Self-Supervised Voltage Sag Source Identification Method Based on CNN
A self-supervised voltage sag source identification method based on a convolution neural network is proposed in this study. In addition, a self-supervised CNN (Convolutional Neural Networks) voltage sag source identification model is constructed on the basis of the convolution neural network and Aut...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2019-03-01
|
| Series: | Energies |
| Subjects: | |
| Online Access: | http://www.mdpi.com/1996-1073/12/6/1059 |
| _version_ | 1811183918656782336 |
|---|---|
| author | Danqi Li Fei Mei Chenyu Zhang Haoyuan Sha Jianyong Zheng |
| author_facet | Danqi Li Fei Mei Chenyu Zhang Haoyuan Sha Jianyong Zheng |
| author_sort | Danqi Li |
| collection | DOAJ |
| description | A self-supervised voltage sag source identification method based on a convolution neural network is proposed in this study. In addition, a self-supervised CNN (Convolutional Neural Networks) voltage sag source identification model is constructed on the basis of the convolution neural network and AutoEncoder. The convolution layer and pool layer in CNN are used to extract the voltage sag characteristics, and the self-supervised network training process is realized based on the principle of AE. In the constructed mode, features which reflect the data characteristics are used rather than artificial features, thus improving the accuracy of practical application. It is unnecessary to input a lot of correct labels before the self-supervised training process. The model can meet the requirements of sag source identification on timeliness, practicability, diversity, and versatility in the context of modern big data. In this study, three-phase asymmetric sag sources in sag sources are classified into more detailed categories according to different fault phases. Therefore, the proposed method can not only identify the voltage sag source, but also accurately determine the specific fault phase. Finally, the optimal parameters of the model are recognized through a case study, and a self-supervised CNN model is established based on the data type of voltage sag. This model extracts features and identifies sag sources through the measured sag data. The superiority of the proposed method is verified by a comparison. |
| first_indexed | 2024-04-11T13:04:56Z |
| format | Article |
| id | doaj.art-4c579d2fd18c440a82506b1c8099f2ca |
| institution | Directory Open Access Journal |
| issn | 1996-1073 |
| language | English |
| last_indexed | 2024-04-11T13:04:56Z |
| publishDate | 2019-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Energies |
| spelling | doaj.art-4c579d2fd18c440a82506b1c8099f2ca2022-12-22T04:22:47ZengMDPI AGEnergies1996-10732019-03-01126105910.3390/en12061059en12061059Self-Supervised Voltage Sag Source Identification Method Based on CNNDanqi Li0Fei Mei1Chenyu Zhang2Haoyuan Sha3Jianyong Zheng4School of Electrical Engineering, Southeast University, Nanjing 210096, ChinaJiangsu Key Laboratory of Smart Grid Technology and Equipment, Southeast University, Nanjing 210096, ChinaState Grid Jiangsu Electric Power Co., Ltd. Research Institute, Nanjing 211113, ChinaSchool of Electrical Engineering, Southeast University, Nanjing 210096, ChinaSchool of Electrical Engineering, Southeast University, Nanjing 210096, ChinaA self-supervised voltage sag source identification method based on a convolution neural network is proposed in this study. In addition, a self-supervised CNN (Convolutional Neural Networks) voltage sag source identification model is constructed on the basis of the convolution neural network and AutoEncoder. The convolution layer and pool layer in CNN are used to extract the voltage sag characteristics, and the self-supervised network training process is realized based on the principle of AE. In the constructed mode, features which reflect the data characteristics are used rather than artificial features, thus improving the accuracy of practical application. It is unnecessary to input a lot of correct labels before the self-supervised training process. The model can meet the requirements of sag source identification on timeliness, practicability, diversity, and versatility in the context of modern big data. In this study, three-phase asymmetric sag sources in sag sources are classified into more detailed categories according to different fault phases. Therefore, the proposed method can not only identify the voltage sag source, but also accurately determine the specific fault phase. Finally, the optimal parameters of the model are recognized through a case study, and a self-supervised CNN model is established based on the data type of voltage sag. This model extracts features and identifies sag sources through the measured sag data. The superiority of the proposed method is verified by a comparison.http://www.mdpi.com/1996-1073/12/6/1059voltage sagconvolutional neural networkAutoEncodergrayscalesag source identification |
| spellingShingle | Danqi Li Fei Mei Chenyu Zhang Haoyuan Sha Jianyong Zheng Self-Supervised Voltage Sag Source Identification Method Based on CNN Energies voltage sag convolutional neural network AutoEncoder grayscale sag source identification |
| title | Self-Supervised Voltage Sag Source Identification Method Based on CNN |
| title_full | Self-Supervised Voltage Sag Source Identification Method Based on CNN |
| title_fullStr | Self-Supervised Voltage Sag Source Identification Method Based on CNN |
| title_full_unstemmed | Self-Supervised Voltage Sag Source Identification Method Based on CNN |
| title_short | Self-Supervised Voltage Sag Source Identification Method Based on CNN |
| title_sort | self supervised voltage sag source identification method based on cnn |
| topic | voltage sag convolutional neural network AutoEncoder grayscale sag source identification |
| url | http://www.mdpi.com/1996-1073/12/6/1059 |
| work_keys_str_mv | AT danqili selfsupervisedvoltagesagsourceidentificationmethodbasedoncnn AT feimei selfsupervisedvoltagesagsourceidentificationmethodbasedoncnn AT chenyuzhang selfsupervisedvoltagesagsourceidentificationmethodbasedoncnn AT haoyuansha selfsupervisedvoltagesagsourceidentificationmethodbasedoncnn AT jianyongzheng selfsupervisedvoltagesagsourceidentificationmethodbasedoncnn |