基于多尺度特征融合的绝缘子缺陷检测

doi:10.19595/j.cnki.1000-6753.tces.212052

Abstract
Figure/Table
References
Related Citation (15)

Download: PDF (14110 KB) HTML (1 KB)
Export: BibTeX | EndNote (RIS)

Abstract Defective insulators in substations pose a major risk to the safe and stable operation of the power grid. To promote intelligent operation and maintenance of substations, efficient and accurate insulator defect detection algorithms are of great significance. Aiming at the problem that insulator defect regions are poor in pixel information, and distinct in shapes and sizes, a multi-scale defect detection network (MSD²Net) was proposed.
First, this paper analyzes the main challenge currently faced in insulator defect detection. Secondly, to accommodate insufficient pixel information of insulator defects, the model is improved based on SSD detector, replacing ResNet with the attentional feature extraction network. Thirdly, to detect targets at different scales, the feature fusion network is designed, and a deconvolution structure is used to enhance its automatic learning ability. In addition, MSD²Net uses Focal loss as the classification loss and Gaussian non-maximum suppression as the post-processing method, which further improves the detection performance.
For the model experiment, a defective insulator dataset in substation scenarios is produced by image processing methods. To enhance the diversity of the dataset, data augmentation operations are adopted such as color transformation, random crop, and random flip. Based on the dataset, the MSD²Net achieves a mean average precision (mAP) of 94.3%. Compared with the baseline network SSD and the classic single-stage network RetinaNet, MSD²Net improves the mAP value by 4.5% and 3.9%, respectively. In addition, when tested on the public Chinese power line insulator dataset (CPLID), the mAP of MSD²Net reaches 91.2%, higher than the SSD and VFNet models by 2.7% and 7.9%. The results show that the proposed model in this paper can effectively identify insulators and their defects in power inspection images.
The following conclusions can be drawn from the experimental analysis: ①The attention-based backbone network can reduce the loss of information and enhance the information interaction between feature map groups, thus extracting more critical information. ②The deconvolution fusion module realizes the fusion of deep and shallow features, thereby providing more complete feature information to the detection module. ③Focal Loss makes the network focus on positive samples and therefore alleviates the imbalance of positive and negative samples. At the same time, Gaussian non-maximum suppression mitigates the effects of the missed detection of overlapping targets.

Key words： Intelligent inspection tour insulator defect detection feature fusion

Received: 17 December 2021

PACS:

TM216

	Service

	E-mail this article
	Add to my bookshelf
	Add to citation manager
	E-mail Alert
	RSS
	Articles by authors
	Li Bin
	Qu Luyao
	Zhu Xinshan
	Guo Zhimin
	Tian Yangyang

Cite this article:

Li Bin,Qu Luyao,Zhu Xinshan等. Insulator Defect Detection Based on Multi-Scale Feature Fusion[J]. Transactions of China Electrotechnical Society, 2023, 38(1): 60-70.

URL:

https://dgjsxb.ces-transaction.com/EN/10.19595/j.cnki.1000-6753.tces.212052 OR https://dgjsxb.ces-transaction.com/EN/Y2023/V38/I1/60

[1] 蒲天骄, 乔骥, 韩笑, 等. 人工智能技术在电力设备运维检修中的研究及应用[J]. 高电压技术, 2020, 46(2): 369-383.
Pu Tianjiao, Qiao Ji, Han Xiao, et al.Research and application of artificial intelligence in operation and maintenance for power equipment[J]. High Voltage Engineering, 2020, 46(2): 369-383.
[2] 李奎, 高志成, 武一, 等. 基于统计回归和非线性Wiener过程的交流接触器剩余寿命预测[J]. 电工技术学报, 2019, 34(19): 4058-4070.
Li Kui, Gao Zhicheng, Wu Yi, et al.Remaining lifetime prediction of AC contactor based on statistical regression and nonlinear Wiener process[J]. Transactions of China Electrotechnical Society, 2019, 34(19): 4058-4070.
[3] 袁欢, 孙正可, 王露缙, 等. 基于姿态感知系统的隔离开关故障诊断[J]. 高电压技术, 2022, 48(1): 47-57.
Yuan Huan, Sun Zhengke, Wang Lujin, et al.Fault diagnosis of disconnector based on attitude sensing system[J]. High Voltage Engineering, 2022, 48(1): 47-57.
[4] Han S, Hao Ru, Lee J.Inspection of insulators on high-voltage power transmission lines[J]. IEEE Transactions on Power Delivery, 2009, 24(4): 2319-2327.
[5] 屠幼萍, 孙佑飞, 彭庆军, 等. 雾霾环境下自然积污绝缘子的污秽颗粒粒径分布特性[J]. 高电压技术, 2014, 40(11): 3318-3326.
Tu Youping, Sun Youfei, Peng Qingjun, et al.Particle size distribution characteristics of naturally polluted insulators under the fog-haze environment[J]. High Voltage Engineering, 2014, 40(11): 3318-3326.
[6] 吕玉坤, 赵伟萍, 庞广陆, 等. 典型伞型瓷及复合绝缘子积污特性模拟研究[J]. 电工技术学报, 2018, 33(1): 209-216.
Lü Yukun, Zhao Weiping, Pang Guanglu, et al.Simulation of contamination deposition on typical shed porcelain and composite insulators[J]. Transactions of China Electrotechnical Society, 2018, 33(1): 209-216.
[7] 周立辉, 张永生, 孙勇, 等. 智能变电站巡检机器人研制及应用[J]. 电力系统自动化, 2011, 35(19): 85-88, 96.
Zhou Lihui, Zhang Yongsheng, Sun Yong, et al.Development and application of equipment inspection robot for smart substations[J]. Automation of Electric Power Systems, 2011, 35(19): 85-88, 96.
[8] Zhao Zhenbing, Liu Ning, Wang Le.Localization of multiple insulators by orientation angle detection and binary shape prior knowledge[J]. IEEE Transactions on Dielectrics and Electrical Insulation, 2015, 22(6): 3421-3428.
[9] Lin J, Han J, Chen F, et al.Defects detection of glass insulator based on color image[J]. Power System Technology, 2011, 35(1): 127-133.
[10] Murthy V S, Tarakanath K, Mohanta D K, et al.Insulator condition analysis for overhead distribution lines using combined wavelet support vector machine (SVM)[J]. IEEE Transactions on Dielectrics and Electrical Insulation, 2010, 17(1): 89-99.
[11] 郑含博, 李金恒, 刘洋, 等. 基于改进YOLOv3的电力设备红外目标检测模型[J]. 电工技术学报, 2021, 36(7): 1389-1398.
Zheng Hanbo, Li Jinheng, Liu Yang, et al.Infrared object detection model for power equipment based on improved YOLOv3[J]. Transactions of China Electrotechnical Society, 2021, 36(7): 1389-1398.
[12] 赵振兵, 段记坤, 孔英会, 等. 基于门控图神经网络的栓母对知识图谱构建与应用[J]. 电网技术, 2021, 45(1): 98-106.
Zhao Zhenbing, Duan Jikun, Kong Yinghui, et al.Construction and application of bolt and nut pair knowledge graph based on GGNN[J]. Power System Technology, 2021, 45(1): 98-106.
[13] Tian Zhi, Shen Chunhua, Chen Hao, et al.FCOS: fully convolutional one-stage object detection[C]//2019 IEEE/CVF International Conference on Computer Vision (ICCV), Seoul, Korea (South), 2019: 9626-9635.
[14] Zhang Haoyang, Wang Ying, Dayoub F, et al.VarifocalNet: an IoU-aware dense object detector[C]//2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Nashville, TN, USA, 2021: 8510-8519.
[15] Girshick R, Donahue J, Darrell T, et al.Rich feature hierarchies for accurate object detection and semantic segmentation[C]//2014 IEEE Conference on Computer Vision and Pattern Recognition, Columbus, OH, USA, 2014: 580-587.
[16] Ren Shaoqing, He Kaiming, Girshick R, et al.Faster R-CNN: towards real-time object detection with region proposal networks[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017, 39(6): 1137-1149.
[17] 侯春萍, 章衡光, 张巍, 等. 输电线路绝缘子自爆缺陷识别方法[J]. 电力系统及其自动化学报, 2019, 31(6): 1-6.
Hou Chunping, Zhang Hengguang, Zhang Wei, et al.Recognition method for faults of insulators on transmission lines[J]. Proceedings of the CSU-EPSA, 2019, 31(6): 1-6.
[18] 赵振兵, 李延旭, 甄珍, 等. 结合KL散度和形状约束的Faster R-CNN典型金具检测方法[J]. 高电压技术, 2020, 46(9): 3018-3026.
Zhao Zhenbing, Li Yanxu, Zhen Zhen, et al.Typical fittings detection method with faster R-CNN combining KL divergence and shape constraints[J]. High Voltage Engineering, 2020, 46(9): 3018-3026.
[19] Redmon J, Divvala S, Girshick R, et al.You only look once: unified, real-time object detection[C]//2016 IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas, NV, USA. IEEE, : 779-788.
[20] Liu Wei, Anguelov D, Erhan D, et al.SSD: single shot multibox detector[C]//European Conference on Computer Vision, Amsterdam, the Netherlands, 2016: 21-37.
[21] Lin T Y, Goyal P, Girshick R, et al.Focal loss for dense object detection[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2020, 42(2): 318-327.
[22] 王卓, 王玉静, 王庆岩, 等. 基于协同深度学习的二阶段绝缘子故障检测方法[J]. 电工技术学报, 2021, 36(17): 3594-3604.
Wang Zhuo, Wang Yujing, Wang Qingyan, et al.Two stage insulator fault detection method based on collaborative deep learning[J]. Transactions of China Electrotechnical Society, 2021, 36(17): 3594-3604.
[23] Miao Xiren, Liu Xinyu, Chen Jing, et al.Insulator detection in aerial images for transmission line inspection using single shot multibox detector[J]. IEEE Access, 2019, 7: 9945-9956.
[24] 马鹏, 樊艳芳. 基于深度迁移学习的小样本智能变电站电力设备部件检测[J]. 电网技术, 2020, 44(3): 1148-1159.
Ma Peng, Fan Yanfang.Small sample smart substation power equipment component detection based on deep transfer learning[J]. Power System Technology, 2020, 44(3): 1148-1159.
[25] 张倩, 王建平, 李帷韬. 基于反馈机制的卷积神经网络绝缘子状态检测方法[J]. 电工技术学报, 2019, 34(16): 3311-3321.
Zhang Qian, Wang Jianping, Li Weitao.Insulator state detection of convolutional neural networks based on feedback mechanism[J]. Transactions of China Electrotechnical Society, 2019, 34(16): 3311-3321.
[26] 徐建军, 黄立达, 闫丽梅, 等. 基于层次多任务深度学习的绝缘子自爆缺陷检测[J]. 电工技术学报, 2021, 36(7): 1407-1415.
Xu Jianjun, Huang Lida, Yan Limei, et al.Insulator self-explosion defect detection based on hierarchical multi-task deep learning[J]. Transactions of China Electrotechnical Society, 2021, 36(7): 1407-1415.
[27] Zhang Dongkai, Gao Shibin, Yu Long, et al.DefGAN: defect detection GANs with latent space pitting for high-speed railway insulator[J]. IEEE Transactions on Instrumentation and Measurement, 2021, 70: 1-10.
[28] 王旭红, 李浩, 樊绍胜, 等. 基于改进SSD的电力设备红外图像异常自动检测方法[J]. 电工技术学报, 2020, 35(增刊1): 302-305, 306.
Wang Xuhong, Li Hao, Fan Shaosheng, et al.Infrared image anomaly automatic detection method for power equipment based on improved single shot multi box detection[J]. Transactions of China Electrotechnical Society, 2020, 35(S1): 302-305, 306.
[29] 左国玉, 马蕾, 徐长福, 等. 基于跨连接卷积神经网络的绝缘子检测方法[J]. 电力系统自动化, 2019, 43(4): 101-106.
Zuo Guoyu, Ma Lei, Xu Changfu, et al.Insulator detection method based on cross-connected convolutional neural network[J]. Automation of Electric Power Systems, 2019, 43(4): 101-106.
[30] Gao Zishu, Yang Guodong, Li En, et al.Novel feature fusion module-based detector for small insulator defect detection[J]. IEEE Sensors Journal, 2021, 21(15): 16807-16814.
[31] Jeong J, Park H, Kwak N. Enhancement of SSD by concatenating feature maps for object detection[J]. arXiv preprint arXiv:1705.09587, 2017.
[32] Li Buyu, Liu Yu, Wang Xiaogang.Gradient harmonized single-stage detector[J]. Proceedings of the AAAI Conference on Artificial Intelligence, 2019, 33: 8577-8584.
[33] Zhang H, Wu C, Zhang Z, et al.Resnest: split-attention networks[J]. arXiv preprint arXiv: 2004.08955, 2020.
[34] Lin T Y, Goyal P, Girshick R, et al.Focal loss for dense object detection[C]//2017 IEEE International Conference on Computer Vision, Venice, Italy, 2017 : 2999-3007.
[35] Zhu Xinshan, Li Shuoshi, Gan Yongdong, et al.Multi-stream fusion network with generalized smooth L₁ loss for single image dehazing[J]. IEEE Transactions on Image Processing, 2021, 30: 7620-7635.
[36] Tao Xian, Zhang Dapeng, Wang Zihao, et al.Detection of power line insulator defects using aerial images analyzed with convolutional neural networks[J]. IEEE Transactions on Systems, Man, and Cybernetics: Systems, 2020, 50(4): 1486-1498.
[37] Everingham M, Eslami S M A, Gool L, et al. The pascal visual object classes challenge: a retrospective[J]. International Journal of Computer Vision, 2015, 111(1): 98-136.