<-上一篇/Previous Article 下一篇/Next Article->

[1]赵振兵,席悦,冯烁,等.面向复杂场景的变电设备锈蚀检测方法[J].智能系统学报,2025,20(3):679-688.[doi:10.11992/tis.202403044]
　ZHAO Zhenbing,XI Yue,FENG Shuo,et al.Corrosion detection method for complex scenario substation equipment[J].CAAI Transactions on Intelligent Systems,2025,20(3):679-688.[doi:10.11992/tis.202403044]

点击复制

面向复杂场景的变电设备锈蚀检测方法

PDF下载 HTML

《智能系统学报》[ISSN 1673-4785/CN 23-1538/TP] 卷: 20 期数: 2025年第3期页码: 679-688 栏目: 学术论文—智能系统出版日期: 2025-05-05

Title:: Corrosion detection method for complex scenario substation equipment

作者:: 赵振兵^1,2,3, 席悦¹, 冯烁¹, 赵文清^2,4, 翟永杰⁴, 李冰⁴; 1. 华北电力大学电子与通信工程系, 河北保定 071003;
2. 华北电力大学复杂能源系统智能计算教育部工程研究中心, 河北保定 071003;
3. 华北电力大学河北省电力物联网技术重点实验室, 河北保定 071003;
4. 华北电力大学控制与计算机工程学院, 河北保定 071003

Author(s):: ZHAO Zhenbing^1,2,3, XI Yue¹, FENG Shuo¹, ZHAO Wenqing^2,4, ZHAI Yongjie⁴, LI Bing⁴; 1. Department of Electronic and Communication Engineering, North China Electric Power University, Baoding 071003, China;
2. Engineering Research Center of Intelligent Computing for Complex Energy Systems of Ministry of Education, North China Electric Power University, Baoding 071003, China;
3. Hebei Key Laboratory of Power Internet of Things Technology, North China Electric Power University, Baoding 071003, China;
4. School of Control and Computer Engineering, North China Electric Power University, Baoding 071003, China

关键词:: 变电设备; 不规则缺陷; 锈蚀检测; YOLOv8; 注意力机制; 多尺度特征; 检测头; 复杂场景; 电力视觉

Keywords:: substation equipment; irregular defect; corrosion detection; YOLOv8; attention mechanism; multi-scale feature; detection head; complex scenarios; power computer vision

分类号:: TP183

DOI:: 10.11992/tis.202403044

摘要:: 针对复杂场景下变电设备锈蚀检测中存在锈蚀形态差异大、尺度大小不一、特征显著性低等问题，提出了一种面向复杂场景的变电设备锈蚀检测方法。引入了频率通道注意力机制，通过更多的频率分量补充深层网络中的细节特征，优化模型对锈蚀特征的提取；在特征融合网络中使用多尺度特征增强模块重新构建C2f模块，使网络可以更好地捕获不同大小的锈蚀区域；引入附加检测头，缓解模型在特征融合过程中因卷积层下采样造成的锈蚀关键信息丢失的情况，从而提高变电设备锈蚀检测的精度。实验结果表明，改进以后的网络模型相较于原始的YOLOv8m模型，平均检测精度(mAP50)提升了5.1%，检测效果也优于其他主流目标检测模型，为变电设备锈蚀检测提供了新的参考方法。

Abstract:: To address the significant challenges posed by significant variations in corrosion morphology, varying scales, and low feature saliency in corrosion detection in substation equipment under complex scenarios, a corrosion detection method for complex scenario substation equipment is proposed. First, frequency channel attention networks are introduced, leveraging additional frequency components to complement the fine-grained features in deep networks, thus optimizing the extraction of corrosion-related features. Second, within the feature fusion network, the multi-scale module is employed to rebuild the C2f module, thereby allowing the network to better capture corrosion areas of different sizes. Finally, the additional detection head mitigates crucial corrosion-related information loss during feature fusion caused by downsampling, thereby enhancing corrosion detection accuracy. The relevant experimental results reveal a 5.1% improvement in the average detection accuracy (mAP50/%) compared with the results obtained by the original YOLOv8m model. Overall, this improved model outperforms other mainstream object detection models, thereby representing a novel approach for substation equipment corrosion detection.

参考文献/References:: [1] 赵振兵, 冯烁, 赵文清, 等. 融合知识迁移和改进YOLOv6的变电设备热像检测方法[J]. 智能系统学报, 2023, 18(6): 1213-1222.
ZHAO Zhenbing, FENG Shuo, ZHAO Wenqing, et al. Thermd image detection method for substation equipment by incorporating knowledge migration and improved YOLOv6[J]. CAAI transactions on intelligent systems, 2023, 18(6): 1213-1222.
[2] 吴添权, 戴美胜, 杨刚, 等. 基于改进Mask-RCNN模型的电力设备锈蚀识别[J]. 电力信息与通信技术, 2021, 19(4): 25-30.
WU Tianquan, DAI Meisheng, YANG Gang, et al. Corrosion detection of power equipment based on improved mask-RCNN model[J]. Electric power information and communication technology, 2021, 19(4): 25-30.
[3] 王凌云, 李婷宜, 李阳, 等. 基于FEF-DeepLabV3+的电力金具锈蚀分割方法[J]. 电子测量与仪器学报, 2023, 37(7): 166-176.
WANG Lingyun, LI Tingyi, LI Yang, et al. Segmentation method of power armor clamp corrosion based on FEF-DeepLabV3+[J]. Journal of electronic measurement and instrumentation, 2023, 37(7): 166-176.
[4] LOWE D G. Distinctive image features from scale-invariant keypoints[J]. International journal of computer vision, 2004, 60(2): 91-110.
[5] ZHU Qiang, YEH M C, CHENG K T, et al. Fast human detection using a cascade of histograms of oriented gradients[C]//2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. New York: IEEE, 2006: 1491-1498.
[6] 刘传洋, 吴一全. 基于深度学习的输电线路视觉检测方法研究进展[J]. 中国电机工程学报, 2023, 43(19): 7423-7446.
LIU Chuanyang, WU Yiquan. Research progress of vision detection methods based on deep learning for transmission lines[J]. Proceedings of the CSEE, 2023, 43(19): 7423-7446.
[7] ZHANG Yu, LI Weixing, ZHOU Jian, et al. Substation equipment abnormity detection based on improved YOLOv5[C]//2022 41st Chinese Control Conference. Hefei: IEEE, 2022: 6654-6659.
[8] ZHENG Zhaohui, WANG Ping, LIU Wei, et al. Distance-IoU loss: Faster and better learning for bounding box regression[C]//Proceedings of the AAAI Conference on Artificial Intelligence. New York: AAAI, 2020: 12993-13000.
[9] XU Bo, DING Yuan. Research on the application of deep learning object detection in rust defect detection of power equipment[C]//2023 3rd International Conference on Electrical Engineering and Mechatronics Technology. Nanjing: IEEE, 2023: 770-775.
[10] 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.
[11] 张迎晨, 王波, 马富齐, 等. 基于域适应网络的电力设备不规则外表面缺陷高精度检测方法[J]. 高电压技术, 2022, 48(11): 4516-4526.
ZHANG Yingchen, WANG Bo, MA Fuqi, et al. High-precision detection method of irregular outer surface defects of power equipment based on domain adaptation network[J]. High voltage engineering, 2022, 48(11): 4516-4526.
[12] 于豪, 蒋锦霞, 赖晓翰, 等. 基于自适应感受野的电力设备表面缺陷检测方法[J]. 系统仿真学报, 2023, 35(7): 1572-1580.
YU Hao, JIANG Jinxia, LAI Xiaohan, et al. Surface defect detection of power equipment using adaptive receptive field network[J]. Journal of system simulation, 2023, 35(7): 1572-1580.
[13] CHEN Xiaojiao, AN Zhenyu, HUANG Liansheng, et al. Surface defect detection of electric power equipment in substation based on improved YOLOV4 algorithm[C]//2020 10th International Conference on Power and Energy Systems. Chengdu: IEEE, 2020: 256-261.
[14] BOCHKOVSKIY A, WANG C Y, LIAO H M. YOLOv4: optimal speed and accuracy of object detection[EB/OL]. (2020–04–23)[2024–01–01]. https://arxiv.org/abs/2004.10934v1.
[15] DAI Yan, HAN Rui, LIU Li, et al. Research on substation equipment rust detection method based on improved SSD[C]//2021 International Conference on Advanced Electrical Equipment and Reliable Operation. Beijing: IEEE, 2021: 1-3.
[16] LIU Wei, ANGUELOV D, ERHAN D, et al. SSD: single shot MultiBox detector[M]//Computer Vision-ECCV 2016. Cham: Springer International Publishing, 2016: 21-37.
[17] HE Kaiming, ZHANG Xiangyu, REN Shaoqing, et al. Deep residual learning for image recognition[C]//2016 IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas: IEEE, 2016: 770-778.
[18] ZHANG Sheng, DENG Xinling, LU Yumin, et al. A channel attention based deep neural network for automatic metallic corrosion detection[J]. Journal of building engineering, 2021, 42: 103046.
[19] HU Jie, SHEN Li, SUN Gang. Squeeze-and-excitation networks[C]//2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Salt Lake City: IEEE, 2018: 7132-7141.
[20] QIN Zequn, ZHANG Pengyi, WU Fei, et al. FcaNet: frequency channel attention networks[C]//2021 IEEE/CVF International Conference on Computer Vision. Montreal: IEEE, 2021: 763-772.
[21] 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. Honolulu: IEEE, 2017: 936-944.
[22] 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: IEEE, 2018: 8759-8768.
[23] LIN Min, CHEN Qiang, YAN Shuicheng. Network in network[EB/OL]. (2014-03-04)[2024-01-01]. https://arxiv.org/abs/1312.4400v3.
[24] AHMED N, NATARAJAN T, RAO K R. Discrete cosine transform[J]. IEEE transactions on computers, 1974, C-23(1): 90-93.
[25] LIU Jiangjiang, HOU Qibin, CHENG Mingming, et al. Improving convolutional networks with self-calibrated convolutions[C]//2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Seattle: IEEE, 2020: 10093-10102.
[26] LEE C Y, XIE S, GALLAGHER P, et al. Deeply-supervised nets[C]//Artificial intelligence and statistics. San Diego: PMLR, 2015: 562-570.
[27] FENG Chengjian, ZHONG Yujie, GAO Yu, et al. TOOD: task-aligned one-stage object detection[C]//2021 IEEE/CVF International Conference on Computer Vision. Montreal: IEEE, 2021: 3490-3499.
[28] LI Xiang, WANG Wenhai, WU Lijun, et al. Generalized focal loss: Learning qualified and distributed bounding boxes for dense object detection[J]. Advances in neural information processing systems, 2020, 33: 21002-21012.
[29] LI Chuyi, LI Lulu, JIANG Hongliang, et al. YOLOv6: A single-stage object detection framework for industrial applications[EB/OL]. (2022-09-07)[2024-01-01]. https://arxiv.org/abs/2209.02976.
[30] WANG C Y, BOCHKOVSKIY A, LIAO H M. YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors[EB/OL]. (2022-07-06)[2024-01-01]. https://arxiv.org/abs/2207.02696v1.
[31] ZHAO Yian, LYU Wenyu, XU Shangliang, ZHAO Y, et al. Detrs beat yolos on real-time object detection[EB/OL]. (2023-07-06)[2024-01-01]. https://arxiv.org/abs/2304.08069.
[32] WANG C Y, YEH I H, LIAO H M. YOLOv9: learning what you want to learn using programmable gradient information[EB/OL]. (2024-02-29)[2024-03-28]. https://arxiv.org/abs/2402.13616v2.

相似文献/References:: [1]王凯旋,任福继,倪红军,等.基于循环互相关系数的CGAN温度值图像扩增[J].智能系统学报,2022,17(1):32.[doi:10.11992/tis.202106036]
　WANG Kaixuan,REN Fuji,NI Hongjun,et al.Image amplification for temperature value image based on cyclic cross-correlation coefficient CGAN[J].CAAI Transactions on Intelligent Systems,2022,17():32.[doi:10.11992/tis.202106036]
[2]赵振兵,冯烁,赵文清,等.融合知识迁移和改进YOLOv6的变电设备热像检测方法[J].智能系统学报,2023,18(6):1213.[doi:10.11992/tis.202303030]
　ZHAO Zhenbing,FENG Shuo,ZHAO Wenqing,et al.Thermd image detection method for substation equipment by incorporating knowledge migration and improved YOLOv6[J].CAAI Transactions on Intelligent Systems,2023,18():1213.[doi:10.11992/tis.202303030]

备注/Memo

收稿日期:2024-3-28。
基金项目:国家自然科学基金项目（U21A20486, 62373151, 62371188, 62303184）；中央高校基本科研业务费专项资金项目（2023JC006）；河北省自然科学基金项目（F2021502008, F2021502013）.
作者简介:赵振兵，教授，博士，主要研究方向为电力视觉。主持国家自然科学基金项目等纵向课题10项；获省科技进步奖一等奖2项；以第一完成人获得国家专利授权16项；以第一作者出版专著2部、发表学术论文50余篇。E-mail：zhaozhenbing@ncepu.edu.cn。;席悦，硕士研究生，主要研究方向为电力视觉。E-mail：17325207795@163.com。;冯烁，博士研究生，主要研究方向为电力视觉。E-mail：fs_ncepu@163.com。
通讯作者:赵振兵. E-mail：zhaozhenbing@ncepu.edu.cn

更新日期/Last Update: 1900-01-01

面向复杂场景的变电设备锈蚀检测方法 PDF下载HTML

备注/Memo

面向复杂场景的变电设备锈蚀检测方法

PDF下载 HTML