Fault detection in wind turbines: a supervised learning approach with multilayer perceptron neural network
Detecção de falhas em turbinas eólicas: uma abordagem de aprendizagem supervisionada com rede neural perceptron multicamadas
Palavras-chave:
Wind turbines, Supervisory control and data acquisition system, Attribute extraction, Multi layer perceptron, Fault detectionResumo
The expansion of energies aligning with sustainable development requirements is continually progressing. A particular focus on wind turbines (WT), characterized as a highly intricate system, has brought attention to the costs associated with operation and maintenance. This has prompted a quest for increasingly efficient maintenance procedures. This article proposes that deviations from expected behavior be detected and classified as failure using operational data from permanent magnet direct drive wind turbines, obtained through the supervisory control and data acquisition system. To achieve real-time fault detection and gather information on the state of faults, the CFS subset evaluator method was employed to extract the most relevant attributes from the dataset. Experimental results demonstrate that the strategy of selecting the most pertinent attributes for the Multilayer Perceptron algorithm (MLP), comprising four layers, in fault classification, resulted in a high recognition rate for detecting and classifying faults in wind turbines. Computational results validating the models are presented.
Downloads
Referências
BAJAJ, Naman S. et al. Aplicação de máquina de vetores de suporte baseada em otimização metaheurística para monitoramento da integridade da fresa. Sistemas Inteligentes com Aplicações , v. 18, p. 200196, 2023. Doi:10.1016/j.iswa.2023.200196.
BEAUSON, J. et al. The complex end-of-life of wind turbine blades: A review of the European context. Renewable and Sustainable Energy Reviews, v. 155, p. 111847, 2022. Doi:10.1016/j.rser.2021.111847.
BloombergNEF. Wind-10 Predictions for 2022. 2022. In: https://about.bnef.com/blog/wind-10-predictions-for-2022/ (Accessed on 02 december 2023).
GUO, Xinyang et al. Grid integration feasibility and investment planning of offshore wind power under carbon-neutral transition in China. Nature Communications, v. 14, n. 1, p. 2447, 2023. Doi:10.1038/s41467-023-37536-3.
Hall, Mark A. Correlation-based feature subset selection for machine learning. Thesis Submitted in Partial Fulfillment of the Requirements of the Degree of Doctor of Philosophy at the University of Waikato, 1998.
KALE, Archana P. et al. Development of Deep Belief Network for Tool Faults Recognition. Sensors, v. 23, n. 4, p. 1872, 2023. Doi:10.3390/s23041872.
KONG, Lingchao et al. Research on wind turbine fault detection based on the fusion of ASL-CatBoost and TtRSA. Sensors, v. 23, n. 15, p. 6741, 2023. Doi:10.3390/s23156741.
LEAHY, Kevin et al. Diagnosing wind turbine faults using machine learning techniques applied to operational data. In: 2016 ieee international conference on prognostics and health management (icphm). IEEE, 2016. p. 1-8. Doi:10.1109/ICPHM.2016.7542860.
LIU, Huan; MOTODA, Hiroshi; YU, Lei. A selective sampling approach to active feature selection. Artificial Intelligence, v. 159, n. 1-2, p. 49-74, 2004. Doi:10.1016/j.artint.2004.05.009.
PAL, Kaushika; PATEL, Biraj V. Data classification with k-fold cross validation and holdout accuracy estimation methods with 5 different machine learning techniques. In: 2020 fourth international conference on computing methodologies and communication (ICCMC). IEEE, 2020. p. 83-87. Doi:10.1109/ICCMC48092.2020.ICCMC-00016.
PATANGE, A. D. et al. Application of machine learning for tool condition monitoring in turning. Sound Vib, v. 56, p. 127-145, 2022. Doi:10.32604/sv.2022.014910.
SANTOLAMAZZA, Annalisa; DADI, Daniele; INTRONA, Vito. A data-mining approach for wind turbine fault detection based on SCADA data analysis using artificial neural networks. Energies, v. 14, n. 7, p. 1845, 2021. Doi:10.3390/en14071845.
STETCO, Adrian et al. Machine learning methods for wind turbine condition monitoring: A review. Renewable energy, v. 133, p. 620-635, 2019. Doi:10.1016/j.renene.2018.10.047.
TOMA, Rafia Nishat; PROSVIRIN, Alexander E.; KIM, Jong-Myon. Bearing fault diagnosis of induction motors using a genetic algorithm and machine learning classifiers. Sensors, v. 20, n. 7, p. 1884, 2020. Doi:10.3390/s20071884.
ULUYOL, Onder et al. Power curve analytic for wind turbine performance monitoring and prognostics. In: Annual conference of the PHM society. 2011.
WANG, Chao. Health Monitoring and Fault Diagnostics of Wind Turbines. 2016. Doi:10.5278/vbn.phd.engsci.00152.
WANG, Ziqi; LIU, Changliang. Wind turbine condition monitoring based on a novel multivariate state estimation technique. Measurement, v. 168, p. 108388, 2021. Doi:10.1016/j.measurement.2020.108388.
WWEA. (2022). Annual Report 2022: Wind Power Installations 2022 Stay Below Expectations. In: https://wwindea.org/wp-content/uploads/2023/03/WWEA_WPR2022.pdf (Accessed on 02 december 2023).
XIAO, Cheng et al. Deep learning method for fault detection of wind turbine converter. Applied Sciences, v. 11, n. 3, p. 1280, 2021. Doi:10.3390/app11031280.
ZAHER, A. S. A. E. et al. Online wind turbine fault detection through automated SCADA data analysis. Wind Energy: An International Journal for Progress and Applications in Wind Power Conversion Technology, v. 12, n. 6, p. 574-593, 2009. Doi:https://10.1002/we.319.
