Convolutional Neural Networks using the SMOTE Algorithm and Features Fusion for Wind Turbine Fault Prediction

Authors

Keywords:

Machine Learning, Convolutional Neural Networks, Wind turbine faul detection, Wind turbine failure predict

Abstract

This research introduces an innovative method using Convolutional Neural Networks (CNNs) to identify mass imbalances in wind turbine rotors through a feature fusion strategy. To address the issue of class imbalance, the Synthetic Minority Oversampling Technique (SMOTE) is applied. A detailed simulation was carried out using a 1.5 MW three-bladed Wind Turbine model, employing tools such as Turbsim, FAST, and Matlab Simulink, to collect rotor speed data under different wind conditions. Mass imbalances were simulated by modifying blade density in the software. The fusion architecture combines feature extraction with Power Spectral Density analysis, improving the CNN’s ability to work across both frequency and time domains. The effectiveness of this approach was confirmed through a comparative analysis with 9 classifiers and 4 different dataset combinations, demonstrating its capability in detecting mass imbalances.

Downloads

Download data is not yet available.

Author Biographies

Mr. Lucas França Aires, Universidade Federal de Santa Maria

Lucas Franca is a student of Electrical Engineering at the Federal University of Santa Maria. Currently develops projects in machine learning, focused on the utilization of Convolutional Neural Networks. Also has research interests in embedded systems and electronics.

Mr. Júlio Oliveira Schmidt, Universidade Federal de Santa Maria

Julio Oliveira is a student of Electrical Engineering at the Federal University of Santa Maria. Presently working on projects within the realm of artificial intelligence, with a particular focus on the application of Long Short-Term Memory and Convolutional Neural Networks.

Dr. Guilherme Ricardo Hübner, Universidade Federal de Santa Maria

Guilherme Hubner received his BSc.Degree in control and automation engineering from Universidade Federal de Santa Maria (UFSM), in Santa Maria, Brazil (2018), and his MSc in Electrical Engineering from Universidade Federal de Santa Maria (UFSM), in Santa Maria, Brazil(2021). His current research interest centers on artificial intelligence techniques applied in predictive maintenance solutions.

Dr. Frederico Menine Schaf, Universidade Federal de Santa Maria

Federico Menine received Electrical Engineering BSc. degree from the Federal University of Santa Maria (2002), master's (2006) and doctorate (2011) degree in Electrical Engineering from the Federal University of Rio Grande do Sul in the research area of industrial process automation. He is currently an associate professor at the Federal University of Santa Maria (UFSM). He has experience in the area of Industrial Automation, Wind Power Generation, and Educational Technologies, with an emphasis on Automation 

Dr. Claiton Moro Franchi, Universidade Federal de Santa Maria

Claiton Moro received Electrical Engineering BSc. degree from the Federal University of Santa Maria (2002), Master in Chemical Engineering from the State University of Maringá (2007). PhD in Chemical Engineering from the State University of Maringá (2010). He is currently a professor at the Federal University of Santa Maria. affiliated with the Department of Electric Energy Processing (DPEE) at the Technology Center (CT) Has experience in Electrical and Chemical Engineering, with emphasis on Process Control and Industrial Automation, working mainly on the following topics: Wind energy, supervision systems, programmable logic controllers and industrial networks and industrial process control.

Dr. Humberto Pinheiro, Universidade Federal de Santa Maria

Humberto Pinheiro received the B.S. degree from the Federal University of Santa Maria (UFSM), Santa Maria, Brazil, in 1983, the M.Eng. degree from the Federal University of Santa Catarina, Florianópolis, Brazil, in 1987, and the Ph.D. degree from Concordia University, Montreal, QC, Canada, in 1999. From 1987 to 1999, he was a Research Engineer with a Brazilian UPS company and a Professor with the Pontificia Universidade Católica do Rio Grande do Sul, Porto Alegre, Brazil, where he lectured on power electronics. Since 1991, he has been with UFSM. His research interests include modulation and control of static converters especially those used for the connection DER to the electric grid. Dr. Pinheiro has more than eighty journal papers and has supervised more than ten Ph.D. students. Dr. Pinheiro is a member of the IEEE Power Electronics and IEEE Industrial Electronics Societies.

Daniel Fernando Tello Gamarra, Universidade Federal de Santa Maria (UFSM)

Daniel Tello received his BSc.Degree in mechanical engineering from Universidad Nacional del Centro del Peru (UNCP), in Huancayo, Peru (1999), and his MSc in electrical Engineering from Universidade Federal do Espirito Santo (UFES), in Espirito Santo, Brazil(2004) and PhD degree in Biomedical Robotics from Scuola Superiore Santa Anna, Italy (2009). He is Professor at the Universidade Federal de Santa Maria(UFSM), in Santa Maria, Rio Grande do Sul, Brazil. His current research interest centers on robotics, computational vision and machine learning.

References

G. W. E. Council, “Gwec global wind report 2021,” Global Wind Energy

Council: Brussels, Belgium, 2021.

X. Chen, X. Zhang, M. Dong, L. Huang, Y. Guo, and S. He, “Deep

learning-based prediction of wind power for multi-turbines in a wind

farm,” Frontiers in Energy Research, p. 403, 2021. doi:https://doi.org/

3389/fenrg.2021.723775.

M. Kaasik and S. Mirme, “Wind: generating power and cooling the

power lines,” Advances in Science and Research, vol. 17, pp. 105–108,

doi:https://doi.org/10.5194/asr-17-105-2020.

S.-Y. Cho, S.-K. Choi, J.-G. Kim, and C.-H. Cho, “An experimental

study of the optimal design parameters of a wind power tower used to

improve the performance of vertical axis wind turbines,” Advances in

Mechanical Engineering, vol. 10, no. 9, p. 1687814018799543, 2018.

doi:https://doi.org/10.1177/1687814018799543.

X. Gong and W. Qiao, “Imbalance fault detection of direct-drive wind

turbines using generator current signals,” IEEE Transactions on energy

conversion, vol. 27, no. 2, pp. 468–476, 2012. doi:https://doi.org/10.

/PESMG.2013.6672920.

J. Wang, Y. Liang, Y. Zheng, R. X. Gao, and F. Zhang, “An integrated

fault diagnosis and prognosis approach for predictive maintenance of

wind turbine bearing with limited samples,” Renewable Energy, vol. 145,

pp. 642–650, 2020. doi:http://dx.doi.org/10.1016/j.renene.2019.06.103.

L. Mishnaevsky Jr, “Repair of wind turbine blades: Review of methods

and related computational mechanics problems,” Renewable energy,

vol. 140, pp. 828–839, 2019. doi:https://doi.org/10.1016/j.renene.2019.

113.

Q. Gao, W. Liu, B. Tang, and G. Li, “A novel wind turbine fault

diagnosis method based on intergral extension load mean decomposition

multiscale entropy and least squares support vector machine,” Renewable

energy, vol. 116, pp. 169–175, 2018. doi:https://doi.org/10.1016/j.

renene.2017.09.061.

Y. Li, W. Jiang, G. Zhang, and L. Shu, “Wind turbine fault diagnosis

based on transfer learning and convolutional autoencoder with smallscale

data,” Renewable Energy, vol. 171, pp. 103–115, 2021. doi:https:

//doi.org/10.1016/j.renene.2021.01.143.

S. Cho, M. Choi, Z. Gao, and T. Moan, “Fault detection and diagnosis

of a blade pitch system in a floating wind turbine based on kalman filters

and artificial neural networks,” Renewable Energy, vol. 169, pp. 1–13,

doi:https://doi.org/10.1016/j.renene.2020.12.116.

H. Malik and S. Mishra, “Artificial neural network and empirical mode

decomposition based imbalance fault diagnosis of wind turbine using

turbsim, fast and simulink,” IET Renewable Power Generation, vol. 11,

no. 6, pp. 889–902, 2017. doi: https://doi.org/10.1049/iet-rpg.2015.0382.

Y. Chang, J. Chen, C. Qu, and T. Pan, “Intelligent fault diagnosis of

wind turbines via a deep learning network using parallel convolution

layers with multi-scale kernels,” Renewable Energy, vol. 153, pp. 205–

, 2020. doi:https://doi.org/10.1016/j.renene.2020.02.004.

J. Zeng and B. Song, “Research on experiment and numerical simulation

of ultrasonic de-icing for wind turbine blades,” Renewable Energy,

vol. 113, pp. 706–712, 2017. doi:https://doi.org/10.1016/j.renene.2017.

045.

G. Hübner, H. Pinheiro, C. de Souza, C. Franchi, L. da Rosa, and J. Dias,

“Detection of mass imbalance in the rotor of wind turbines using support

vector machine,” Renewable Energy, 2021. doi: https://doi.org/10.1016/

j.renene.2021.01.080.

N. V. Chawla, K. W. Bowyer, L. O. Hall, and W. P. Kegelmeyer,

“Smote synthetic minority oversampling technique,” Journal Of Artificial

Intelligence Research, vol. 16, pp. 321–357, 2002. doi:https:

//doi.org/10.1613/jair.953.

H. He and E. A. Garcia, “Learning from imbalanced data,” IEEE

Transactions on Knowledge and Data Engineering, vol. 21, no. 9,

pp. 1263–1284, 2009. doi:https://doi.org/10.1109/TKDE.2008.239.

B. Yegnanarayana, “Artificial neural networks for pattern recognition,”

vol. 19, pp. 189–238, 1994. doi:https://doi.org/10.1007/BF02811896.

H. Ramchoun, M. J. Idrissi, Y. Ghanou, and M. Ettaouil, “Multilayer

perceptron: Architecture optimization and training,” Int. J. Interact.

Multim. Artif. Intell., vol. 4, pp. 26–30, 2016. doi:https://doi.org/10.

/ijimai.2016.415.

S. Albawi, T. Mohammed, and S. Al-Zawi, “Understanding of a convolutional

neural network,” 2017 International Conference on Engineering

and Technology (ICET), pp. 1–6, 2017. doi:https://doi.org/10.1109/

ICEngTechnol.2017.8308186.

G. Huang, Z. Liu, L. Van Der Maaten, and K. Q. Weinberger, “Densely

connected convolutional networks,” in 2017 IEEE Conference on Computer

Vision and Pattern Recognition (CVPR), pp. 2261–2269, 2017.

doi:https://doi.org/10.1109/CVPR.2017.243.

D. Scherer, A. Müller, and S. Behnke, “Evaluation of pooling operations

in convolutional architectures for object recognition,” in Artificial Neural

Networks – ICANN 2010 (K. Diamantaras, W. Duch, and L. S. Iliadis,

eds.), (Berlin, Heidelberg), pp. 92–101, Springer Berlin Heidelberg,

doi:https://doi.org/10.1007/978-3-642-15825-4_10.

S. Park and N. Kwak, “Analysis on the dropout effect in convolutional

neural networks,” in Asian Conference on Computer Vision, 2016.

doi:https://doi.org/10.1007/978-3-319-54184-6_12.

P. Welch, “The use of fast fourier transform for the estimation of power

spectra: A method based on time averaging over short, modified periodograms,”

IEEE Transactions on Audio and Electroacoustics, vol. 15,

no. 2, pp. 70–73, 1967. doi:https://doi.org/10.1109/TAU.1967.1161901.

R. N. Youngworth, B. B. Gallagher, and B. L. Stamper, “An overview

of power spectral density (PSD) calculations,” in Optical Manufacturing

and Testing VI (H. P. Stahl, ed.), vol. 5869, pp. 206 – 216, International

Society for Optics and Photonics, SPIE, 2005.

Z. Wang and T. Oates, “Imaging time-series to improve classification

and imputation,” in Proceedings of the 24th International Conference

on Artificial Intelligence, IJCAI’15, p. 3939–3945, AAAI Press, 2015.

O. Gecgel, S. Ekwaro-Osire, J. P. Dias, A. Serwadda, F. M. Alemayehu,

and A. Nispel, “Gearbox fault diagnostics using deep learning with

simulated data,” in 2019 IEEE International Conference on Prognostics

and Health Management (ICPHM), pp. 1–8, 2019. doi:10.1109/ICPHM.

8819423.

Downloads

Published

2025-01-30

How to Cite

França Aires, . L., Oliveira Schmidt, J. ., Hübner, G. R. ., Menine Schaf, F., Moro Franchi, C., Pinheiro, H. ., & Tello Gamarra, D. F. (2025). Convolutional Neural Networks using the SMOTE Algorithm and Features Fusion for Wind Turbine Fault Prediction. IEEE Latin America Transactions, 23(3), 191–197. Retrieved from https://latamt.ieeer9.org/index.php/transactions/article/view/9269

Issue

Vol. 23 No. 3 (2025): Ordinary Issue

Section

Computing

Most read articles by the same author(s)