浏览全部资源
扫码关注微信
Received：16 July 2021，
Revised：2021-9-10，
Accepted：17 September 2021，
Published：16 November 2022
移动端阅览
目的
2
螺栓销钉是输电线路中至关重要的连接部件，螺栓的销钉缺失会导致输电线路中关键部件解体，甚至造成大规模停电事故。螺栓缺销检测属于小目标检测问题，由于其尺寸较小且背景复杂，现有的目标检测算法针对螺栓缺销的检测效果较差。为了提升输电线路中螺栓缺销的检测效果，本文以SSD（single shot multibox detector）算法为基础，提出了基于隔级交叉自适应特征融合的输电线路螺栓缺销检测方法。
方法
2
在建立了螺栓缺销故障检测数据集后，首先在SSD网络中加入隔级交叉特征金字塔结构，增强特征图的视觉信息和语义信息；其次，引入自适应特征融合机制进行特征图二次融合，不同尺度的特征图以自适应学习到的权重进行加权特征融合，有效提升螺栓缺销的检测效果；最后，对原始的SSD网络中的先验框尺寸进行调整，使其大小和长宽比更加适合螺栓目标。
结果
2
实验结果表明，本文方法在正常螺栓类的检测精度达到87.93%，螺栓缺销类的检测精度达到89.15%。与原始的SSD网络相比，检测精度分别提升了2.71%和3.99%。
结论
2
本文方法针对螺栓缺销故障的检测精度较高，较原始SSD网络的检测精度有明显提升，与其他方法相比也有一定优势。为后续进一步提升螺栓缺销的检测精度以及对输电线路中其他部件的识别检测工作奠定了良好的基础。
Objective
2
Bolts are widely distributed connecting components in transmission lines for maintaining the safe and stable operation. Bolt-relevant pins loss may threaten to the key components disintegration for transmission lines and even cause large-scale power outages. To eliminate potential safety hazards and ensure the safe and stable operation of the line
it is inevitable to resolve missing-pins bolt issues timely and accurately. Traditional manual-based transmission line inspection has low efficiency
high risk
and is easily restricted by external environmental factors. Unmanned air vehicle (UAV) inspections have emerged to resolve the security problems to a certain extent. The drones-based high-definition inspection pictures are sent back to the ground for manual processing
but this method is still inefficient
and the missed detection rate and false detection rate are relatively high. Current deep learning technique has yielded more target detection algorithms for transmission line inspections. The challenging issues for inspection picture are derived of the size of the bolt structure and its small proportion and its complicated background. Existing target detection algorithms are oriented to obtain feature maps by continuously up-sampling the pictures input to the network. However
the scale of the feature maps tends to be quite smaller in the continuous up-sampling process. The loss of visual detail information in the feature map can get positioning and classification effects better
which is incapable to the recognition and detection of bolt-relevant pins loss
and the detection effect is poor. In order to improve the detection effect of missing pins of bolt in transmission lines
we develop a method based on inter-level cross feature fusion.
Method
2
To detect multi-scale targets
the single shot multibox detector (SSD) based network is used to output six different scale feature maps. 1) The low-level large-scale feature maps are used to detect small targets
and the high-level small-scale feature maps are used to detect large targets.2) The anchor box mechanism is also introduced into the SSD to guarantee the overall detection in the feature map. Therefore
SSD algorithm is more suitable for detecting bolt-related missing pins in the inspection picture. First
the small target paste data augmentation is carried out on the bolt missing pins fault detection data set. After cutting out the parts corresponding to the missing-pins bolt category and randomly paste into larger-scale inspection pictures
the number of label boxes in the large-scale inspection pictures and the number of images in the data set are both increased to realize data augmentation. Next
the inter-level cross self-adaptive feature fusion module is introduced into SSD network. It can add the feature pyramid structure
improve its structure and increase the level of cross-connection between feature maps. The feature map of the Conv4_3 layer in SSD network is beneficial to the detection of missing-pins bolts. Feature maps of the Conv3_3 layer and the Conv5_3 layer are introduced in terms of the six-layer output feature maps-derived feature pyramid. The fusion of the Conv4_3 layer and the Conv8_2 layer is used to enhance the visual information and semantic information of the feature maps. At the same time
the adaptively spatial feature fusion (ASFF) mechanism is melted into the network to adaptively learn the spatial weights of feature map fusion at various scales
and the obtained weight fusion inspection feature map is used for the final detection. Finally
the K-means clustering method is employed to statistically analyze the size and aspect ratio of the labeled frame for the bolt structure
and the anchor box is adjusted in the original SSD network adequately.
Result
2
The verification experiments are performed for the effectiveness of the network on the PASCAL VOC(pattern analysis
statistical modeling and computational learning visual object classes) dataset. The improved network has reached a 2.3% growth in detection accuracy compared to the original SSD. In the bolt missing pins detection experiments
the training set and the test set are randomly divided according to the ratio of 7:3. Experimental results show that our detection accuracy is 87.93% for normal bolts
89.15% for missing-pins bolts. The detection accuracy is increased by 2.71% and 3.99%
respectively.
Conclusion
2
Our method has greatly improved the accuracy of bolt-relevant pins loss detection. The detection accuracy of the original SSD network has been significantly improved. Our optimized detection is beneficial to further develop the recognition and detection of other parts in the transmission line.
Chen C, Peng X Y, Song S, Wang K, Qian J J and Yang B S. 2017. Safety distance diagnosis of large scale transmission line corridor inspection based on LiDAR point cloud collected with UAV. Power System Technology, 41(8): 2723-2730
陈驰, 彭向阳, 宋爽, 王柯, 钱金菊, 杨必胜. 2017. 大型无人机电力巡检LiDAR点云安全距离诊断方法. 电网技术, 41(8): 2723-2730[DOI: 10.13335/j.1000-3673.pst.2016.3194]
Fu C Y, Liu W, Ranga A, Tyagi A and Berg A C. 2017. DSSD: deconvolutional singleshot detector[EB/OL]. [2021-07-05] . https://arxiv.org/pdf/1701.06659.pdf https://arxiv.org/pdf/1701.06659.pdf
Gu C Y, Li Z, Shi J T, Zhao H H, Jiang Y and Jiang X C. 2020. Detection for pin defects of overhead lines by UAV patrol image based on improved Faster-RCNN. High Voltage Engineering, 46(9): 3089-3096
顾超越, 李喆, 史晋涛, 赵航航, 江一, 江秀臣. 2020. 基于改进Faster-RCNN的无人机巡检架空线路销钉缺陷检测. 高电压技术, 46(9): 3089-3096[DOI: 10.13336/j.1003-6520.hve.20190748]
Kisantal M, Wojna Z, Murawski J, Naruniec J and Cho K. 2019. Augmentation for small object detection[EB/OL]. [2021-07-05] . https://arxiv.org/pdf/1902.07296.pdf https://arxiv.org/pdf/1902.07296.pdf
Li X F, Liu H Y, Liu G H and Su H S. 2021. Transmission line pin defect detection based on deep learning. Power System Technology, 45(8): 2988-2995
李雪峰, 刘海莹, 刘高华, 苏寒松. 2021. 基于深度学习的输电线路销钉缺陷检测. 电网技术, 45(8): 2988-2995[DOI: 10.13335/j.1000-3673.pst.2020.1028]
Li Z X and Zhou F Q. 2017. FSSD: feature fusion single shot MultiBox detector[EB/OL]. [2021-07-05] . https://arxiv.org/pdf/1712.00960.pdf https://arxiv.org/pdf/1712.00960.pdf
Lin T Y, Dollár P, Girshick R B, He K M, Hariharan B and Belongie S. 2017. Feature pyramid networks for object detection//Proceedings of 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Honolulu, USA: IEEE: 936-944[ DOI:10.1109/CVPR.2017.106 http://dx.doi.org/10.1109/CVPR.2017.106 ]
Liu S T, Huang D and Wang Y H. 2019. Learning spatial fusion for single-shot object detection[EB/OL]. [2021-07-05] . https://arxiv.org/pdf/1911.09516.pdf https://arxiv.org/pdf/1911.09516.pdf
Liu T and Wang X L. 2020. Single-stage object detection using filter pyramid and atrous convolution. Journal of Image and Graphics, 25(1): 102-112
刘涛, 汪西莉. 2020. 采用卷积核金字塔和空洞卷积的单阶段目标检测. 中国图象图形学报, 25(1): 102-112[DOI: 10.11834/jig.190166]
Liu W, Anguelov D, Erhan D, Szegedy C, Reed S, Fu C Y and Berg A C. 2016. SSD: single shot MultiBox detector//Proceedings of the 14th European Conference on Computer Vision. Amsterdam, the Netherlands: Springer: 21-37[ DOI:10.1007/978-3-319-46448-0_2 http://dx.doi.org/10.1007/978-3-319-46448-0_2 ]
Miao X R, Lin Z C, Jiang H, Chen J, Liu X Y and Zhuang S B. 2021. Fault detection of power tower anti-bird spurs based on deep convolutional neural network. Power System Technology, 45(1): 126-133
缪希仁, 林志成, 江灏, 陈静, 刘欣宇, 庄胜斌. 2021. 基于深度卷积神经网络的输电线路防鸟刺部件识别与故障检测. 电网技术, 45(1): 126-133[DOI: 10.13335/j.1000-3673.pst.2019.1775]
Peng X Y, Qian J J, Wu G P, Mai X M, Wei L and Rao Z Q. 2017. Full automatic inspection system and its demonstration application based on robot for overhead transmission lines. High Voltage Engineering, 43(8): 2582-2591
彭向阳, 钱金菊, 吴功平, 麦晓明, 魏莱, 饶章权. 2017. 架空输电线路机器人全自主巡检系统及示范应用. 高电压技术, 43(8): 2582-2591[DOI: 10.13336/j.1003-6520.hve.20170731019]
Redmon J and Farhadi A. 2017. YOLO9000: better, faster, stronger//Proceedigns of 2017 IEEE Conference on Computer Vision and Pattern Recognition. Honolulu, USA: IEEE: 6517-6525[ DOI:10.1109/CVPR.2017.690 http://dx.doi.org/10.1109/CVPR.2017.690 ]
Ren S Q, He K M, Girshick R and Sun J. 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[DOI: 10.1109/TPAMI.2016.2577031]
Simonyan K and Zisserman A. 2015. Very deep convolutional networks for large-scale image recognition[EB/OL]. [2021-07-05] . https://arxiv.org/pdf/1409.1556v3.pdf https://arxiv.org/pdf/1409.1556v3.pdf
Wang Z H. 2018. Applied Research on Deep Learning in Defect Detection of Key Components on Transmission Towers. Tianjin: Civil Aviation University of China
王子昊. 2018. 深度学习在输电铁塔关键部件缺陷检测中的应用研究. 天津: 中国民航大学
Yin Z Y, Fan C, Zhao Z H, Huang Z and Zhang F Q. 2021. Object detection algorithm based on the multi-scale feature maps classification and feature extraction. Journal of Chinese Computer Systems, 42(3): 536-541
尹震宇, 樊超, 赵志浩, 黄哲, 张飞青. 2021. 多尺度特征图分类再提取的目标检测算法. 小型微型计算机系统, 42(3): 536-541[DOI: 10.3969/j.issn.1000-1220.2021.03.015]
Zhai S P, Shang D R, Wang S H and Dong S S. 2020. DF-SSD: an improved SSD object detection algorithm based on DenseNet and feature fusion. IEEE Access, 8: 24344-24357[DOI: 10.1109/ACCESS.2020.2971026]
Zhang S, Wang H T, Dong X C, Li Y R, Li Y, Wang X Y and Sun Y Y. 2021. Bolt detection technology of transmission lines based on deep learning. Power System Technology, 45(7): 2821-2829
张姝, 王昊天, 董骁翀, 李玉容, 李烨, 王新迎, 孙英云. 2021. 基于深度学习的输电线路螺栓检测技术. 电网技术, 45(7): 2821-2829[DOI: 10.13335/j.1000-3673.pst.2020.1336]
Zhang X Y. 2018. Research on Grading Ring Detection Technique of Power Line Based on Deep Learning. Beijing: Beijing Jiaotong University
张新影. 2018. 基于深度学习的输电线均压环检测技术研究. 北京: 北京交通大学
Zhao J L, Zhang X Z and Dong H Y. 2022. Defect detection in transmission line based on scale-invariant feature pyramid networks. Computer Engineering and Applications, 58(8): 289-296
赵杰伦, 张兴忠, 董红月. 2022. 基于尺度不变特征金字塔的输电线路缺陷检测. 计算机工程与应用, 58(8): 289-296
Zhao W Q, Cheng X F, Zhao Z B and Zhai Y J. 2020. Insulator recognition based on attention mechanism and Faster RCNN. CAAI Transactions on Intelligent Systems, 15(1): 92-98
赵文清, 程幸福, 赵振兵, 翟永杰. 2020. 注意力机制和Faster RCNN相结合的绝缘子识别. 智能系统学报, 15(1): 92-98[DOI: 10.11992/tis.201907023]
Zhao Z B, Zhang S, Jiang W and Wu P. 2021. Detection method for bolts with mission pins on transmission lines based on DBSCAN-FPN. Electric Power, 54(3): 45-54
赵振兵, 张帅, 蒋炜, 吴鹏. 2021. 基于DBSCAN-FPN的输电线路螺栓缺销检测方法. 中国电力, 54(3): 45-54[DOI: 10.11930/j.issn.1004-9649.202005160]
Zhao Z B, Zhang W, Zhai Y J, Zhao W Q, Zhang K, Kong Y H and Qi Y C. 2020. Concept, research status and prospect of electric power vision technology. Electric Power Science and Engineering, 36(1): 1-8
赵振兵, 张薇, 翟永杰, 赵文清, 张珂, 孔英会, 戚银城. 2020. 电力视觉技术的概念、研究现状与展望. 电力科学与工程, 36(1): 1-8[DOI:10.3969/j.ISSN.1672-0792.2020.01.001]
相关文章
相关作者
相关机构
京公网安备11010802024621
