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...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2021-11-01
|
| Series: | International Journal of Distributed Sensor Networks |
| Online Access: | https://doi.org/10.1177/15501477211057737 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850178197942960128 |
|---|---|
| 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 |
| collection | DOAJ |
| 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 |
| id | doaj-art-c51852bee0c64b43b7cb1b64a10bd6f7 |
| institution | OA Journals |
| issn | 1550-1477 |
| language | English |
| publishDate | 2021-11-01 |
| publisher | Wiley |
| record_format | Article |
| series | International Journal of Distributed Sensor Networks |
| spelling | doaj-art-c51852bee0c64b43b7cb1b64a10bd6f72025-08-20T02:18:47ZengWileyInternational Journal of Distributed Sensor Networks1550-14772021-11-011710.1177/15501477211057737A PCC-Ensemble-TCN model for wind turbine icing detection using class-imbalanced and label-missing SCADA dataShenyi DingZhijie WangJue ZhangFang HanXiaochun GuGuangxiao SongBlade 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.https://doi.org/10.1177/15501477211057737 |
| spellingShingle | 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 International Journal of Distributed Sensor Networks |
| title | 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_short | 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 |
| url | https://doi.org/10.1177/15501477211057737 |
| 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 |