A lightweight power quality disturbance recognition model based on CNN and Transformer
A lightweight power quality disturbances (PQDs) recognition model that integrates convolutional neural network (CNN) and Transformer (CaT) is proposed to address the high number of parameters and computational complexity in existing deep learning-based models. Depthwise separable convolutions are fi...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | zho |
| Published: |
Editorial Department of Electric Power Engineering Technology
2025-01-01
|
| Series: | 电力工程技术 |
| Subjects: | |
| Online Access: | https://www.epet-info.com/dlgcjsen/article/abstract/240907889 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1823865246767382528 |
|---|---|
| author | ZHANG Bide QIU Jie LOU Guangxin ZHOU Can LUO Qingqing LI Tianqian |
| author_facet | ZHANG Bide QIU Jie LOU Guangxin ZHOU Can LUO Qingqing LI Tianqian |
| author_sort | ZHANG Bide |
| collection | DOAJ |
| description | A lightweight power quality disturbances (PQDs) recognition model that integrates convolutional neural network (CNN) and Transformer (CaT) is proposed to address the high number of parameters and computational complexity in existing deep learning-based models. Depthwise separable convolutions are first employed to extract local features from the disturbance signals. An efficient softthreshold block is then introduced to reduce noise and redundant features without significantly increasing the model′s parameters or complexity. The Transformer model is used to capture global features of the disturbance signals. Finally, pooling layers, fully connected layers, and Softmax are applied to complete the recognition PQDs. Simulation experiments demonstrate that the CaT model effectively recognizes PQDs with fewer parameters and floating point operations, achieving high accuracy and strong noise robustness. Its lightweight, end-to-end design also results in shorter inference times compared to other deep learning models. |
| format | Article |
| id | doaj-art-7280cedd18d44854aed3f31dc7f3f6c5 |
| institution | Kabale University |
| issn | 2096-3203 |
| language | zho |
| publishDate | 2025-01-01 |
| publisher | Editorial Department of Electric Power Engineering Technology |
| record_format | Article |
| series | 电力工程技术 |
| spelling | doaj-art-7280cedd18d44854aed3f31dc7f3f6c52025-02-08T08:40:18ZzhoEditorial Department of Electric Power Engineering Technology电力工程技术2096-32032025-01-01441697810.12158/j.2096-3203.2025.01.008240907889A lightweight power quality disturbance recognition model based on CNN and TransformerZHANG Bide0QIU Jie1LOU Guangxin2ZHOU Can3LUO Qingqing4LI Tianqian5School of Electrical Engineering and Electronic Information, Xihua University, Chengdu 610039, ChinaSchool of Electrical Engineering and Electronic Information, Xihua University, Chengdu 610039, ChinaChengdu Power Supply Company, State Grid Sichuan Electric Power Company, Chengdu 610000, ChinaSchool of Electrical Engineering and Electronic Information, Xihua University, Chengdu 610039, ChinaSchool of Electrical Engineering and Electronic Information, Xihua University, Chengdu 610039, ChinaSchool of Electrical Engineering and Electronic Information, Xihua University, Chengdu 610039, ChinaA lightweight power quality disturbances (PQDs) recognition model that integrates convolutional neural network (CNN) and Transformer (CaT) is proposed to address the high number of parameters and computational complexity in existing deep learning-based models. Depthwise separable convolutions are first employed to extract local features from the disturbance signals. An efficient softthreshold block is then introduced to reduce noise and redundant features without significantly increasing the model′s parameters or complexity. The Transformer model is used to capture global features of the disturbance signals. Finally, pooling layers, fully connected layers, and Softmax are applied to complete the recognition PQDs. Simulation experiments demonstrate that the CaT model effectively recognizes PQDs with fewer parameters and floating point operations, achieving high accuracy and strong noise robustness. Its lightweight, end-to-end design also results in shorter inference times compared to other deep learning models.https://www.epet-info.com/dlgcjsen/article/abstract/240907889power quality disturbances (pqds)lightweightnumber of parametersefficient soft threshold blockdepthwise separable convolutiontransformer model |
| spellingShingle | ZHANG Bide QIU Jie LOU Guangxin ZHOU Can LUO Qingqing LI Tianqian A lightweight power quality disturbance recognition model based on CNN and Transformer 电力工程技术 power quality disturbances (pqds) lightweight number of parameters efficient soft threshold block depthwise separable convolution transformer model |
| title | A lightweight power quality disturbance recognition model based on CNN and Transformer |
| title_full | A lightweight power quality disturbance recognition model based on CNN and Transformer |
| title_fullStr | A lightweight power quality disturbance recognition model based on CNN and Transformer |
| title_full_unstemmed | A lightweight power quality disturbance recognition model based on CNN and Transformer |
| title_short | A lightweight power quality disturbance recognition model based on CNN and Transformer |
| title_sort | lightweight power quality disturbance recognition model based on cnn and transformer |
| topic | power quality disturbances (pqds) lightweight number of parameters efficient soft threshold block depthwise separable convolution transformer model |
| url | https://www.epet-info.com/dlgcjsen/article/abstract/240907889 |
| work_keys_str_mv | AT zhangbide alightweightpowerqualitydisturbancerecognitionmodelbasedoncnnandtransformer AT qiujie alightweightpowerqualitydisturbancerecognitionmodelbasedoncnnandtransformer AT louguangxin alightweightpowerqualitydisturbancerecognitionmodelbasedoncnnandtransformer AT zhoucan alightweightpowerqualitydisturbancerecognitionmodelbasedoncnnandtransformer AT luoqingqing alightweightpowerqualitydisturbancerecognitionmodelbasedoncnnandtransformer AT litianqian alightweightpowerqualitydisturbancerecognitionmodelbasedoncnnandtransformer AT zhangbide lightweightpowerqualitydisturbancerecognitionmodelbasedoncnnandtransformer AT qiujie lightweightpowerqualitydisturbancerecognitionmodelbasedoncnnandtransformer AT louguangxin lightweightpowerqualitydisturbancerecognitionmodelbasedoncnnandtransformer AT zhoucan lightweightpowerqualitydisturbancerecognitionmodelbasedoncnnandtransformer AT luoqingqing lightweightpowerqualitydisturbancerecognitionmodelbasedoncnnandtransformer AT litianqian lightweightpowerqualitydisturbancerecognitionmodelbasedoncnnandtransformer |