A PCC-Ensemble-TCN model for wind turbine icing detection using class-imbalanced and label-missing SCADA data

Blade icing problems are ubiquitous for wind turbines located in cold climate zones. Data-driven indirect icing detection methods based on supervisory control and data acquisition system have shown strong potential recently. However, the supervisory control and data acquisition data is annotated thr...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Shenyi Ding, Zhijie Wang, Jue Zhang, Fang Han, Xiaochun Gu, Guangxiao Song
Formato:	article
Lenguaje:	EN
Publicado:	SAGE Publishing 2021
Materias:	Electronic computers. Computer science QA75.5-76.95
Acceso en línea:	https://doaj.org/article/c51852bee0c64b43b7cb1b64a10bd6f7
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:c51852bee0c64b43b7cb1b64a10bd6f7
record_format	dspace
spelling	oai:doaj.org-article:c51852bee0c64b43b7cb1b64a10bd6f72021-12-02T03:04:56ZA PCC-Ensemble-TCN model for wind turbine icing detection using class-imbalanced and label-missing SCADA data1550-147710.1177/15501477211057737https://doaj.org/article/c51852bee0c64b43b7cb1b64a10bd6f72021-11-01T00:00:00Zhttps://doi.org/10.1177/15501477211057737https://doaj.org/toc/1550-1477Blade icing problems are ubiquitous for wind turbines located in cold climate zones. Data-driven indirect icing detection methods based on supervisory control and data acquisition system have shown strong potential recently. However, the supervisory control and data acquisition data is annotated through manual observation, which will cause the data between normal condition and icing condition to be unlabeled. In addition, the amount of normal data is far more than icing data. The above two issues restrict the performance of most current data-driven models. In order to solve the label missing problem, this article proposes a Pearson correlation coefficient–based algorithm for measuring the degree of blade icing, which calculates the similarity between the unlabeled data and the icing data as its label. Aiming at the class-imbalance problem, this article constructs multiple class-balanced subsets from the original dataset by under-sampling the normal data. Temporal convolutional networks are trained to extract features and make predictions on each subset. The final prediction result is obtained by ensembling the prediction results of all temporal convolutional network models. The proposed model is validated using the actual supervisory control and data acquisition data collected from a wind farm in northern China, and the results indicate that ensuring the consecutiveness and class-balance of the data are quite advantageous for improving the detection accuracy.Shenyi DingZhijie WangJue ZhangFang HanXiaochun GuGuangxiao SongSAGE PublishingarticleElectronic computers. Computer scienceQA75.5-76.95ENInternational Journal of Distributed Sensor Networks, Vol 17 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Electronic computers. Computer science QA75.5-76.95
spellingShingle	Electronic computers. Computer science QA75.5-76.95 Shenyi Ding Zhijie Wang Jue Zhang Fang Han Xiaochun Gu Guangxiao Song A PCC-Ensemble-TCN model for wind turbine icing detection using class-imbalanced and label-missing SCADA data
description	Blade icing problems are ubiquitous for wind turbines located in cold climate zones. Data-driven indirect icing detection methods based on supervisory control and data acquisition system have shown strong potential recently. However, the supervisory control and data acquisition data is annotated through manual observation, which will cause the data between normal condition and icing condition to be unlabeled. In addition, the amount of normal data is far more than icing data. The above two issues restrict the performance of most current data-driven models. In order to solve the label missing problem, this article proposes a Pearson correlation coefficient–based algorithm for measuring the degree of blade icing, which calculates the similarity between the unlabeled data and the icing data as its label. Aiming at the class-imbalance problem, this article constructs multiple class-balanced subsets from the original dataset by under-sampling the normal data. Temporal convolutional networks are trained to extract features and make predictions on each subset. The final prediction result is obtained by ensembling the prediction results of all temporal convolutional network models. The proposed model is validated using the actual supervisory control and data acquisition data collected from a wind farm in northern China, and the results indicate that ensuring the consecutiveness and class-balance of the data are quite advantageous for improving the detection accuracy.
format	article
author	Shenyi Ding Zhijie Wang Jue Zhang Fang Han Xiaochun Gu Guangxiao Song
author_facet	Shenyi Ding Zhijie Wang Jue Zhang Fang Han Xiaochun Gu Guangxiao Song
author_sort	Shenyi Ding
title	A PCC-Ensemble-TCN model for wind turbine icing detection using class-imbalanced and label-missing SCADA data
title_short	A PCC-Ensemble-TCN model for wind turbine icing detection using class-imbalanced and label-missing SCADA data
title_full	A PCC-Ensemble-TCN model for wind turbine icing detection using class-imbalanced and label-missing SCADA data
title_fullStr	A PCC-Ensemble-TCN model for wind turbine icing detection using class-imbalanced and label-missing SCADA data
title_full_unstemmed	A PCC-Ensemble-TCN model for wind turbine icing detection using class-imbalanced and label-missing SCADA data
title_sort	pcc-ensemble-tcn model for wind turbine icing detection using class-imbalanced and label-missing scada data
publisher	SAGE Publishing
publishDate	2021
url	https://doaj.org/article/c51852bee0c64b43b7cb1b64a10bd6f7
work_keys_str_mv	AT shenyiding apccensembletcnmodelforwindturbineicingdetectionusingclassimbalancedandlabelmissingscadadata AT zhijiewang apccensembletcnmodelforwindturbineicingdetectionusingclassimbalancedandlabelmissingscadadata AT juezhang apccensembletcnmodelforwindturbineicingdetectionusingclassimbalancedandlabelmissingscadadata AT fanghan apccensembletcnmodelforwindturbineicingdetectionusingclassimbalancedandlabelmissingscadadata AT xiaochungu apccensembletcnmodelforwindturbineicingdetectionusingclassimbalancedandlabelmissingscadadata AT guangxiaosong apccensembletcnmodelforwindturbineicingdetectionusingclassimbalancedandlabelmissingscadadata AT shenyiding pccensembletcnmodelforwindturbineicingdetectionusingclassimbalancedandlabelmissingscadadata AT zhijiewang pccensembletcnmodelforwindturbineicingdetectionusingclassimbalancedandlabelmissingscadadata AT juezhang pccensembletcnmodelforwindturbineicingdetectionusingclassimbalancedandlabelmissingscadadata AT fanghan pccensembletcnmodelforwindturbineicingdetectionusingclassimbalancedandlabelmissingscadadata AT xiaochungu pccensembletcnmodelforwindturbineicingdetectionusingclassimbalancedandlabelmissingscadadata AT guangxiaosong pccensembletcnmodelforwindturbineicingdetectionusingclassimbalancedandlabelmissingscadadata
_version_	1718402007051534336

A PCC-Ensemble-TCN model for wind turbine icing detection using class-imbalanced and label-missing SCADA data

Ejemplares similares