Abstract：Transmission lines occupy a relatively large proportion in the power system, in order to ensure the safe and stable operation of the power system, it is necessary to regularly inspect the transmission lines, among them, insulators in the transmission line play the role of insulation and support, due to the long-term hanging and working outdoors, prone to self-explosion defects, resulting in short-circuit faults on the line, and even large-scale power outages. With the development of artificial intelligence, the use of unmanned aerial vehicles (UAV) for line inspection, and then based on deep learning target detection methods for insulator defect detection has become an intelligent inspection method with great development potential. Due to the different shooting angles of the UAV, the insulators of the lines obtained by the inspection are different, and the environment in which the insulators are located is different, which results in the occlusion phenomenon of some insulators, to overcome these problems, this paper proposes to make relevant improvements on the basis of the two-stage target detection algorithm Mask region-convolutional neural network (Mask R-CNN), to ensure the detection speed and improve the detection rate of defective insulators by the algorithm. For the insulator defects belonging to the category of small target detection, the convolutional block attention module (CBAM) attention mechanism is introduced in the backbone feature extraction network, so that the network can focus on the defect contour and obtain more interesting high-semantic information in the process of extracting the semantic information of the defect part. Then, in order to improve the limitations of semantic information still possessed by the feature layer, the parallel "bottom-up" path and feature fusion module are added to the original feature fusion network to promote the flow of information and global feature fusion. Once more, with the help of Generalized Intersection over Union (GIoU) to accurately characterize the distance between targets, the positioning performance of the model can be effectively improved when the targets overlap. Conclusively, the part of the original algorithmic loss function is replaced with the Tversky Loss function to alleviate the effect of sample imbalance on model training. Based on the defective insulator dataset obtained by the UAV operation class of a transmission and transportation inspection center of the State Grid, the training of the improved network is carried out, and the model training effect is obtained from the convergence of the loss curve, and the generalization ability of the model is also improved. By using the improved model for defect detection and comparing the visual positioning results, the proposed algorithm avoids the interference of the high likelihood structure around the target to a certain extent, which realizes the effective detection of the insulator defect part, and improves the impact of small targets and sample unevenness on the detection. Compared with the original algorithm, the AP50:95 of the proposed algorithm is increased to 0.56, AP50 to 0.79, and AP75 to 0.72. Finally, the performance of the algorithm is comprehensively compared, and the P-R curves of the improved before and after models under the conditions of AP50 and AP75 are compared, and it can be obtained that the corresponding curves of the improved algorithm are on the outside of the original algorithm curve, which shows the effectiveness of the proposed method, and the performance is better than that of the original algorithm.
苟军年, 杜愫愫, 刘力. 基于改进掩膜区域卷积神经网络的输电线路绝缘子自爆检测[J]. 电工技术学报, 2023, 38(1): 47-59.
Gou Junnian, Du Susu, Liu Li. Transmission Line Insulator Self-Explosion Detection Based on Improved Mask Region-Convolutional Neural Network. Transactions of China Electrotechnical Society, 2023, 38(1): 47-59.
[1] 赵振兵, 翟永杰, 张珂, 等. 电力视觉技术[M]. 北京: 中国电力出版社, 2020. [2] 申泽浩. 航拍架空输电线路绝缘子缺陷检测方法研究[D]. 天津: 天津工业大学, 2020. [3] Ren Ruoxu, Hung T, Tan K C.A generic deep-learning-based approach for automated surface inspection[J]. IEEE Transactions on Cybernetics, 2018, 48(3): 929-940. [4] 翟永杰, 王迪, 赵振兵. 基于目标建议与结构搜索的绝缘子识别方法[J]. 华北电力大学学报(自然科学版), 2016, 43(4): 66-71, 78. Zhai Yongjie, Wang Di, Zhao Zhenbing.Recognition method of insulator based on object proposals and structure research[J]. Journal of North China Electric Power University (Natural Science Edition), 2016, 43(4): 66-71, 78. [5] Zhao Zhenbing, Xu Guozhi, Qi Yincheng, et al.Multi-patch deep features for power line insulator status classification from aerial images[C]//2016 International Joint Conference on Neural Networks (IJCNN), Vancouver, BC, Canada, 2016: 3187-3194. [6] 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. [7] 陈明, 赵连飞, 苑立民, 等. 基于特征选择YOLOv3网络的红外图像绝缘子检测方法[J]. 红外与激光工程, 2020, 49(增刊2): 262-267. Chen Ming, Zhao Lianfei, Yuan Limin, et al.Insulator detection method based on feature selection YOLOv3 network[J]. Infrared and Laser Engineering, 2020, 49(S2): 262-267. [8] 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. [9] 李瑞生, 张彦龙, 翟登辉, 等. 基于改进SSD的输电线路销钉缺陷检测[J]. 高电压技术, 2021, 47(11): 3795-3802. Li Ruisheng, Zhang Yanlong, Zhai Denghui, et al.Pin defect detection of transmission line based on improved SSD[J]. High Voltage Engineering, 2021, 47(11): 3795-3802. [10] 郝帅, 杨磊, 马旭, 等.基于注意力机制与跨尺度特征融合的YOLOv5输电线路故障检测[J/OL]. 中国电机工程学报: 1-12 [2022-08-09]. http://kns.cnki. net/kcms/detail/11.2107.tm.20220126.1718.008.html. Hao Shuai, Yang Lei, Ma Xu, et al. YOLOv5 Transmission Line Fault Detection Based on Attention Mechanism and Cross-scale Feature Fusion[J/OL]. Proceedings of the CSEE: 1-12 [2022-08-09]. http://kns.cnki.net/kcms/detail/11.2107.tm.20220126.1718.008.html. [11] 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. [12] 易继禹, 陈慈发, 龚国强. 基于改进Faster RCNN的输电线路航拍绝缘子检测[J]. 计算机工程, 2021, 47(6): 292-298, 304. Yi Jiyu, Chen Cifa, Gong Guoqiang.Aerial insulator detection of transmission line based on improved faster RCNN[J]. Computer Engineering, 2021, 47(6): 292-298, 304. [13] 赵振兵, 熊静, 李冰, 等. 基于改进Cascade R-CNN的典型金具及其部分缺陷检测方法[J]. 高电压技术, 2022, 48(3): 1060-1067. Zhao Zhenbing, Xiong Jing, Li Bing, et al.Typical fittings and its partial defect detection method based on improved Cascade R-CNN[J]. High Voltage Engineering, 2022, 48(3): 1060-1067. [14] 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. [15] 孙备, 左震, 吴鹏, 等. 面向无人艇环境感知的改进型SSD目标检测方法[J]. 仪器仪表学报, 2021, 42(9): 52-61. Sun Bei, Zuo Zhen, Wu Peng, et al.Object detection for environment perception of unmanned surface vehicles based on the improved SSD[J]. Chinese Journal of Scientific Instrument, 2021, 42(9): 52-61. [16] 伍锡如, 邱涛涛, 王耀南. 改进Mask R-CNN的交通场景多目标快速检测与分割[J]. 仪器仪表学报, 2021, 42(7): 242-249. Wu Xiru, Qiu Taotao, Wang Yaonan.Multi-object detection and segmentation for traffic scene based on improved Mask R-CNN[J]. Chinese Journal of Scientific Instrument, 2021, 42(7): 242-249. [17] 赵文清, 程幸福, 赵振兵, 等. 注意力机制和Faster RCNN相结合的绝缘子识别[J]. 智能系统学报, 2020, 15(1): 92-98. Zhao Wenqing, Cheng Xingfu, Zhao Zhenbing, et al.Insulator recognition based on attention mechanism and Faster RCNN[J]. CAAI Transactions on Intelligent Systems, 2020, 15(1): 92-98. [18] He Kaiming, Zhang Xiangyu, Ren Shaoqing, et al.Deep residual learning for image recognition[C]//2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA, 2016: 770-778. [19] 蒋弘毅, 王永娟, 康锦煜. 目标检测模型及其优化方法综述[J]. 自动化学报, 2021, 47(6): 1232-1255. Jiang Hongyi, Wang Yongjuan, Kang Jinyu.A survey of object detection models and its optimization methods[J]. Acta Automatica Sinica, 2021, 47(6): 1232-1255. [20] 张宸嘉, 朱磊, 俞璐. 卷积神经网络中的注意力机制综述[J]. 计算机工程与应用, 2021, 57(20): 64-72. Zhang Chenjia, Zhu Lei, Yu Lu.Review of attention mechanism in convolutional neural networks[J]. Computer Engineering and Applications, 2021, 57(20): 64-72. [21] Woo S, Park J, Lee J Y, et al.CBAM: convolutional block attention module[C]//Computer Vision - ECCV 2018, Munich, Germany, 2018: 3-19. [22] 史彩娟, 陈厚儒, 葛录录, 等. 注意力残差多尺度特征增强的显著性实例分割[J]. 图学学报, 2021, 42(6): 883-890. Shi Caijuan, Chen Houru, Ge Lulu, et al.Salient instance segmentation via attention residual multi-scale feature enhancement[J]. Journal of Graphics, 2021, 42(6): 883-890. [23] Liu Shu, Qi Lu, Qin Haifang, et al.Path aggregation network for instance segmentation[C]//2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA, 2018: 8759-8768. [24] 文韬, 周稻祥, 李明. Mask R-CNN中特征不平衡问题的全局信息融合方法[J]. 计算机工程, 2021, 47(3): 256-260, 268. Wen Tao, Zhou Daoxiang, Li Ming.Global information fusion method for feature imbalance problem in mask R-CNN[J]. Computer Engineering, 2021, 47(3): 256-260, 268. [25] 侯志强, 刘晓义, 余旺盛, 等. 使用GIoU改进非极大值抑制的目标检测算法[J]. 电子学报, 2021, 49(4): 696-705. Hou Zhiqiang, Liu Xiaoyi, Yu Wangsheng, et al.Object detection algorithm for improving non-maximum suppression using GIoU[J]. Acta Electronica Sinica, 2021, 49(4): 696-705. [26] 曹洁, 何智栋, 余萍, 等. 数据不平衡分布下轴承故障诊断方法[J/OL]. 吉林大学学报(工学版): 1-10 [2021-08-19]. DOI:10.13229/j.cnki.jdxbgxb20210374. Cao Jie, He Zhidong, Yu Ping, et al.Bearing fault diagnosis method under unbalanced data distribution[J]. Journal of Jilin University (Engineering and Technology Edition): 1-10 [2021-08-19]. DOI:10.13229/j.cnki. jdxbgxb20210374. [27] Salehi S S M, Erdogmus D, Gholipour A. Tversky loss function for image segmentation using 3D fully convolutional deep networks[C]//MLMI 2017: Machine Learning in Medical Imaging, Quebec City, QC, Canada, 2017: 379-387. [28] 周宸, 高伟, 郭谋发. 基于YOLOv4模型的玻璃绝缘子自爆缺陷识别方法[J]. 电气技术, 2021, 22(5): 38-42, 49. Zhou Chen, Gao Wei, Guo Moufa.Recognition method of self-explosion defects of glass insulators based on YOLOv4 model[J]. Electrical Engineering, 2021, 22(5): 38-42, 49.
2023, Vol. 38 
