STATE PREDICTION OF WIND TURBINE GENERATOR BASED ON K-CNN AND N-GRU (MT)
In order to detect abnormal wind turbine generator and reduce the occurrence of outages, a deep learning framework combining K-CNN and N-GRU is proposed based on multi-dimensional sensor parameters recorded in real wind farm SCADA system, and a wind turbine generator state prediction model is establ...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | zho |
| Published: |
Editorial Office of Journal of Mechanical Strength
2023-01-01
|
| Series: | Jixie qiangdu |
| Subjects: | |
| Online Access: | http://www.jxqd.net.cn/thesisDetails#10.16579/j.issn.1001.9669.2023.05.005 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841534201292128256 |
|---|---|
| author | CHAI Tong YUAN YiPing MA JunYan FAN PanPan |
| author_facet | CHAI Tong YUAN YiPing MA JunYan FAN PanPan |
| author_sort | CHAI Tong |
| collection | DOAJ |
| description | In order to detect abnormal wind turbine generator and reduce the occurrence of outages, a deep learning framework combining K-CNN and N-GRU is proposed based on multi-dimensional sensor parameters recorded in real wind farm SCADA system, and a wind turbine generator state prediction model is established. Firstly, the correlation of state parameters was analyzed by Pearson correlation coefficient, and then the one-dimensional fusion parameters were weighted by weight coefficient. Secondly, to solve the problem of ignoring shallow features in traditional feature extraction, CNN was used to extract the features of one-dimensional fusion parameters in layers, and KPCA was used to reduce the feature extraction results of different layers to one dimension. Then, to solve the problem of parameter optimization of the traditional GRU algorithm, the neural network architecture search was used to improve the GRU algorithm, and the N-GRU model was obtained. The feature extraction results after dimensionality reduction were input into N-GRU for prediction and reconstruction error was obtained, then the state evaluation was realized by setting the alarm threshold. Finally, a 2 MW wind turbine in a wind farm in Xinjiang was taken as an example to verify the model validity and model accuracy. |
| format | Article |
| id | doaj-art-c2bc1bddecf34d0799189cce2383a626 |
| institution | Kabale University |
| issn | 1001-9669 |
| language | zho |
| publishDate | 2023-01-01 |
| publisher | Editorial Office of Journal of Mechanical Strength |
| record_format | Article |
| series | Jixie qiangdu |
| spelling | doaj-art-c2bc1bddecf34d0799189cce2383a6262025-01-15T02:44:22ZzhoEditorial Office of Journal of Mechanical StrengthJixie qiangdu1001-96692023-01-011043104944026193STATE PREDICTION OF WIND TURBINE GENERATOR BASED ON K-CNN AND N-GRU (MT)CHAI TongYUAN YiPingMA JunYanFAN PanPanIn order to detect abnormal wind turbine generator and reduce the occurrence of outages, a deep learning framework combining K-CNN and N-GRU is proposed based on multi-dimensional sensor parameters recorded in real wind farm SCADA system, and a wind turbine generator state prediction model is established. Firstly, the correlation of state parameters was analyzed by Pearson correlation coefficient, and then the one-dimensional fusion parameters were weighted by weight coefficient. Secondly, to solve the problem of ignoring shallow features in traditional feature extraction, CNN was used to extract the features of one-dimensional fusion parameters in layers, and KPCA was used to reduce the feature extraction results of different layers to one dimension. Then, to solve the problem of parameter optimization of the traditional GRU algorithm, the neural network architecture search was used to improve the GRU algorithm, and the N-GRU model was obtained. The feature extraction results after dimensionality reduction were input into N-GRU for prediction and reconstruction error was obtained, then the state evaluation was realized by setting the alarm threshold. Finally, a 2 MW wind turbine in a wind farm in Xinjiang was taken as an example to verify the model validity and model accuracy.http://www.jxqd.net.cn/thesisDetails#10.16579/j.issn.1001.9669.2023.05.005Pearson correlation coefficientCNN stratified feature extractionKernel principal component analysisN-GRU modelReconstruction error |
| spellingShingle | CHAI Tong YUAN YiPing MA JunYan FAN PanPan STATE PREDICTION OF WIND TURBINE GENERATOR BASED ON K-CNN AND N-GRU (MT) Jixie qiangdu Pearson correlation coefficient CNN stratified feature extraction Kernel principal component analysis N-GRU model Reconstruction error |
| title | STATE PREDICTION OF WIND TURBINE GENERATOR BASED ON K-CNN AND N-GRU (MT) |
| title_full | STATE PREDICTION OF WIND TURBINE GENERATOR BASED ON K-CNN AND N-GRU (MT) |
| title_fullStr | STATE PREDICTION OF WIND TURBINE GENERATOR BASED ON K-CNN AND N-GRU (MT) |
| title_full_unstemmed | STATE PREDICTION OF WIND TURBINE GENERATOR BASED ON K-CNN AND N-GRU (MT) |
| title_short | STATE PREDICTION OF WIND TURBINE GENERATOR BASED ON K-CNN AND N-GRU (MT) |
| title_sort | state prediction of wind turbine generator based on k cnn and n gru mt |
| topic | Pearson correlation coefficient CNN stratified feature extraction Kernel principal component analysis N-GRU model Reconstruction error |
| url | http://www.jxqd.net.cn/thesisDetails#10.16579/j.issn.1001.9669.2023.05.005 |
| work_keys_str_mv | AT chaitong statepredictionofwindturbinegeneratorbasedonkcnnandngrumt AT yuanyiping statepredictionofwindturbinegeneratorbasedonkcnnandngrumt AT majunyan statepredictionofwindturbinegeneratorbasedonkcnnandngrumt AT fanpanpan statepredictionofwindturbinegeneratorbasedonkcnnandngrumt |