Home > Research > Publications & Outputs > Wind Turbine Blade Icing Diagnosis Using Convol...

Research

Associated organisational unit

Links

Text available via DOI:

View graph of relations

Wind Turbine Blade Icing Diagnosis Using Convolutional LSTM-GRU With Improved African Vultures Optimization

Research output: Contribution to Journal/Magazine › Journal article › peer-review

Published

Standard

Wind Turbine Blade Icing Diagnosis Using Convolutional LSTM-GRU With Improved African Vultures Optimization. / Chen, Wenhe; Zhou, Hanting; Cheng, Longsheng et al.
In: IEEE Open Journal of Instrumentation and Measurement, Vol. 1, 3500809, 30.11.2022, p. 1-9.

Research output: Contribution to Journal/Magazine › Journal article › peer-review

Harvard

Chen, W, Zhou, H, Cheng, L & Xia, M 2022, 'Wind Turbine Blade Icing Diagnosis Using Convolutional LSTM-GRU With Improved African Vultures Optimization', IEEE Open Journal of Instrumentation and Measurement, vol. 1, 3500809, pp. 1-9. https://doi.org/10.1109/ojim.2022.3217850

APA

Chen, W., Zhou, H., Cheng, L., & Xia, M. (2022). Wind Turbine Blade Icing Diagnosis Using Convolutional LSTM-GRU With Improved African Vultures Optimization. IEEE Open Journal of Instrumentation and Measurement, 1, 1-9. Article 3500809. https://doi.org/10.1109/ojim.2022.3217850

Vancouver

Chen W, Zhou H, Cheng L, Xia M. Wind Turbine Blade Icing Diagnosis Using Convolutional LSTM-GRU With Improved African Vultures Optimization. IEEE Open Journal of Instrumentation and Measurement. 2022 Nov 30;1:1-9. 3500809. doi: 10.1109/ojim.2022.3217850

Author

Chen, Wenhe ; Zhou, Hanting ; Cheng, Longsheng et al. / Wind Turbine Blade Icing Diagnosis Using Convolutional LSTM-GRU With Improved African Vultures Optimization. In: IEEE Open Journal of Instrumentation and Measurement. 2022 ; Vol. 1. pp. 1-9.

Bibtex

@article{1db583d2da1f4418be2c1a98fc652cf1,
title = "Wind Turbine Blade Icing Diagnosis Using Convolutional LSTM-GRU With Improved African Vultures Optimization",
abstract = "Wind farms are usually located in plateau mountains and northern coastal areas, bringing a high probability of blade icing. Blade icing even leads to blade cracks and turbine collapse. Traditional methods of blade icing diagnosis increase operating costs and have the potential risk of damaging the original mechanical structure. A data-driven model based on a novel convolutional recurrent neural network is proposed in this article. The method can effectively extract hidden features for accurate icing diagnosis. The hyperparameters of the proposed model are optimized by the improved African vultures optimization algorithm (IAVOA). To alleviate the critical data imbalance, the adaptive synthetic (ADASYN) is used to oversample the minority classes of icing status. In comparison to the state-of-the-art classification methods, the proposed method illustrates the outstanding effectiveness in blade icing diagnosis using the sensor data from supervisory control and data acquisition (SCADA) systems. The effectiveness analysis of variables, ablation study, and sensitivity analysis validates the performance of the proposed method.",
author = "Wenhe Chen and Hanting Zhou and Longsheng Cheng and Min Xia",
year = "2022",
month = nov,
day = "30",
doi = "10.1109/ojim.2022.3217850",
language = "English",
volume = "1",
pages = "1--9",
journal = "IEEE Open Journal of Instrumentation and Measurement",
issn = "2768-7236",
publisher = "Institute of Electrical and Electronics Engineers (IEEE)",

}

RIS

TY - JOUR

T1 - Wind Turbine Blade Icing Diagnosis Using Convolutional LSTM-GRU With Improved African Vultures Optimization

AU - Chen, Wenhe

AU - Zhou, Hanting

AU - Cheng, Longsheng

AU - Xia, Min

PY - 2022/11/30

Y1 - 2022/11/30

N2 - Wind farms are usually located in plateau mountains and northern coastal areas, bringing a high probability of blade icing. Blade icing even leads to blade cracks and turbine collapse. Traditional methods of blade icing diagnosis increase operating costs and have the potential risk of damaging the original mechanical structure. A data-driven model based on a novel convolutional recurrent neural network is proposed in this article. The method can effectively extract hidden features for accurate icing diagnosis. The hyperparameters of the proposed model are optimized by the improved African vultures optimization algorithm (IAVOA). To alleviate the critical data imbalance, the adaptive synthetic (ADASYN) is used to oversample the minority classes of icing status. In comparison to the state-of-the-art classification methods, the proposed method illustrates the outstanding effectiveness in blade icing diagnosis using the sensor data from supervisory control and data acquisition (SCADA) systems. The effectiveness analysis of variables, ablation study, and sensitivity analysis validates the performance of the proposed method.

AB - Wind farms are usually located in plateau mountains and northern coastal areas, bringing a high probability of blade icing. Blade icing even leads to blade cracks and turbine collapse. Traditional methods of blade icing diagnosis increase operating costs and have the potential risk of damaging the original mechanical structure. A data-driven model based on a novel convolutional recurrent neural network is proposed in this article. The method can effectively extract hidden features for accurate icing diagnosis. The hyperparameters of the proposed model are optimized by the improved African vultures optimization algorithm (IAVOA). To alleviate the critical data imbalance, the adaptive synthetic (ADASYN) is used to oversample the minority classes of icing status. In comparison to the state-of-the-art classification methods, the proposed method illustrates the outstanding effectiveness in blade icing diagnosis using the sensor data from supervisory control and data acquisition (SCADA) systems. The effectiveness analysis of variables, ablation study, and sensitivity analysis validates the performance of the proposed method.

U2 - 10.1109/ojim.2022.3217850

DO - 10.1109/ojim.2022.3217850

M3 - Journal article

VL - 1

SP - 1

EP - 9

JO - IEEE Open Journal of Instrumentation and Measurement

JF - IEEE Open Journal of Instrumentation and Measurement

SN - 2768-7236

M1 - 3500809

ER -