Evaluation method of hydrophobicity of composite insulators based on improved Mask R-CNN

To ensure the safe operation of power system, it is necessary to discriminate the hydrophobicity level online of composite insulators in time. In order to improve the generalization ability of composite insulator hydrophobicity state evaluation model, and solve the problem that the existing classifi...

Full description

Saved in:
Bibliographic Details
Main Authors: SHENG Fei, CAO Liu, LIU Yulong, HUANG Jie, HUANG Yaqian, ZHU Yanqing
Format: Article
Language:zho
Published: Harbin Jinhe Electrical Measurement & Instrumentation Magazine Publishing Co., Ltd. 2025-04-01
Series:Diance yu yibiao
Subjects:
Online Access:http://www.emijournal.net/dcyyben/ch/reader/create_pdf.aspx?file_no=20220525002&flag=1&journal_id=dcyyben&year_id=2025
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849312613941379072
author SHENG Fei
CAO Liu
LIU Yulong
HUANG Jie
HUANG Yaqian
ZHU Yanqing
author_facet SHENG Fei
CAO Liu
LIU Yulong
HUANG Jie
HUANG Yaqian
ZHU Yanqing
author_sort SHENG Fei
collection DOAJ
description To ensure the safe operation of power system, it is necessary to discriminate the hydrophobicity level online of composite insulators in time. In order to improve the generalization ability of composite insulator hydrophobicity state evaluation model, and solve the problem that the existing classification models only focus on the parts with good hydrophobicity when evaluating the composite insulators with uneven hydrophobicity degree. In this paper, the classification problem is transformed into the target detection problem, and the improved mask region-based convolutional neural network (Mask R-CNN) algorithm is used to evaluate the hydrophobicity level of composite insulators. Firstly, the location and size of all water droplets in the image are determined by feature pyramid network (FPN) and the mask branch of Mask R-CNN is used to predict the hydrophobicity level of all water droplets. Then, the area of the corresponding hydrophobicity level is calculated. Finally, the hydrophobicity level with the largest area is selected as the classification results of the image. Especially, combined with the characteristics of each level of hydrophobicity image, we introduce the soft non-maximum suppression (Soft-NMS) structure to reduced the missed target detection because of the scale problem of water droplets and the irregular distribution in high level hydrophobicity images, and introduce generalized intersection over union loss (GIOU) to accelerate the convergence rate of the model with small and multi-temporal objects in low level images. Final validation through comparative experiments demonstrated the effectiveness and superiority of the enhanced Mask R-CNN-based hydrophobicity image recognition algorithm across three critical metrics: mean average precision (MAP), frames per second (FPS), and classification accuracy.
format Article
id doaj-art-dfc2996fb4cf4928842de0c76fbd90f7
institution Kabale University
issn 1001-1390
language zho
publishDate 2025-04-01
publisher Harbin Jinhe Electrical Measurement & Instrumentation Magazine Publishing Co., Ltd.
record_format Article
series Diance yu yibiao
spelling doaj-art-dfc2996fb4cf4928842de0c76fbd90f72025-08-20T03:53:02ZzhoHarbin Jinhe Electrical Measurement & Instrumentation Magazine Publishing Co., Ltd.Diance yu yibiao1001-13902025-04-01624738010.19753/j.issn1001-1390.2025.04.0091001-1390(2025)04-0073-08Evaluation method of hydrophobicity of composite insulators based on improved Mask R-CNNSHENG Fei0CAO Liu1LIU Yulong2HUANG Jie3HUANG Yaqian4ZHU Yanqing5Urumqi Power Supply Company, State Grid Xinjiang Electric Power Co., Ltd., Urumqi 830000, ChinaUrumqi Power Supply Company, State Grid Xinjiang Electric Power Co., Ltd., Urumqi 830000, ChinaUrumqi Power Supply Company, State Grid Xinjiang Electric Power Co., Ltd., Urumqi 830000, ChinaSchool of Electrical and Information Engineering, Hunan University, Changsha 410012, ChinaSchool of Electrical and Information Engineering, Hunan University, Changsha 410012, ChinaSchool of Electrical and Information Engineering, Hunan University, Changsha 410012, ChinaTo ensure the safe operation of power system, it is necessary to discriminate the hydrophobicity level online of composite insulators in time. In order to improve the generalization ability of composite insulator hydrophobicity state evaluation model, and solve the problem that the existing classification models only focus on the parts with good hydrophobicity when evaluating the composite insulators with uneven hydrophobicity degree. In this paper, the classification problem is transformed into the target detection problem, and the improved mask region-based convolutional neural network (Mask R-CNN) algorithm is used to evaluate the hydrophobicity level of composite insulators. Firstly, the location and size of all water droplets in the image are determined by feature pyramid network (FPN) and the mask branch of Mask R-CNN is used to predict the hydrophobicity level of all water droplets. Then, the area of the corresponding hydrophobicity level is calculated. Finally, the hydrophobicity level with the largest area is selected as the classification results of the image. Especially, combined with the characteristics of each level of hydrophobicity image, we introduce the soft non-maximum suppression (Soft-NMS) structure to reduced the missed target detection because of the scale problem of water droplets and the irregular distribution in high level hydrophobicity images, and introduce generalized intersection over union loss (GIOU) to accelerate the convergence rate of the model with small and multi-temporal objects in low level images. Final validation through comparative experiments demonstrated the effectiveness and superiority of the enhanced Mask R-CNN-based hydrophobicity image recognition algorithm across three critical metrics: mean average precision (MAP), frames per second (FPS), and classification accuracy.http://www.emijournal.net/dcyyben/ch/reader/create_pdf.aspx?file_no=20220525002&flag=1&journal_id=dcyyben&year_id=2025hydrophobicitytarget detectionmask r-cnndeep learningcomposite insulator
spellingShingle SHENG Fei
CAO Liu
LIU Yulong
HUANG Jie
HUANG Yaqian
ZHU Yanqing
Evaluation method of hydrophobicity of composite insulators based on improved Mask R-CNN
Diance yu yibiao
hydrophobicity
target detection
mask r-cnn
deep learning
composite insulator
title Evaluation method of hydrophobicity of composite insulators based on improved Mask R-CNN
title_full Evaluation method of hydrophobicity of composite insulators based on improved Mask R-CNN
title_fullStr Evaluation method of hydrophobicity of composite insulators based on improved Mask R-CNN
title_full_unstemmed Evaluation method of hydrophobicity of composite insulators based on improved Mask R-CNN
title_short Evaluation method of hydrophobicity of composite insulators based on improved Mask R-CNN
title_sort evaluation method of hydrophobicity of composite insulators based on improved mask r cnn
topic hydrophobicity
target detection
mask r-cnn
deep learning
composite insulator
url http://www.emijournal.net/dcyyben/ch/reader/create_pdf.aspx?file_no=20220525002&flag=1&journal_id=dcyyben&year_id=2025
work_keys_str_mv AT shengfei evaluationmethodofhydrophobicityofcompositeinsulatorsbasedonimprovedmaskrcnn
AT caoliu evaluationmethodofhydrophobicityofcompositeinsulatorsbasedonimprovedmaskrcnn
AT liuyulong evaluationmethodofhydrophobicityofcompositeinsulatorsbasedonimprovedmaskrcnn
AT huangjie evaluationmethodofhydrophobicityofcompositeinsulatorsbasedonimprovedmaskrcnn
AT huangyaqian evaluationmethodofhydrophobicityofcompositeinsulatorsbasedonimprovedmaskrcnn
AT zhuyanqing evaluationmethodofhydrophobicityofcompositeinsulatorsbasedonimprovedmaskrcnn