2022
DOI: 10.1002/tee.23683
|View full text |Cite
|
Sign up to set email alerts
|

Hydrophobicity Classification of Composite Insulators Based on Light‐Weight Convolutional Neural Networks

Abstract: To achieve accurate and rapid measurement of the hydrophobicity class (HC) of composite insulators, an intelligent spray image recognition technique based on light‐weight convolutional neural networks (CNN) is proposed in this paper. A spray image data set contains clean, contaminated and aged insulators with various illuminations, shooting angles and distances, about 10 400 images of shed surface were collected by spray tests and data augmentation. Five classification models were established by different CNNs… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1

Citation Types

0
3
0

Year Published

2022
2022
2024
2024

Publication Types

Select...
4
1
1

Relationship

0
6

Authors

Journals

citations
Cited by 6 publications
(3 citation statements)
references
References 20 publications
0
3
0
Order By: Relevance
“…Based on the above experimental results, in order to further verify the performance of the discrimination method in this paper, the method of literature [18] and the method of literature [19] are used as the comparison methods of this paper's method to discriminate the HC grade of high-voltage composite insulators, respectively. The F1 Score results of different methods are shown in figure 4.…”
Section: Comparison and Analysis Of Experimental Resultsmentioning
confidence: 99%
See 1 more Smart Citation
“…Based on the above experimental results, in order to further verify the performance of the discrimination method in this paper, the method of literature [18] and the method of literature [19] are used as the comparison methods of this paper's method to discriminate the HC grade of high-voltage composite insulators, respectively. The F1 Score results of different methods are shown in figure 4.…”
Section: Comparison and Analysis Of Experimental Resultsmentioning
confidence: 99%
“…Xin et al constructed a migration learning and feature fusion based discriminative model for HC grade of composite insulators on the basis of VGG-19 network by fusing deep features and local features [18]. Qiu et al proposed an intelligent identification method of HC of composite insulators based on convolutional neural network [19,20]. The processed image was inputted into the designed convolutional neural network model for classification, so as to realize the intelligent recognition of HC of composite insulators.…”
Section: Introductionmentioning
confidence: 99%
“…Traditional methods of insulator defect detection focus on color, texture, edge, and other features [1][2][3][4]. This kind of method relies on high-quality images and appropriate shooting angles.…”
Section: Introductionmentioning
confidence: 99%