 175 (Jun): 109094. https://doi.org/10.1016/j.measurement.2021.109094.
Xie, Z., and J. Yan. 2008. “Kernel density estimation of traffic accidents in a network space.” Comput. Environ. Urban Syst. 32 (5): 396–406. https://doi.org/10.1016/j.compenvurbsys.2008.05.001.
Yang, L., L. Wang, and Z. Zhang. 2022. Generative wind power curve modeling via machine vision: A deep convolutional network method with data-synthesis-informed-training. New York: IEEE.
Yang, L., and Z. Zhang. 2020. “A conditional convolutional autoencoder-based method for monitoring wind turbine blade breakages.” IEEE Trans. Ind. Inf. 17 (9): 6390–6398. https://doi.org/10.1109/TII.2020.3011441.
Yang, W., R. Court, and J. Jiang. 2013. “Wind turbine condition monitoring by the approach of SCADA data analysis.” Renewable Energy 53 (22): 365–376. https://doi.org/10.1016/j.renene.2012.11.030.
Yang, W., C. Liu, and D. Jiang. 2018. “An unsupervised spatiotemporal graphical modeling approach for wind turbine condition monitoring.” Renewable Energy 127 (Jun): 230–241. https://doi.org/10.1016/j.renene.2018.04.059.
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 (Apr): 825–834. https://doi.org/10.1016/j.renene.2018.05.024.
Zhao, Y., L. Ye, W. Wang, H. Sun, Y. Ju, and Y. Tang. 2017. “Data-driven correction approach to refine power curve of wind farm under wind curtailment.” IEEE Trans. Sustainable Energy 9 (1): 95–105. https://doi.org/10.1109/TSTE.2017.2717021.
Information & Authors
Information
Published In
Copyright
© 2023 American Society of Civil Engineers.
History
Received: Oct 24, 2022
Accepted: Apr 2, 2023
Published online: Aug 25, 2023
Published in print: Dec 1, 2023
Discussion open until: Jan 25, 2024
ASCE Technical Topics:
- Case studies
- Data analysis
- Data collection
- Distribution functions
- Electric power
- Energy engineering
- Energy sources (by type)
- Engineering fundamentals
- Engines
- Equipment and machinery
- Mathematical functions
- Mathematics
- Methodology (by type)
- Power transmission
- Probability distribution
- Renewable energy
- Research methods (by type)
- Structural engineering
- Turbines
- Wind engineering
- Wind power
- Wind speed
Authors
Metrics & Citations
Metrics
Citations
Download citation
If you have the appropriate software installed, you can download article citation data to the citation manager of your choice. Simply select your manager software from the list below and click Download.