Wind Turbine Multi-Fault Detection and Classification Based on SCADA Data
Abstract
:1. Introduction
2. Fault Diagnosis Strategy
2.1. Model Overview
2.2. Noise Handling
2.3. Data Collection
2.4. Data Reshape and Tensor Unfolding
- Fault 8 (F8) is required to fulfill . This is the most restrictive detection time, as this is the most severe fault. It is related to the torque actuator, and it is noteworthy that the torque rate limit for the NREL 5-MW WT is 15,000 Nm/s [26].
- Fault 1 (F1) is required to fulfill . This fault has a high varying dynamic and is related to the pitch actuator (i.e., high air content in oil). In this case, the blade-pitch rate limit for the NREL 5-MW WT is 8 deg/s, as this is speculated to be the blade pitch rate limit of conventional 5-MW machines based on General Electric (GE) Wind’s long blade test program [26].
- Faults 4 to 7 (F4, F5, F6, F7) are required to fulfill . These faults are related to the generator speed sensor and the pitch sensors.
- Finally, Faults 2 and 3 (F2, F3) are only required to satisfy , as these are faults with a very slow dynamic. These faults are related to the pitch actuator (i.e., pump wear and hydraulic leakage).
- (a)
- In samples of only time steps (this will lead to a detection time of approximately ).
- (b)
- In samples of time steps (in this case, detection time is close to ).
- (c)
- In samples of time steps (for a detection time around to ).
- (a)
- samples when ;
- (b)
- samples when ;
- (c)
- samples when .
2.5. Autoscaling or Standardization
2.6. Multiway PCA
2.7. Support Vector Machines
2.8. k-Fold Cross-Validation
3. Results, Analysis, and Discussion
4. Conclusions
Author Contributions
Funding
Conflicts of Interest
References
- Hossain, M.L.; Abu-Siada, A.; Muyeen, S.M. Methods for AdvancedWind Turbine Condition Monitoring and Early Diagnosis: A Literature Review. Energies 2018, 11, 1309. [Google Scholar] [CrossRef]
- Ahadi, A. Wind turbine fault diagnosis techniques and related algorithms. Int. J. Renew. Energy Res. (IJRER) 2016, 6, 80–89. [Google Scholar]
- De Azevedo, H.D.M.; Araújo, A.M.; Bouchonneau, N. A review of wind turbine bearing condition monitoring: State of the art and challenges. Renew. Sustain. Energy Rev. 2016, 56, 368–379. [Google Scholar] [CrossRef]
- Kandukuri, S.T.; Klausen, A.; Karimi, H.R.; Robbersmyr, K.G. A review of diagnostics and prognostics of low-speed machinery towards wind turbine farm-level health management. Renew. Sustain. Energy Rev. 2016, 53, 697–708. [Google Scholar] [CrossRef]
- Huang, S.; Wu, X.; Liu, X.; Gao, J.; He, Y. Overview of condition monitoring and operation control of electric power conversion systems in direct-drive wind turbines under faults. Front. Mech. Eng. 2017, 12, 281–302. [Google Scholar] [Green Version]
- Yang, Z.; Chai, Y. A survey of fault diagnosis for onshore grid-connected converter in wind energy conversion systems. Renew. Sustain. Energy Rev. 2016, 66, 345–359. [Google Scholar] [CrossRef]
- Ochieng, F.X.; Hancock, C.M.; Roberts, G.W.; Le Kernec, J. A review of ground-based radar as a noncontact sensor for structural health monitoring of in-field wind turbines blades. Wind Energy 2018. [Google Scholar] [CrossRef]
- Shohag, M.A.S.; Hammel, E.C.; Olawale, D.O.; Okoli, O.I. Damage mitigation techniques in wind turbine blades: A review. Wind Eng. 2017, 41, 185–210. [Google Scholar] [CrossRef]
- Zhao, Y.; Li, D.; Dong, A.; Kang, D.; Lv, Q.; Shang, L. Fault Prediction and Diagnosis of Wind Turbine Generators Using SCADA Data. Energies 2017, 10, 1210. [Google Scholar] [CrossRef]
- Astolfi, D.; Castellani, F.; Scappaticci, L.; Terzi, L. Diagnosis of wind turbine misalignment through SCADA data. Diagnostyka 2017, 18, 17–24. [Google Scholar]
- Leahy, K.; Hu, R.L.; Konstantakopoulos, I.C.; Spanos, C.J.; Agogino, A.M.; O’Sullivan, D.T.J. Diagnosing and predicting wind turbine faults from SCADA data using support vector machines. Int. J. Progn. Health Manag. 2018, 9, 1–11. [Google Scholar]
- Mazidi, P.; Du, M.; Tjernberg, L.B.; Bobi, M.A.S. A performance and maintenance evaluation framework for wind turbines. In Proceedings of the 2016 International Conference on Probabilistic Methods Applied to Power Systems (PMAPS), Beijing, China, 16–20 October 2016; pp. 1–8. [Google Scholar] [CrossRef]
- Laouti, N.; Sheibat, N.; Othman, S. Support vector machines for fault detection in wind turbines. In Proceedings of the IFAC World Congress, Milano, Italy, 28 August–2 September 2011; Volume 2, pp. 7067–7707. [Google Scholar]
- Laouti, N.; Othman, S.; Alamir, M.; Sheibat-Othman, N. Combination of model-based observer and support vector machines for fault detection of wind turbines. Int. J. Autom. Comput. 2014, 11, 274–287. [Google Scholar] [CrossRef]
- Xiao, Y.; Hong, Y.; Chen, X.; Chen, W. The application of dual-tree complex wavelet transform (DTCWT) energy entropy in misalignment fault diagnosis of doubly-fed wind turbine (DFWT). Entropy 2017, 19, 587. [Google Scholar] [CrossRef]
- Abdelkrim, S.; Djamel, M.M.; Samia, A.; Hayet, M.; Mawloud, T. The MAED and SVM for fault diagnosis of wind turbine system. Int. J. Renew. Energy Res. (IJRER) 2017, 7, 758–769. [Google Scholar]
- Wang, K.S.; Sharma, V.S.; Zhang, Z.Y. SCADA data based condition monitoring of wind turbines. Adv. Manuf. 2014, 2, 61–69. [Google Scholar] [CrossRef] [Green Version]
- Gonzalez, E.; Stephen, B.; Infield, D.; Melero, J. On the use of high-frequency SCADA data for improved wind turbine performance monitoring. J. Phys. Conf. Ser. 2017, 926, 012009. [Google Scholar] [CrossRef] [Green Version]
- Odgaard, P.F.; Stoustrup, J.; Kinnaert, M. Fault tolerant control of wind turbines—A benchmark model. IFAC Proc. Vol. 2009, 42, 155–160. [Google Scholar] [CrossRef]
- KK Wind Solutions. Available online: http://www.kkwindsolutions.com/ (accessed on 10 September 2018).
- The MathWorks, Inc. Available online: http://www.mathworks.com/ (accessed on 10 September 2018).
- Odgaard, P.F.; Stoustrup, J.; Kinnaert, M. Fault-tolerant control of wind turbines: A benchmark model. IEEE Trans. Control Syst. Technol. 2013, 21, 1168–1182. [Google Scholar] [CrossRef]
- Odgaard, P.; Johnson, K. Wind Turbine Fault Diagnosis and Fault Tolerant Control—An Enhanced Benchmark Challenge. In Proceedings of the American Control Conference, Washington, DC, USA, 17–19 June 2013; pp. 1–6. [Google Scholar]
- Ruiz, M.; Mujica, L.E.; Alférez, S.; Acho, L.; Tutivén, C.; Vidal, Y.; Rodellar, J.; Pozo, F. Wind turbine fault detection and classification by means of image texture analysis. Mech. Syst. Signal Process. 2018, 107, 149–167. [Google Scholar] [CrossRef] [Green Version]
- Lackner, M.A.; Rotea, M.A. Passive structural control of offshore wind turbines. Wind Energy 2011, 14, 373–388. [Google Scholar] [CrossRef]
- Jonkman, J.; Butterfield, S.; Musial, W.; Scott, G. Definition of a 5-MW Reference Wind Turbine for Offshore System Development; Technical Report No. NREL/TP-500-38060; National Renewable Energy Laboratory: Golden, CO, USA, 2009. [Google Scholar]
- May, A.; McMillan, D.; Thöns, S. Economic analysis of condition monitoring systems for offshore wind turbine sub-systems. IET Renew. Power Gener. 2015, 9, 900–907. [Google Scholar] [CrossRef] [Green Version]
- Hong, X.; Xu, Y.; Zhao, G. LBP-TOP: A Tensor Unfolding Revisit. In Proceedings of the Asian Conference on Computer Vision, Taipei, Taiwan, 20–24 November; pp. 513–527.
- Vapnik, V. The Nature of Statistical Learning Theory; Springer: Berlin, Germany, 1995. [Google Scholar]
- Yang, C.H.; Chin, L.C.; Hsieh, S.C. Morse code recognition using support vector machines. In Proceedings of the IEEE EMBS Asian-Pacific Conference on Biomedical Engineering, Kyoto, Japan, 20–22 October 2003; pp. 220–222. [Google Scholar]
- Theodoridis, S.; Koutroumbas, K. Pattern Recognition; Elsevier: Amsterdam, The Netherlands, 2009. [Google Scholar]
- Santos, P.; Villa, L.F.; Reñones, A.; Bustillo, A.; Maudes, J. An SVM-based solution for fault detection in wind turbines. Sensors 2015, 15, 5627–5648. [Google Scholar] [CrossRef] [PubMed] [Green Version]
- Melgani, F.; Bruzzone, L. Classification of hyperspectral remote sensing images with support vector machines. IEEE Trans. Geosci. Remote Sens. 2004, 42, 1778–1790. [Google Scholar] [CrossRef] [Green Version]
- McLachlan, G. Discriminant Analysis and Statistical Pattern Recognition; John Wiley & Sons: Hoboken, NJ, USA, 2004; Volume 544. [Google Scholar]
- Devroye, L.; Wagner, T. Distribution-free performance bounds with the resubstitution error estimate (Corresp.). IEEE Trans. Inf. Theory 1979, 25, 208–210. [Google Scholar] [CrossRef]
- Efron, B.; Tibshirani, R.J. An Introduction to the Bootstrap; CRC Press: Boca Raton, FL, USA, 1994. [Google Scholar]
- Stone, M. Cross-validatory choice and assessment of statistical predictions. J. R. Stat. Soc. Ser. B Methodol. 1974, 36, 111–147. [Google Scholar]
- Westerhuis, J.A.; Kourti, T.; MacGregor, J.F. Comparing alternative approaches for multivariate statistical analysis of batch process data. J. Chemom. 1999, 13, 397–413. [Google Scholar] [CrossRef]
- Pozo, F.; Vidal, Y.; Salgado, Ó. Wind Turbine Condition Monitoring Strategy through Multiway PCA and Multivariate Inference. Energies 2018, 11, 749. [Google Scholar] [CrossRef]
- Leahy, K.; Gallagher, C.; O’Donovan, P.; Bruton, K.; O’Sullivan, D. A Robust Prescriptive Framework and Performance Metric for Diagnosing and Predicting Wind Turbine Faults Based on SCADA and Alarms Data with Case Study. Energies 2008, 11, 1738. [Google Scholar] [CrossRef]
Number | Sensor Type | Symbol | Unit | Noise Power |
---|---|---|---|---|
S1 | Generated electrical power | W | 10 | |
S2 | Rotor speed | rad/s | ||
S3 | Generator speed | rad/s | ||
S4 | Generator torque | Nm | ||
S5 | Pitch angle of first blade | deg | ||
S6 | Pitch angle of second blade | deg | ||
S7 | Pitch angle of third blade | deg | ||
S8 | Tower top fore-aft acceleration | m/s2 | ||
S9 | Tower top side-to-side acceleration | m/s2 |
Reference Wind Turbine | Data |
---|---|
Rated power | 5 MW |
Number of blades | 3 |
Rotor/Hub diameter | 126 m, 3 m |
Hub height | 90 m |
Cut-in, rated, cut-out wind speed | 3 m/s, 11.4 m/s, 25 m/s |
Rated generator speed () | 1173.7 rpm |
Gearbox ratio | 97 |
Number | Fault | Type |
---|---|---|
F1 | Pitch actuator—High air content in oil | Change in system dynamics |
F2 | Pitch actuator—Pump wear | Change in system dynamics |
F3 | Pitch actuator—Hydraulic leakage | Change in system dynamics |
F4 | Generator speed sensor | Gain factor (1.2) |
F5 | Pitch sensor | Stuck value ( deg) |
F6 | Pitch sensor | Stuck value ( deg) |
F7 | Pitch sensor | Gain factor (1.2) |
F8 | Torque actuator | Offset value (2000 Nm) |
Performance | |||
---|---|---|---|
Accuracy (%) | 95.5 | 98 | 98.2 |
Training time (s) | 2990 | 202 | 181 |
Prediction speed (obs/s) | 3000 | 3500 | 3600 |
© 2018 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (http://creativecommons.org/licenses/by/4.0/).
Share and Cite
Vidal, Y.; Pozo, F.; Tutivén, C. Wind Turbine Multi-Fault Detection and Classification Based on SCADA Data. Energies 2018, 11, 3018. https://doi.org/10.3390/en11113018
Vidal Y, Pozo F, Tutivén C. Wind Turbine Multi-Fault Detection and Classification Based on SCADA Data. Energies. 2018; 11(11):3018. https://doi.org/10.3390/en11113018
Chicago/Turabian StyleVidal, Yolanda, Francesc Pozo, and Christian Tutivén. 2018. "Wind Turbine Multi-Fault Detection and Classification Based on SCADA Data" Energies 11, no. 11: 3018. https://doi.org/10.3390/en11113018