Wind Turbine Fault Detection Using a Denoising Autoencoder With Temporal Information
Open accessThe DOI matches its Crossref record; 50 of the 50 references it cites were found in a registry or an index.
Abstract
Data-driven approaches have gained increasing interests in the fault detection of wind turbines (WTs) due to the difficulty in system modeling and the availability of sensor data. However, the nonlinearity of WTs, uncertainty of disturbances and measurement noise, and temporal dependence in time-series data still pose grand challenges to effective fault detection. To this end, this paper proposes a new fault detector based on a recently developed unsupervised learning method, denoising autoencoder (DAE), which offers the learning of robust nonlinear representations from data against noise and input fluctuation. A DAE is used to build a robust multivariate reconstruction model on raw time-series data from multiple sensors, and then, the reconstruction error of the DAE trained with normal data is analyzed for fault detection. In addition, we apply the sliding-window technique to consider temporal information inherent in time-series data by including the current and past information within a small time window. A key advantage of the proposed approach is the ability to capture the nonlinear correlations among multiple sensor variables and the temporal dependence of each sensor variable simultaneously, which significantly enhanced the fault detection performance. Simulated data from a generic WT benchmark and field supervisory control and data acquisition data from a real wind farm are used to evaluate the proposed approach. The results of two case studies demonstrate the effectiv…
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Citations
Cites
He, H., & Garcia, E. A. (2009) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2008.239 · Cited by 10,359 · cited 2×
“Thus, the ROC curve and the AUC metric can provide a relative tradeoff between FDR and FAR and a comprehensive evaluation way [48].”
BackgroundMethodSelf-citationExtracting and composing robust features with denoising autoencoders
Vincent, P., Larochelle, H., Bengio, Y., & Manzagol, P.-A. (2008) · Proceedings of the 25th international conference on Machine learning - ICML '08 · doi:10.1145/1390156.1390294 · Cited by 7,436
(2010) · Journal of Machine Learning Research · doi:10.5555/1756006.1953039 · Cited by 4,051
A Review on Basic Data-Driven Approaches for Industrial Process Monitoring
Yin, S., Ding, S. X., Xie, X., & Luo, H. (2014) · IEEE Transactions on Industrial Electronics · doi:10.1109/tie.2014.2301773 · Cited by 1,716
Disturbance detection and isolation by dynamic principal component analysis
Ku, W., Storer, R. H., & Georgakis, C. (1995) · Chemometrics and Intelligent Laboratory Systems · doi:10.1016/0169-7439(95)00076-3 · Cited by 1,483
On optimization methods for deep learning
Ngiam, J., Coates, A., Lahiri, A., Prochnow, B., Le, Q. V., & Ng, A. Y. (2011) · International Conference on Machine Learning · Cited by 1,076
Learning a Deep Compact Image Representation for Visual Tracking
Wang, N., & Yeung, D. (2013) · neural information processing systems · Cited by 1,011
Condition monitoring and fault detection of wind turbines and related algorithms: A review
Hameed, Z., Hong, Y. S., Cho, Y. M., Ahn, S. H., & Song, C. K. (2009) · Renewable and Sustainable Energy Reviews · doi:10.1016/j.rser.2007.05.008 · Cited by 995
Reconstruction-based contribution for process monitoring
Alcala, C. F., & Qin, S. J. (2009) · Automatica · doi:10.1016/j.automatica.2009.02.027 · Cited by 567
Fault-Tolerant Control of Wind Turbines: A Benchmark Model
Odgaard, P. F., Stoustrup, J., & Kinnaert, M. (2013) · IEEE Transactions on Control Systems Technology · doi:10.1109/tcst.2013.2259235 · Cited by 538
A Survey on Wind Turbine Condition Monitoring and Fault Diagnosis—Part I: Components and Subsystems
Qiao, W., & Lu, D. (2015) · IEEE Transactions on Industrial Electronics · doi:10.1109/tie.2015.2422112 · Cited by 533
Online wind turbine fault detection through automated SCADA data analysis
Zaher, A., McArthur, S. D. J., Infield, D. G., & Patel, Y. (2009) · Wind Energy · doi:10.1002/we.319 · Cited by 464
Using SCADA data for wind turbine condition monitoring – a review
Tautz‐Weinert, J., & Watson, S. J. (2017) · IET Renewable Power Generation · doi:10.1049/iet-rpg.2016.0248 · Cited by 458
Fault detection and diagnosis based on modified independent component analysis
Lee, J., Qin, S. J., & Lee, I. (2006) · AIChE Journal · doi:10.1002/aic.10978 · Cited by 419
Wind turbine condition monitoring by the approach of SCADA data analysis
Yang, W., Court, R., & Jiang, J. (2013) · Renewable Energy · doi:10.1016/j.renene.2012.11.030 · Cited by 400
Data-driven design of robust fault detection system for wind turbines
Yin, S., Wang, G., & Karimi, H. R. (2014) · Mechatronics · doi:10.1016/j.mechatronics.2013.11.009 · Cited by 366
Nonlinear Dynamic Process Monitoring Using Canonical Variate Analysis and Kernel Density Estimations
Odiowei, P.-E. P., & Cao, Y. (2010) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2009.2032654 · Cited by 361
An Artificial Neural Network Approach for Early Fault Detection of Gearbox Bearings
Bangalore, P., & Tjernberg, L. B. (2015) · IEEE Transactions on Smart Grid · doi:10.1109/tsg.2014.2386305 · Cited by 339
Schlechtingen, M., Santos, I. F., & Achiche, S. (2013) · Applied Soft Computing · doi:10.1016/j.asoc.2012.08.033 · Cited by 311
Yin, S., & Huang, Z. (2015) · IEEE/ASME Transactions on Mechatronics · doi:10.1109/tmech.2014.2358674 · Cited by 308
Jiang, G., He, H., Xie, P., & Tang, Y. (2017) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2017.2698738 · Cited by 271
Self-citationChen, Q., Wynne, R. J., Goulding, P., & Sandoz, D. (2000) · Control Engineering Practice · doi:10.1016/s0967-0661(99)00191-4 · Cited by 218
The Distribution of Robust Distances
Hardin, J., & Rocke, D. M. (2005) · Journal of Computational and Graphical Statistics · doi:10.1198/106186005x77685 · Cited by 209
Offshore Wind Turbines: Reliability, availability and maintenance
Tavner, P. (2012) · Institution of Engineering and Technology eBooks · doi:10.1049/pbrn013e · Cited by 205
Wind Turbine Generator Condition-Monitoring Using Temperature Trend Analysis
Guo, P., Infield, D., & Yang, X. (2012) · IEEE Transactions on Sustainable Energy · doi:10.1109/tste.2011.2163430 · Cited by 198
Wind Turbine Condition Assessment Through Power Curve Copula Modeling
Gill, S., Stephen, B., & Galloway, S. (2012) · IEEE Transactions on Sustainable Energy · doi:10.1109/tste.2011.2167164 · Cited by 193
Approximate Back-Stepping Fault-Tolerant Control of the Flexible Air-Breathing Hypersonic Vehicle
An, H., Liu, J., Wang, C., & Wu, L. (2015) · IEEE/ASME Transactions on Mechatronics · doi:10.1109/tmech.2015.2507186 · Cited by 184
Nonlinear Autoassociation Is Not Equivalent to PCA
Japkowicz, N., Hanson, S. J., & Gluck, M. A. (2000) · Neural Computation · doi:10.1162/089976600300015691 · Cited by 164
Wind turbine fault detection and fault tolerant control - An enhanced benchmark challenge
Odgaard, P. F., & Johnson, K. E. (2013) · 2013 American Control Conference · doi:10.1109/acc.2013.6580525 · Cited by 163
Wind Turbine Blade Breakage Monitoring With Deep Autoencoders
Wang, L., Zhang, Z., Xu, J., & Liu, R. (2018) · IEEE Transactions on Smart Grid · doi:10.1109/tsg.2016.2621135 · Cited by 163
Wind Turbine Fault Diagnosis and Fault-Tolerant Torque Load Control Against Actuator Faults
Badihi, H., Zhang, Y. M., & Hong, H. (2014) · IEEE Transactions on Control Systems Technology · doi:10.1109/tcst.2014.2364956 · Cited by 154
Wind turbine performance assessment using multi-regime modeling approach
Lapira, E., Brisset, D., Ardakani, H. D., Siegel, D., & Lee, J. (2012) · Renewable Energy · doi:10.1016/j.renene.2012.02.018 · Cited by 142
Aghili, F., & Su, C. (2016) · IEEE/ASME Transactions on Mechatronics · doi:10.1109/tmech.2016.2547905 · Cited by 138
Two-Stage Learning to Predict Human Eye Fixations via SDAEs
Han, J., Zhang, D., Wen, S., Guo, L., Liu, T., & Li, X. (2016) · IEEE Transactions on Cybernetics · doi:10.1109/tcyb.2015.2404432 · Cited by 137
A Data-Mining Approach to Monitoring Wind Turbines
Kusiak, A., & Verma, A. (2012) · IEEE Transactions on Sustainable Energy · doi:10.1109/tste.2011.2163177 · Cited by 134
Wei, X., Verhaegen, M., & van Engelen, T. G. (2009) · International Journal of Adaptive Control and Signal Processing · doi:10.1002/acs.1162 · Cited by 132
Online Anomaly Detection for Hard Disk Drives Based on Mahalanobis Distance
Wang, Y., Miao, Q., Ma, E. W. M., Tsui, K., & PECHT, M. G. (2013) · IEEE Transactions on Reliability · doi:10.1109/tr.2013.2241204 · Cited by 110
Fault Diagnosis of a Wind Turbine Benchmark via Identified Fuzzy Models
Simani, S., Farsoni, S., & Castaldi, P. (2014) · IEEE Transactions on Industrial Electronics · doi:10.1109/tie.2014.2364548 · Cited by 108
A Benchmark Evaluation of Fault Tolerant Wind Turbine Control Concepts
Odgaard, P. F., & Stoustrup, J. (2014) · IEEE Transactions on Control Systems Technology · doi:10.1109/tcst.2014.2361291 · Cited by 104
Fault Diagnosis of Advanced Wind Turbine Benchmark using Interval-based ARRs and Observers
Sanchez, H., Escobet, T., Puig, V., & Odgaard, P. F. (2015) · IEEE Transactions on Industrial Electronics · doi:10.1109/tie.2015.2399401 · Cited by 101
An online application of dynamic PLS to a dearomatization process
Komulainen, T. M., Sourander, M., & Jämsä‐Jounela, S. (2004) · Computers & Chemical Engineering · doi:10.1016/j.compchemeng.2004.07.014 · Cited by 91
Development of a Novel Power Curve Monitoring Method for Wind Turbines and Its Field Tests
Park, J.-Y., Lee, J.-K., Oh, K., & Lee, J.-S. (2014) · IEEE Transactions on Energy Conversion · doi:10.1109/tec.2013.2294893 · Cited by 79
Vanini, Z. N. S., Meskin, N., & Khorasani, K. (2014) · Journal of Engineering for Gas Turbines and Power · doi:10.1115/1.4027215 · Cited by 78
Fault Tolerant Control of Wind Turbines using Unknown Input Observers
Odgaard, P. F., & Stoustrup, J. (2012) · IFAC Proceedings Volumes · doi:10.3182/20120829-3-mx-2028.00010 · Cited by 57
Exploiting SCADA system data for wind turbine performance monitoring
Butler, S., Ringwood, J. V., & O'Connor, F. (2013) · Conference on Control and Fault-Tolerant Systems · doi:10.1109/systol.2013.6693951 · Cited by 48
Yang, H., Huang, M., & Yang, S. (2015) · Energies · doi:10.3390/en81012100 · Cited by 40
Anomaly detection from multivariate time-series with sparse representation
Takeishi, N., & Yairi, T. (2014) · Conference proceedings/Conference proceedings - IEEE International Conference on Systems, Man, and Cybernetics · doi:10.1109/smc.2014.6974327 · Cited by 33
Powell, M. D. (1993) · Bulletin of the American Meteorological Society · Cited by 26
Employment of Kernel Methods on Wind Turbine Power Performance Assessment
Skrimpas, G. A., Sweeney, C. W., Marhadi, K. S., Jensen, B. B., Mijatović, N., & Holbøll, J. (2015) · IEEE Transactions on Sustainable Energy · doi:10.1109/tste.2015.2405971 · Cited by 19
A data-driven approach for fault diagnosis in gearbox of wind energy conversion system
Krüger, M., Ding, S. X., Haghani, A., Engel, P., & Jeinsch, T. (2013) · Conference on Control and Fault-Tolerant Systems · doi:10.1109/systol.2013.6693901 · Cited by 9
Research works printed but not linked: 2
- 10.1175/1520-0477(1993)074<0615:WMAAUT>2.0.CO;2 · doi:10.1175/1520-0477(1993)074
- fawcett, 2004, Roc graphs: Notes and practical considerations for researchers, Mach Learn, 31, 1
Cited by
A review on fault detection and diagnosis techniques: basics and beyond
Abid, A., Khan, M. T., & Iqbal, J. (2021) · Artificial Intelligence Review · doi:10.1007/s10462-020-09934-2 · Cited by 436
Condition Monitoring using Machine Learning: A Review of Theory, Applications, and Recent Advances
Surucu, O., Gadsden, S. A., & Yawney, J. (2023) · Expert Systems with Applications · doi:10.1016/j.eswa.2023.119738 · Cited by 336
Deep learning for prognostics and health management: State of the art, challenges, and opportunities
Rezaeianjouybari, B., & Shang, Y. (2020) · Measurement · doi:10.1016/j.measurement.2020.107929 · Cited by 310
Self-Supervised Learning for Time Series Analysis: Taxonomy, Progress, and Prospects
Zhang, K., Wen, Q., Zhang, C., Cai, R., Jin, M., Liu, Y., Zhang, J. Y., Liang, Y., Pang, G., Song, D., et al. (2024) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2024.3387317 · Cited by 295
“In time series modeling, more than one method can add noise to the input, such as adding Gaussian noise [69], [70] and randomly setting some time steps to zero [71], [72].”
MethodDeep Learning for fault detection in wind turbines
Helbing, G., & Ritter, M. (2018) · Renewable and Sustainable Energy Reviews · doi:10.1016/j.rser.2018.09.012 · Cited by 278
Metadata
- Authors
- Jiang, G., Xie, P., He, H., & Yan, J.
- Affiliations
- Yanshan University (CN)
- University of Rhode Island (US)
- Concordia University (CA)
- Venue
- IEEE/ASME Transactions on Mechatronics
- Published
- 2018-02
- Volume
- 23
- Issue
- 1
- Pages
- 89-100
- ISSN
- 1083-4435 (ISSN-L)
- 1941-014X
- OpenAlex
- W2761148314
- Cited by
- 288
- References
- 50
- Citations by year
- 2026: 17 · 2025: 31 · 2024: 45 · 2023: 34 · 2022: 50 · 2021: 38 · 2020: 35 · 2019: 28 · 2018: 10
- FWCI
- 12.54
- Type
- journal article
- Language
- en
- Open access
- Licence
- Locations
- IEEE/ASME Transactions on Mechatronics (publishedVersion)
- Journal of Media Literacy Education (submittedVersion, cc-by)
- Funders
- National Natural Science Foundation of China (61673336, 51529701)
- Natural Science Foundation of Hebei Province (F2016203421)
- Topics
- Physical Sciences › Engineering › Control and Systems Engineering › Machine Fault Diagnosis Techniques
- Physical Sciences › Engineering › Control and Systems Engineering › Fault Detection and Control Systems
- Physical Sciences › Engineering › Civil and Structural Engineering › Structural Health Monitoring Techniques
- Keywords
- wind turbine fault detection, denoising autoencoder, unsupervised learning, reconstruction error, sliding window, time dependence, time series, multivariate sensor data, SCADA data, wind farms
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.