Full Text:   <321>

Summary:  <69>

CLC number: 

On-line Access: 2022-06-22

Received: 2022-01-09

Revision Accepted: 2022-05-23

Crosschecked: 2022-09-22

Cited: 0

Clicked: 237

Citations:  Bibtex RefMan EndNote GB/T7714

 ORCID:

Ping Tan

https://orcid.org/0000-0001-8656-3514

-   Go to

Article info.
Open peer comments

Journal of Zhejiang University SCIENCE A 2022 Vol.23 No.9 P.745-756

http://doi.org/10.1631/jzus.A2100494


Mask R-CNN and multifeature clustering model for catenary insulator recognition and defect detection


Author(s):  Ping TAN, Xu-feng LI, Jin DING, Zhi-sheng CUI, Ji-en MA, Yue-lan SUN, Bing-qiang HUANG, You-tong FANG

Affiliation(s):  School of Automation and Electrical Engineering, Zhejiang University of Science and Technology, Hangzhou 310023, China; more

Corresponding email(s):   jding@zust.edu.cn, majien@zju.edu.cn

Key Words:  High speed railway (HSR) catenary insulator, Mask region-convolutional neural network (R-CNN), Multifeature fusion, K-means clustering analysis model (KCAM), Defect detection


Share this article to: More <<< Previous Article|

Ping TAN, Xu-feng LI, Jin DING, Zhi-sheng CUI, Ji-en MA, Yue-lan SUN, Bing-qiang HUANG, You-tong FANG. Mask R-CNN and multifeature clustering model for catenary insulator recognition and defect detection[J]. Journal of Zhejiang University Science A, 2022, 23(9): 745-756.

@article{title="Mask R-CNN and multifeature clustering model for catenary insulator recognition and defect detection",
author="Ping TAN, Xu-feng LI, Jin DING, Zhi-sheng CUI, Ji-en MA, Yue-lan SUN, Bing-qiang HUANG, You-tong FANG",
journal="Journal of Zhejiang University Science A",
volume="23",
number="9",
pages="745-756",
year="2022",
publisher="Zhejiang University Press & Springer",
doi="10.1631/jzus.A2100494"
}

%0 Journal Article
%T Mask R-CNN and multifeature clustering model for catenary insulator recognition and defect detection
%A Ping TAN
%A Xu-feng LI
%A Jin DING
%A Zhi-sheng CUI
%A Ji-en MA
%A Yue-lan SUN
%A Bing-qiang HUANG
%A You-tong FANG
%J Journal of Zhejiang University SCIENCE A
%V 23
%N 9
%P 745-756
%@ 1673-565X
%D 2022
%I Zhejiang University Press & Springer
%DOI 10.1631/jzus.A2100494

TY - JOUR
T1 - Mask R-CNN and multifeature clustering model for catenary insulator recognition and defect detection
A1 - Ping TAN
A1 - Xu-feng LI
A1 - Jin DING
A1 - Zhi-sheng CUI
A1 - Ji-en MA
A1 - Yue-lan SUN
A1 - Bing-qiang HUANG
A1 - You-tong FANG
J0 - Journal of Zhejiang University Science A
VL - 23
IS - 9
SP - 745
EP - 756
%@ 1673-565X
Y1 - 2022
PB - Zhejiang University Press & Springer
ER -
DOI - 10.1631/jzus.A2100494


Abstract: 
Rod insulators are vital parts of the catenary of high speed railways (HSRs). There are many different catenary insulators, and the background of the insulator image is complicated. It is difficult to recognise insulators and detect defects automatically. In this paper, we propose a catenary intelligent defect detection algorithm based on mask region-convolutional neural network (R-CNN) and an image processing model. Vertical projection technology is used to achieve single shed positioning and precise cutting of the insulator. Gradient, texture, and gray feature fusion (GTGFF) and a k-means clustering analysis model (KCAM) are proposed to detect broken insulators, dirt, foreign bodies, and flashover. Using this model, insulator recognition and defect detection can achieve a high recall rate and accuracy, and generalized defect detection. The algorithm is tested and verified on a dataset of realistic insulator images, and the accuracy and reliability of the algorithm satisfy current requirements for HSR catenary automatic inspection and intelligent maintenance.

基于Mask R-CNN和多特征聚类模型的接触网绝缘子识别和缺陷检测

作者:谭平1,李旭峰2,丁进1,崔志晟1,马吉恩2,孙月兰1,黄炳强1,方攸同2
机构:1浙江科技学院,自动化与电气工程学院,中国杭州,310023;2浙江大学,电气工程学院,中国杭州,310027
目的:绝缘子是高速铁路接触网的重要组成部分。绝缘子的故障会导致绝缘劣化,甚至会导致接触网断电,所以绝缘子缺陷检测对高速列车运行具有重要意义。本文旨在分析巡检车拍摄的接触网绝缘子的图像特点,结合绝缘子破损、污垢、异物和闪络四类主要缺陷,研究一种智能图像处理方法,以期有效识别绝缘子及其缺陷。
创新点:1.通过MaskR-CNN模型,实现绝缘子区域像素级切割及旋正;2.提出垂直投影技术,实现绝缘子单片区域快速准确定位;3.通过多特征融合和聚类分析模型,检测绝缘子破损、污垢、异物和闪络。
方法:1.通过分析接触网图像的特点,采用Mask R-CNN方法实现绝缘子区域定位、前后景像素分割以及倾斜修正(图5);2.通过垂直投影方法,得到绝缘子各片空间坐标信息(图6);3.通过提取图像梯度、纹理和灰度特征(公式(2)~(4)),运用特征融合聚类方法(公式(5)~(7)),计算其相邻片之间的特征分布差异(公式(8));4.基于实际拍摄图片构建实验测试样本,并分析实验过程及结果,验证所提方法的可行性和有效性。
结论:1.Mask R-CNN是一种高效的目标识别和实例分割深度学习模型;它在绝缘子识别方面展现了鲁棒性和高精度。2.实验表明,本文提出的绝缘子像素区域切割和倾斜校正具有较高精度。3.对于绝缘子缺陷检测,本文提出的多特征融合聚类分析模型测试结果显示其具有较高的缺陷识别精确度。

关键词:高铁接触网绝缘子;MaskR-CNN;多特征融合;K均值聚类分析模型;缺陷检测

Darkslateblue:Affiliate; Royal Blue:Author; Turquoise:Article

Reference

[1]AdouMW, XuHR, ChenGH, 2019. Insulator faults detection based on deep learning. Proceedings of the IEEE 13th International Conference on Anti-counterfeiting, Security, and Identification, p.173-177.

[2]DaiJF, HeKM, SunJ, 2016. Instance-aware semantic segmentation via multi-task network cascades. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, p.3150-3158.

[3]DalalN, TriggsB, 2005. Histograms of oriented gradients for human detection. Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, p.886-893.

[4]HanY, LiuZG, LeeDJ, et al., 2016. High-speed railway rod-insulator detection using segment clustering and deformable part models. Proceedings of the IEEE International Conference on Image Processing, p.3852-3856.

[5]HartiganJA, WongMA, 1979. Algorithm as 136: a K-means clustering algorithm. Journal of the Royal Statistical Society. Series C (Applied Statistics), 28(1):100-108.

[6]HeKM, GkioxariG, DollárP, et al., 2017. Mask R-CNN. Proceedings of the IEEE International Conference on Computer Vision, p.2980-2988.

[7]JiangH, QiuXJ, ChenJ, et al., 2019. Insulator fault detection in aerial images based on ensemble learning with multi-level perception. IEEE Access, 7:61797-61810.

[8]KangGQ, GaoSB, YuL, et al., 2019. Deep architecture for high-speed railway insulator surface defect detection: denoising autoencoder with multitask learning. IEEE Transactions on Instrumentation and Measurement, 68(8):2679-2690.

[9]KienDN, ZhuangXY, 2021. A deep neural network-based algorithm for solving structural optimization. Journal of Zhejiang University-SCIENCE A (Applied Physics & Engineering), 22(8):609-620.

[10]LeCunY, BengioY, HintonG, 2015. Deep learning. Nature, 521(7553):436-444.

[11]LiY, QiHZ, DaiJF, et al., 2017. Fully convolutional instance-aware semantic segmentation. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, p.4438-4446.

[12]LiuT, ZhaoY, WeiYC, et al., 2019. Concealed object detection for activate millimeter wave image. IEEE Transactions on Industrial Electronics, 66(12):9909-9917.

[13]LyuY, HanZW, ZhongJP, et al., 2020. A generic anomaly detection of catenary support components based on generative adversarial networks. IEEE Transactions on Instrumentation and Measurement, 69(5):2439-2448.

[14]NikbakhtS, AnitescuC, RabczukT, 2021. Optimizing the neural network hyperparameters utilizing genetic algorithm. Journal of Zhejiang University-SCIENCE A (Applied Physics & Engineering), 22(6):407-426.

[15]OjalaT, PietikäinenM, HarwoodD, 1996. A comparative study of texture measures with classification based on featured distributions. Pattern Recognition, 29(1):‍51-59.

[16]RenSQ, HeKM, GirshickR, et al., 2017. Faster R-CNN: towards real-time object detection with region proposal networks. IEEE Transactions on Pattern Analysis and Machine Intelligence, 39(6):1137-1149.

[17]SuM, PengH, LiSF, 2021. Application of an interpretable artificial neural network to predict the interface strength of a near-surface mounted fiber-reinforced polymer to concrete joint. Journal of Zhejiang University-SCIENCE A (Applied Physics & Engineering), 22(6):427-440.

[18]TanP, MaJE, ZhouJ, et al., 2016. Sustainability development strategy of China's high speed rail. Journal of Zhejiang University-SCIENCE A (Applied Physics & Engineering), 17(12):923-932.

[19]TanP, LiXF, XuJM, et al., 2020. Catenary insulator defect detection based on contour features and gray similarity matching. Journal of Zhejiang University-SCIENCE A (Applied Physics & Engineering), 21(1):64-73.

[20]TanP, LiXF, WuZG, et al., 2021. Multialgorithm fusion image processing for high speed railway dropper failure-defect detection. IEEE Transactions on Systems, Man, and Cybernetics: Systems, 51(7):4466-4478.

[21]WangJ, WangTT, LuoQZ, 2019. A practical structural health monitoring system for high-speed train car-body. IEEE Access, 7:168316-168326.

[22]WangL, ZhangZJ, 2017. Automatic detection of wind turbine blade surface cracks based on UAV-taken images. IEEE Transactions on Industrial Electronics, 64(9):7293-7303.

[23]YaoXT, ZhangYP, GaoY, et al., 2017. Research on technology of contact insulator pollution classification and pollution level division based on machine vision. Proceedings of the IEEE 3rd Information Technology and Mechatronics Engineering Conference, p.1264-1268.

[24]YaoXT, ZhangYP, GaoY, et al., 2018. Research on vision-based technology of contamination detection in overhead line insulators. Journal of Lanzhou Jiaotong University, 37(1):65-72 (in Chinese).

[25]YueGH, HouCP, GuK, et al., 2018. Biologically inspired blind quality assessment of tone-mapped images. IEEE Transactions on Industrial Electronics, 65(3):2525-2536.

[26]ZengX, LiZH, GaoW, et al., 2018. A novel virtual sensing with artificial neural network and K-means clustering for IGBT current measuring. IEEE Transactions on Industrial Electronics, 65(9):7343-7352.

[27]ZhaoZB, ZhenZ, ZhangL, et al., 2019. Insulator detection method in inspection image based on improved faster R-CNN. Energies, 12(7):1204.

[28]ZhuQ, LiL, ChenCJ, et al., 2018. A low-cost lateral active suspension system of the high-speed train for ride quality based on the resonant control method. IEEE Transactions on Industrial Electronics, 65(5):4187-4196.

Open peer comments: Debate/Discuss/Question/Opinion

<1>

Please provide your name, email address and a comment





Journal of Zhejiang University-SCIENCE, 38 Zheda Road, Hangzhou 310027, China
Tel: +86-571-87952783; E-mail: cjzhang@zju.edu.cn
Copyright © 2000 - 2023 Journal of Zhejiang University-SCIENCE