Aplicação de Modelos Ocultos de Markov para Detecção de Falhas em Componentes de Turbinas Eólicas
Resumo
A demanda crescente por soluções energéticas renováveis destaca a importância das turbinas eólicas na conversão de energia. Monitorar, diagnosticar e prever falhas nesses sistemas e crucial para garantir a produção contínua de energia. Sensores monitoram o funcionamento das turbinas e os dados coletados são usados para criar modelos que identificam sinais precoces de deterioração, permitindo a detecção rápida de falhas e a redução dos custos de manutenção. Este estudo propõe uma abordagem baseada em Modelos Ocultos de Markov para monitorar e diagnosticar falhas em geradores e caixas de velocidade de turbinas eólicas. Os resultados obtidos pela métrica F-Score demonstram a viabilidade da abordagem proposta.
Palavras-chave:
Monitoramento de Falhas, Turbinas Eólicas, Modelos Ocultos de Markov
Referências
Baum, L. and Petrie, T. (1966). Statistical inference for probabilistic functions of finite state markov chains. The Annals of Mathematical Statistics, 37(6):1554–1563.
Bilmes, J. et al. (1998). A gentle tutorial of the EM algorithm and its application to parameter estimation for gaussian mixture and hidden markov models. International Computer Science Institute, 4(510):126.
Chen, P. et al. (2021). A threshold self-setting condition monitoring scheme for wind turbine generator bearings based on deep convolutional generative adversarial networks. Measurement, 167:108234.
Council, G. W. E. (2021). Global wind report 2021. [link], Acessado em 10/04/2024.
EDP (2021). Edp - open data. [link], Acessado em 07/08/2021.
Feng, Z. et al. (2023). Rolling bearing performance degradation assessment with adaptive sensitive feature selection and multi-strategy optimized svdd. Sensors, 23(3):1110.
Ghojogh, B. et al. (2019). Hidden markov model: Tutorial. engrXiv.
Jiang, Z. et al. (2021). Fault detection and diagnosis of wind turbine gearbox based on acoustic analysis. In 2021 International Conference on Power System Technology (POWERCON), pages 2047–2052. IEEE.
Khan, P. and Byun, Y. (2024). A review of machine learning techniques for wind turbine’s fault detection, diagnosis, and prognosis. International Journal of Green Energy, 21.
Kidam, K. and Hurme, M. (2013). Analysis of equipment failures as contributors to chemical process accidents. Process Safety and Environmental Protection.
Kobbacy, K. and Murthy, D. (2008). Complex system maintenance handbook. Springer Science & Business Media.
Kouadri, A. et al. (2020). Hidden markov model-based principal component analysis for intelligent fault diagnosis of wind energy converter systems. Renewable Energy, 150.
Li, J. et al. (2019). Reliability assessment of wind turbine bearing based on the degradation-hidden-markov model. Renewable Energy, 132:1076–1087.
Li, X. et al. (2024). Correlation warping radius tracking for condition monitoring of rolling bearings under varying operating conditions. Mechanical Systems and Signal Processing, 208:110943.
Lou, H.-L. (1995). Implementing the viterbi algorithm. IEEE Signal processing magazine, 12(5):42–52.
Rabiner, L. and Juang, B. (1986). An introduction to hidden markov models. IEEE ASSP Magazine, 3(1):4–16.
Sa, F. d. et al. (2023). Wind turbine fault detection: a semi-supervised learning approach with two different dimensionality reduction techniques. International Journal of Innovative Computing and Applications, 14(1-2):67–77.
Sahu, D., Dewangan, R. K., and Matharu, S. P. S. (2024). An investigation of fault detection techniques in rolling element bearing. Journal of Vibration Engineering & Technologies, 12(4):5585–5608.
Seymore, K. et al. (1999). Learning hidden markov model structure for information extraction. In AAAI - workshop on machine learning for information extraction.
Xu, J. et al. (2023). Physics-guided, data-refined fault root cause tracing framework for complex electromechanical system. Reliability Engineering System Safety, 236.
Bilmes, J. et al. (1998). A gentle tutorial of the EM algorithm and its application to parameter estimation for gaussian mixture and hidden markov models. International Computer Science Institute, 4(510):126.
Chen, P. et al. (2021). A threshold self-setting condition monitoring scheme for wind turbine generator bearings based on deep convolutional generative adversarial networks. Measurement, 167:108234.
Council, G. W. E. (2021). Global wind report 2021. [link], Acessado em 10/04/2024.
EDP (2021). Edp - open data. [link], Acessado em 07/08/2021.
Feng, Z. et al. (2023). Rolling bearing performance degradation assessment with adaptive sensitive feature selection and multi-strategy optimized svdd. Sensors, 23(3):1110.
Ghojogh, B. et al. (2019). Hidden markov model: Tutorial. engrXiv.
Jiang, Z. et al. (2021). Fault detection and diagnosis of wind turbine gearbox based on acoustic analysis. In 2021 International Conference on Power System Technology (POWERCON), pages 2047–2052. IEEE.
Khan, P. and Byun, Y. (2024). A review of machine learning techniques for wind turbine’s fault detection, diagnosis, and prognosis. International Journal of Green Energy, 21.
Kidam, K. and Hurme, M. (2013). Analysis of equipment failures as contributors to chemical process accidents. Process Safety and Environmental Protection.
Kobbacy, K. and Murthy, D. (2008). Complex system maintenance handbook. Springer Science & Business Media.
Kouadri, A. et al. (2020). Hidden markov model-based principal component analysis for intelligent fault diagnosis of wind energy converter systems. Renewable Energy, 150.
Li, J. et al. (2019). Reliability assessment of wind turbine bearing based on the degradation-hidden-markov model. Renewable Energy, 132:1076–1087.
Li, X. et al. (2024). Correlation warping radius tracking for condition monitoring of rolling bearings under varying operating conditions. Mechanical Systems and Signal Processing, 208:110943.
Lou, H.-L. (1995). Implementing the viterbi algorithm. IEEE Signal processing magazine, 12(5):42–52.
Rabiner, L. and Juang, B. (1986). An introduction to hidden markov models. IEEE ASSP Magazine, 3(1):4–16.
Sa, F. d. et al. (2023). Wind turbine fault detection: a semi-supervised learning approach with two different dimensionality reduction techniques. International Journal of Innovative Computing and Applications, 14(1-2):67–77.
Sahu, D., Dewangan, R. K., and Matharu, S. P. S. (2024). An investigation of fault detection techniques in rolling element bearing. Journal of Vibration Engineering & Technologies, 12(4):5585–5608.
Seymore, K. et al. (1999). Learning hidden markov model structure for information extraction. In AAAI - workshop on machine learning for information extraction.
Xu, J. et al. (2023). Physics-guided, data-refined fault root cause tracing framework for complex electromechanical system. Reliability Engineering System Safety, 236.
Publicado
14/10/2024
Como Citar
DE SÁ, Fernando; PINNA, Danielle; FERNANDES, Kennedy; DE OLIVEIRA, Sanderson Gonzaga; TOSO, Rodrigo; BELLOZE, Kele; BRANDÃO, Diego Nunes.
Aplicação de Modelos Ocultos de Markov para Detecção de Falhas em Componentes de Turbinas Eólicas. In: BRAZILIAN E-SCIENCE WORKSHOP (BRESCI), 18. , 2024, Florianópolis/SC.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2024
.
p. 8-15.
ISSN 2763-8774.
DOI: https://doi.org/10.5753/bresci.2024.243868.
