基于DBSCAN-FPN的输电线路螺栓缺销检测方法

doi:10.11930/j.issn.1004-9649.202005160

中国电力 ›› 2021, Vol. 54 ›› Issue (3): 45-54.DOI: 10.11930/j.issn.1004-9649.202005160

• 国家“十三五”智能电网重大专项专栏：（六）先进计算与人工智能技术专栏 • 上一篇下一篇

基于DBSCAN-FPN的输电线路螺栓缺销检测方法

赵振兵¹, 张帅¹, 蒋炜², 吴鹏^3,4

1. 华北电力大学电气与电子工程学院，河北保定 071003;
2. 国家电网有限公司，北京 100031;
3. 全球能源互联网研究院有限公司，北京 102209;
4. 电力系统人工智能（联研院）国家电网公司联合实验室，北京 102209

收稿日期:2020-05-21 修回日期:2020-10-23 出版日期:2021-03-05 发布日期:2021-03-17
作者简介:赵振兵(1979-)，男，博士，副教授，从事电力人工智能研究，E-mail：zhaozhenbing@ncepu.edu.cn;张帅（1994-），男，硕士研究生，从事深度学习、电力部件视觉检测等方面研究，E-mail：18331129289@163.com;蒋炜（1984-），男，博士，高级工程师，从事电力人工智能、区块链、北斗等能源互联网新技术应用研究，E-mail：wei-jiang@sgcc.com.cn;吴鹏(1982-)，男，硕士，工程师，从事机器学习、最优化方法、智能电网等方面研究，E-mail：wup@geiri.sgcc.com.cn
基金资助:
国家自然科学基金资助项目(基于深度视觉知识表达的输电线路螺栓表面状态检测方法研究，61871182)；北京市自然科学基金资助项目(面向海量螺栓表面缺陷检测的深度视觉感知和认知模型研究，4192055)；河北省自然科学基金资助项目(基于区域解析的输电线路螺栓微视觉缺陷检测模型研究，F2020502009)

Detection Method for Bolts with Mission Pins on Transmission Lines Based on DBSCAN-FPN

ZHAO Zhenbing¹, ZHANG Shuai¹, JIANG Wei², WU Peng^3,4

1. School of Electrical and Electronic Engineering, North China Electric Power University, Baoding 071003, China;
2. State Grid Corporation of China, Beijing 100031, China;
3. Global Energy Interconnection Research Institute Co., Ltd., Beijing 102209, China;
4. Artificial Intelligence on Electric Power System State Grid Corporation Joint Laboratory(GEIRI), Beijing 102209, China

Received:2020-05-21 Revised:2020-10-23 Online:2021-03-05 Published:2021-03-17
Supported by:
This work is supported by the National Natural Science Foundation of China (Research on Detection Method of Transmission Line Bolt Surface State Based on Deep Visual Knowledge Expression, No.61871182), Beijing Natural Science Foundation (Research on Deep Visual Perception and Cognitive Models for Mass Bolt Surface Defect Detection, No.4192055), Hebei Provincial Natural Science Foundation (Research on Micro-vision Defect Detection Model of Transmission Line Bolts Based on Regional Analysis, No.F2020502009)

摘要/Abstract

摘要： 螺栓作为输电线路上数量最大的紧固件，其缺陷检测是输电线路巡检工作中的一项重要内容。针对螺栓缺销为小目标，其定位困难、特征难提取的问题，提出一种基于DBSCAN算法与FPN模型相结合的螺栓缺销检测方法。首先，利用FPN模型定位螺栓缺销目标区域，同时基于DBSCAN聚类算法对具有相同形态结构的区域进行聚类；然后，改进FPN模型：基于螺栓先验知识，利用卷积网络实现自底向上的特征提取，采用双线性插值方法将特征的高层语义信息自顶向下地传递到各个层级，通过卷积滤波方法横向加强高层语义特征与高分辨率特征的融合信息，获得更优化的螺栓缺销特征表达；利用改进FPN模型实现螺栓缺销的初步检测；最后，采用DBSCAN聚类算法对初步检测结果进行误检甄别，实现了螺栓缺销的精确检测。实验结果表明，DBSCAN-FPN在自建数据集上的检测精度达到76.23%，检测效果优于FPN、R-FCN和Faster R-CNN。所提方法可以有效提高螺栓缺销检测精度，对输电线路运维有实际意义。

关键词: 螺栓, 缺销检测, DBSCAN算法, FPN, 先验知识

Abstract: Bolts are the mostly used fasteners on transmission lines, and their defect detection is an important content for transmission line inspection. As the bolt with missing pins are small targets, their positioning is difficult and their features are hard to extract. Aim at this problem, a detection method for bolts with missing pins is proposed based on the DBSCAN algorithm and FPN model. Firstly, the FPN model is used to locate the target area of the bolts with missing pins, and the areas with same morphological structure are clustered based on the DBSCAN clustering algorithm. Then, the FPN model is improved: based on the prior knowledge of bolts, the convolutional network is used to achieve bottom-up feature extraction, the bilinear interpolation method is used to transfer the high-level semantic information of the features to each level from top to bottom, the convolution filtering method is used to laterally strengthen the information fusion of high-level semantic features and high-resolution features, and a more optimized feature expression of bolts with missing pins is obtained. The improved FPN model is used to realize the preliminary detection of the bolts with missing pins. Finally, the DBSCAN clustering algorithm is adopted to screen the preliminary detection results for error detection, thereby achieving the accurate detection of the bolts with missing pins. Experimental results show that the detection accuracy of DBSCAN-FPN reaches up to 76.23% on the self-built data set, with the detection effect better than FPN, R-FCN and Faster R-CNN. The proposed method can effectively improve the detection accuracy of bolts with missing pins, which has practical significance for the operation and maintenance of transmission lines.

Key words: bolt, pin missing detection, DBSCAN algorithm, FPN, prior knowledge

赵振兵, 张帅, 蒋炜, 吴鹏. 基于DBSCAN-FPN的输电线路螺栓缺销检测方法[J]. 中国电力, 2021, 54(3): 45-54.

ZHAO Zhenbing, ZHANG Shuai, JIANG Wei, WU Peng. Detection Method for Bolts with Mission Pins on Transmission Lines Based on DBSCAN-FPN[J]. Electric Power, 2021, 54(3): 45-54.

导出引用管理器 EndNote|Ris|BibTeX

链接本文: https://www.electricpower.com.cn/CN/10.11930/j.issn.1004-9649.202005160

https://www.electricpower.com.cn/CN/Y2021/V54/I3/45

参考文献

[1] 刘云鹏, 裴少通, 武建华, 等. 基于深度学习的输变电设备异常发热点红外图片目标检测方法[J]. 南方电网技术, 2019, 13(2): 27-33
LIU Yunpeng, PEI Shaotong, WU Jianhua, et al. Deep learning based target detection method for abnormal hot spots infrared images of transmission and transformation equipment[J]. Southern Power System Technology, 2019, 13(2): 27-33
[2] NGUYEN V N, JENSSEN R, ROVERSO D. Automatic autonomous vision-based power line inspection: a review of current status and the potential role of deep learning[J]. International Journal of Electrical Power & Energy Systems, 2018, 99: 107-120.
[3] 赵振兵, 张薇, 翟永杰, 等. 电力视觉技术的概念、研究现状与展望[J]. 电力科学与工程, 2020, 36(1): 1-8
ZHAO Zhenbing, ZHANG Wei, ZHAI Yongjie, et al. Concept, research status and prospect of electric power vision technology[J]. Electric Power Science and Engineering, 2020, 36(1): 1-8
[4] 曾勇斌, 王星华, 彭显刚, 等. 输电线路缺陷风险建模及其预测方法研究[J]. 电力系统保护与控制, 2020, 48(10): 91-98
ZENG Yongbin, WANG Xinghua, PENG Xiangang, et al. Research on risk modeling and forecasting method of transmission line defects[J]. Power System Protection and Control, 2020, 48(10): 91-98
[5] DENG C, WANG S W, HUANG Z, et al. Unmanned aerial vehicles for power line inspection: a cooperative way in platforms and communications[J]. Journal of Communications, 2014, 9(9): 687-692.
[6] CHEN J W, LIU Z G, WANG H R, et al. Automatic defect detection of fasteners on the catenary support device using deep convolutional neural network[J]. IEEE Transactions on Instrumentation and Measurement, 2018, 67(2): 257-269.
[7] ZHONG J P, LIU Z G, HAN Z W, et al. A CNN-based defect inspection method for catenary split pins in high-speed railway[J]. IEEE Transactions on Instrumentation and Measurement, 2019, 68(8): 2849-2860.
[8] LIU Z G, ZHONG J P, LYU Y, et al. Location and fault detection of catenary support components based on deep learning[C]//2018 IEEE International Instrumentation and Measurement Technology Conference (I2MTC). Houston, TX, USA. IEEE, 2018: 1-6.
[9] ZHANG M, WU J L, LIN H F, et al. The application of one-class classifier based on CNN in image defect detection[J]. Procedia Computer Science, 2017, 114: 341-348.
[10] 乔丽, 赵尔敦, 刘俊杰, 等. 基于CNN的工件缺陷检测方法研究[J]. 计算机科学, 2017, 44(增刊2): 238-243
QIAO Li, ZHAO Erdun, LIU Junjie, et al. Research of workpiece defect detection method based on CNN[J]. Computer Science, 2017, 44(S2): 238-243
[11] WU X W, SAHOO D, HOI S C H. Recent advances in deep learning for object detection[J]. Neurocomputing, 2020, 396: 39-64.
[12] 冯敏, 罗旺, 余磊, 等. 适用于无人机巡检图像的输电线路螺栓检测方法[J]. 电力科学与技术学报, 2018, 33(4): 135-140
FENG Min, LUO Wang, YU Lei, et al. A bolt detection method for pictures captured from an unmanned aerial vehicle in power transmission line inspection[J]. Journal of Electric Power Science and Technology, 2018, 33(4): 135-140
[13] 王凯, 王健, 刘刚, 等. 基于辅助数据RetinaNet算法的销钉缺陷智能识别[J]. 广东电力, 2019, 32(9): 41-48
WANG Kai, WANG Jian, LIU Gang, et al. RetinaNet algorithm based on auxiliary data for intelligent identification on pin defects[J]. Guangdong Electric Power, 2019, 32(9): 41-48
[14] LIU W, ANGUELOV D, ERHAN D, et al. SSD: single shot multibox detector[M]//Computer Vision - ECCV 2016. Cham: Springer International Publishing, 2016: 21-37.
[15] PINHEIRO P O, LIN T Y, COLLOBERT R, et al. Learning to refine object segments[M]//Computer Vision - ECCV 2016. Cham: Springer International Publishing, 2016: 75-91.
[16] HONARI S, YOSINSKI J, VINCENT P, et al. Recombinator networks: learning coarse-to-fine feature aggregation[C]//2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Las Vegas, NV, USA. IEEE, 2016: 5743-5752.
[17] GHIASI G, FOWLKES C C. Laplacian pyramid reconstruction and refinement for semantic segmentation[M]//Computer Vision - ECCV 2016. Cham: Springer International Publishing, 2016: 519-534.
[18] NEWELL A, YANG K Y, DENG J. Stacked hourglass networks for human pose estimation[M]//Computer Vision - ECCV 2016. Cham: Springer International Publishing, 2016: 483-499.
[19] LIN T Y, DOLLÁR P, GIRSHICK R, et al. Feature pyramid networks for object detection[C]//2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Honolulu, HI, USA. IEEE, 2017: 936-944.
[20] KHAN K, REHMAN S U, AZIZ K, et al. DBSCAN: Past, present and future[C]//The Fifth International Conference on the Applications of Digital Information and Web Technologies (ICADIWT 2014). Bangalore, India. IEEE, 2014: 232-238.
[21] JAIN A K, MURTY M N, FLYNN P J. Data clustering[J]. ACM Computing Surveys, 1999, 31(3): 264-323.
[22] HE K M, ZHANG X Y, REN S Q, et al. Deep residual learning for image recognition[C]//2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Las Vegas, NV, USA. IEEE, 2016: 770-778.
[23] GIRSHICK R. Fast R-CNN[C]//2015 IEEE International Conference on Computer Vision (ICCV). Santiago, Chile. IEEE, 2015: 1440-1448.
[24] HE K M, ZHANG X Y, REN S Q, et al. Spatial pyramid pooling in deep convolutional networks for visual recognition[M]//Computer Vision - ECCV 2014. Cham: Springer International Publishing, 2014: 346-361.
[25] REN S Q, HE K M, 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.
[26] DAI Jifeng, LI Yi, HE Kaiming, et al. R-FCN: Object detection via region-based fully convolution networks[C]//Advances in Neural Information Processing Systems, 2016: 379-387.

基于DBSCAN-FPN的输电线路螺栓缺销检测方法

Detection Method for Bolts with Mission Pins on Transmission Lines Based on DBSCAN-FPN

RichHTML

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 6

编辑推荐

Metrics

[1]	张武能, 汪毅, 张留斌, 吴克华, 王晓晨. 输电铁塔螺栓连接结构健康监测技术进展与展望[J]. 中国电力, 2021, 54(2): 18-26.
[2]	张武能, 兰光宇, 汪毅, 张留斌, 吴克华, 王晓晨. 基于非线性声弹性效应的输电铁塔螺栓预紧力预测数值分析[J]. 中国电力, 2021, 54(10): 152-160.
[3]	高元海，王淳. 基于八种智能算法的配电网络重构计算平台及其性能[J]. 中国电力, 2015, 48(8): 53-60.
[4]	何长华，邢海军，李清华，吴静. 强度级差带颈锻造法兰试验研究[J]. 中国电力, 2015, 48(4): 107-112.
[5]	邢海军，岳平，王灿灿，姜文东，王佳佳，张英杰. D型复合材料管连接性能研究[J]. 中国电力, 2015, 48(3): 94-98.
[6]	邢海军，岳平，王灿灿，姜文东，王佳佳，张英杰. D型复合材料管连接性能研究[J]. 中国电力, 2015, 48(2): 70-75.

模态框（Modal）标题

基于DBSCAN-FPN的输电线路螺栓缺销检测方法

Detection Method for Bolts with Mission Pins on Transmission Lines Based on DBSCAN-FPN

RichHTML

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 6

编辑推荐

Metrics