Monitoramento da Integridade Estrutural de Turbinas Eólicas Utilizando Autocodificadores Esparsos

Mariana Passamai Alvarenga; Marcos Spínola Neto; Rodrigo Astroza; Rafaelle Piazzaroli Finotti; Flávio de Souza Barbosa; Alexandre Abrahão Cury

doi:10.63595/vetor.v36i1.18355

Authors

Mariana Passamai Alvarenga Universidade Federal de Juiz de Fora
Marcos Spínola Neto Universidade Federal de Juiz de Fora https://orcid.org/0009-0008-3955-2458
Rodrigo Astroza Universidad de Los Andes - Facultad de Ingeniería y Ciencias Aplicadas https://orcid.org/0000-0003-0711-1259
Rafaelle Piazzaroli Finotti Universidade Federal de Juiz de Fora https://orcid.org/0000-0002-8569-0041
Flávio de Souza Barbosa Universidade Federal de Juiz de Fora
Alexandre Abrahão Cury Universidade Federal de Juiz de Fora https://orcid.org/0000-0002-8860-1286

DOI:

https://doi.org/10.63595/vetor.v36i1.18355

Keywords:

Sparse Autoencoder, Structural Health Monitoring, Wind Energy, Hotelling T²

Abstract

The structural health monitoring of wind turbine towers is essential to ensure operational safety and extend the lifespan of these structures used in renewable energy generation. Wind turbine towers are subjected to severe environmental conditions and significant dynamic loads due to wind, which may lead to the development of damage. Therefore, this study explores the effectiveness of using unsupervised learning techniques, specifically sparse autoencoders (SAE), for detecting structural damage in wind turbines based on dynamic signals collected during simulated operational scenarios of turbine blade prototypes. The SAE is trained using data from intact structures and tested in scenarios that include the introduction of cracks and the addition of masses to the blades. Using the Hotelling T² Control Chart, the models demonstrated robustness in correctly identifying both mass addition and the presence of cracks, regardless of turbine speed. The analyses show that the SAE is effective in extracting relevant features from the data and detecting structural changes with good accuracy and reliability. The results highlight that the SAE, combined with T² statistics, offers a robust unsupervised approach to wind turbine structural health monitoring, providing a powerful tool for predictive maintenance and early damage detection.

Downloads

Download data is not yet available.

References

[1] Y. Ou, E. N. Chatzi, V. K. Dertimanis, e M. D. Spiridonakos, “Vibration-based experimental damage detection of a small-scale wind turbine blade,” Structural Health Monitoring, vol. 16, no. 1, pp. 79–96, 2017. Disponível em: https://doi.org/10.1177/1475921716663876

[2] Y. Lee, C. Park, N. Kim, J. Ahn, e J. Jeong, “LSTM-autoencoder based anomaly detection using vibration data of wind turbines,” Sensors (Basel), vol. 24, no. 9, p. 2833, 2024. Disponível em: https://doi.org/10.3390/s24092833

[3] H. Sousa e W. Courage, “Value of information of a pro-active SHM-based tool supported by advanced FE models and bayesian statistics towards efficiency in bridge management,” Structure and Infrastructure Engineering: Maintenance, Management, Life-Cycle Design and Performance, vol. 18, no. 4, pp. 554–572, 2022. Disponível em: https://doi.org/10.1080/15732479.2021.1978507

[4] X. Wang, Y.-Q. Ni, e K.-C. Lin, “Comparison of statistical counting methods in SHM-based reliability assessment of bridges,” Journal of Civil Structural Health Monitoring, vol. 5, no. 3, pp. 275–286, 2015. Disponível em: https://doi.org/10.1007/s13349-015-0103-1

[5] F. J. Carrión, J. A. Quintana, e S. E. Crespo, “Techno-economical and practical considerations for SHM systems,” Journal of Civil Structural Health Monitoring, vol. 7, no. 2, pp. 207–215, 2017. Disponível em: https://doi.org/10.1007/s13349-017-0215-x

[6] R. P. Finotti, F. d. S. Barbosa, A. A. Cury, e R. L. Pimentel, “Numerical and experimental evaluation of structural changes using sparse auto-encoders and SVM applied to dynamic responses,” Applied Sciences (Basel), vol. 11, no. 24, p. 11965, 2021. Disponível em: https://doi.org/10.3390/app112411965

[7] M. Spínola Neto, R. Finotti, F. Barbosa, e A. Cury, “Structural damage identification using autoencoders: A comparative study,” Buildings, vol. 14, no. 7, p. 2014, 2024. Disponível em: https://doi.org/10.3390/buildings14072014

[8] A. Oliveira-Filho, R. Zemouri, P. Cambron, e A. Tahan, “Early detection and diagnosis of wind turbine abnormal conditions using an interpretable supervised variational autoencoder model,” Energies, vol. 16, no. 12, p. 4544, 2023. Disponível em: https://doi.org/10.3390/en16124544

[9] J. E. Urrea Cabus, Y. Cui, e L. B. Tjernberg, “An anomaly detection approach based on autoencoders for condition monitoring of wind turbines,” em 2022 17th International Conference on Probabilistic Methods Applied to Power Systems (PMAPS), 2022, pp. 1–6.

[10] M. D. C. Feijóo, Y. Zambrano, Y. Vidal, e C. Tutivén, “Unsupervised damage detection for offshore jacket wind turbine foundations based on an autoencoder neural network,” Sensors (Basel), vol. 21, no. 10, p. 3333, 2021. Disponível em: https://doi.org/10.3390/s21103333

[11] I. Goodfellow, Y. Bengio, e A. Courville, Deep Learning. MIT Press, 2016, http://www.deeplearningbook.org.

[12] D. C. Montgomery, Introduction to Statistical Quality Control. Wiley, 2019.

[13] T. Akiba, S. Sano, T. Yanase, T. Ohta, e M. Koyama, “Optuna,” em Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining. New York, NY, USA: ACM, Jul. 2019.

[14] L. Resende, R. Finotti, F. Barbosa, H. Garrido, A. Cury, e M. Domizio, “Damage identification using convolutional neural networks from instantaneous displacement measurements via image processing,” Structural Health Monitoring, vol. 23, no. 3, pp. 1627–1640, 2024. Disponível em: https://doi.org/10.1177/14759217231193102

[15] R. P. Finotti, C. F. d. Silva, P. H. E. Oliveira, F. d. S. Barbosa, A. A. Cury, e R. C. Silva, “Novelty detection on a laboratory benchmark slender structure using an unsupervised deep learning algorithm,” Latin American Journal of Solids and Structures, vol. 20, no. 9, 2023. Disponível em: https://doi.org/10.1590/1679-78257591

[16] J. M. Gutiérrez, R. Astroza, F. Jaramillo, M. Orchard, e M. Guarini, “Evolution of modal parameters of composite wind turbine blades under short- and long-term forced vibration tests,” Journal of Civil Structural Health Monitoring, vol. 14, no. 4, pp. 1059–1074, Apr. 2024. Disponível em: https://doi.org/10.1007/s13349-024-00773-1