An Edge Recognition Method for Insulator State Based on Multi-dimension Feature Fusion
Traditional insulator state recognition methods have such problems as poor real-time performance and insufficient feature extraction ability. Based on the idea of edge computing, this paper proposes a method for recognizing the insulator state based on multi-dimension feature fusion. An edge recogni...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | zho |
| Published: |
State Grid Energy Research Institute
2022-01-01
|
| Series: | Zhongguo dianli |
| Subjects: | |
| Online Access: | https://www.electricpower.com.cn/CN/10.11930/j.issn.1004-9649.202011120 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850037326611218432 |
|---|---|
| author | Dongmei HUANG Yueqi WANG Anduo HU Jinzhong SUN Shuai SHI Yuan SUN Lingfeng FANG |
| author_facet | Dongmei HUANG Yueqi WANG Anduo HU Jinzhong SUN Shuai SHI Yuan SUN Lingfeng FANG |
| author_sort | Dongmei HUANG |
| collection | DOAJ |
| description | Traditional insulator state recognition methods have such problems as poor real-time performance and insufficient feature extraction ability. Based on the idea of edge computing, this paper proposes a method for recognizing the insulator state based on multi-dimension feature fusion. An edge recognition framework for insulator state is constructed using cloud edge collaboration and edge federation collaboration. And a deep learning network integrating multi-dimension feature extraction is designed, which, by using the ResNet101 as the main feature extraction network, uses the Inception module to build the data pooling layer, and embeds the compression incentive module and convolution attention module to extract features from different dimensions. An insulator state recognition experiment is conducted using the data set of normal and defect states, and the average recognition accuracy reaches 99%. The experimental results have proved the validity of the proposed method. |
| format | Article |
| id | doaj-art-6e8cfd2cf28f4160b9a02b7d3f0c60b9 |
| institution | DOAJ |
| issn | 1004-9649 |
| language | zho |
| publishDate | 2022-01-01 |
| publisher | State Grid Energy Research Institute |
| record_format | Article |
| series | Zhongguo dianli |
| spelling | doaj-art-6e8cfd2cf28f4160b9a02b7d3f0c60b92025-08-20T02:56:52ZzhoState Grid Energy Research InstituteZhongguo dianli1004-96492022-01-0155113314110.11930/j.issn.1004-9649.202011120zgdl-54-08-huangdongmeiAn Edge Recognition Method for Insulator State Based on Multi-dimension Feature FusionDongmei HUANG0Yueqi WANG1Anduo HU2Jinzhong SUN3Shuai SHI4Yuan SUN5Lingfeng FANG6College of Electronic and Information Engineering, Shanghai University of Electric Power, Shanghai 201306, ChinaCollege of Electrical Engineering, Shanghai University of Electric Power, Shanghai 200090, ChinaCollege of Electronic and Information Engineering, Shanghai University of Electric Power, Shanghai 201306, ChinaCollege of Electronic and Information Engineering, Shanghai University of Electric Power, Shanghai 201306, ChinaCollege of Electrical Engineering, Shanghai University of Electric Power, Shanghai 200090, ChinaCollege of Mathematics and Physics, Shanghai University of Electric Power, Shanghai 201306, ChinaState Grid Corporation of China, Beijing 100031, ChinaTraditional insulator state recognition methods have such problems as poor real-time performance and insufficient feature extraction ability. Based on the idea of edge computing, this paper proposes a method for recognizing the insulator state based on multi-dimension feature fusion. An edge recognition framework for insulator state is constructed using cloud edge collaboration and edge federation collaboration. And a deep learning network integrating multi-dimension feature extraction is designed, which, by using the ResNet101 as the main feature extraction network, uses the Inception module to build the data pooling layer, and embeds the compression incentive module and convolution attention module to extract features from different dimensions. An insulator state recognition experiment is conducted using the data set of normal and defect states, and the average recognition accuracy reaches 99%. The experimental results have proved the validity of the proposed method.https://www.electricpower.com.cn/CN/10.11930/j.issn.1004-9649.202011120insulator imagefeature extractionresidual neural networkedge computingstate recognition |
| spellingShingle | Dongmei HUANG Yueqi WANG Anduo HU Jinzhong SUN Shuai SHI Yuan SUN Lingfeng FANG An Edge Recognition Method for Insulator State Based on Multi-dimension Feature Fusion Zhongguo dianli insulator image feature extraction residual neural network edge computing state recognition |
| title | An Edge Recognition Method for Insulator State Based on Multi-dimension Feature Fusion |
| title_full | An Edge Recognition Method for Insulator State Based on Multi-dimension Feature Fusion |
| title_fullStr | An Edge Recognition Method for Insulator State Based on Multi-dimension Feature Fusion |
| title_full_unstemmed | An Edge Recognition Method for Insulator State Based on Multi-dimension Feature Fusion |
| title_short | An Edge Recognition Method for Insulator State Based on Multi-dimension Feature Fusion |
| title_sort | edge recognition method for insulator state based on multi dimension feature fusion |
| topic | insulator image feature extraction residual neural network edge computing state recognition |
| url | https://www.electricpower.com.cn/CN/10.11930/j.issn.1004-9649.202011120 |
| work_keys_str_mv | AT dongmeihuang anedgerecognitionmethodforinsulatorstatebasedonmultidimensionfeaturefusion AT yueqiwang anedgerecognitionmethodforinsulatorstatebasedonmultidimensionfeaturefusion AT anduohu anedgerecognitionmethodforinsulatorstatebasedonmultidimensionfeaturefusion AT jinzhongsun anedgerecognitionmethodforinsulatorstatebasedonmultidimensionfeaturefusion AT shuaishi anedgerecognitionmethodforinsulatorstatebasedonmultidimensionfeaturefusion AT yuansun anedgerecognitionmethodforinsulatorstatebasedonmultidimensionfeaturefusion AT lingfengfang anedgerecognitionmethodforinsulatorstatebasedonmultidimensionfeaturefusion AT dongmeihuang edgerecognitionmethodforinsulatorstatebasedonmultidimensionfeaturefusion AT yueqiwang edgerecognitionmethodforinsulatorstatebasedonmultidimensionfeaturefusion AT anduohu edgerecognitionmethodforinsulatorstatebasedonmultidimensionfeaturefusion AT jinzhongsun edgerecognitionmethodforinsulatorstatebasedonmultidimensionfeaturefusion AT shuaishi edgerecognitionmethodforinsulatorstatebasedonmultidimensionfeaturefusion AT yuansun edgerecognitionmethodforinsulatorstatebasedonmultidimensionfeaturefusion AT lingfengfang edgerecognitionmethodforinsulatorstatebasedonmultidimensionfeaturefusion |