基于深度学习低图像要求的继电保护压板状态自动识别方法
CSTR:
作者:
作者单位:

(国网天津市电力公司滨海供电分公司,天津 300450)

通讯作者:

彭桂喜(1983—),男,硕士,高级工程师,主要从事继电保护研究;E?mail:505176044@qq.com

中图分类号:

TM863

基金项目:

国网天津市电力公司科技项目(SGTJBH00YJXX1903437)


Automatic recognition method on pressing plate state of relay protection based on deep learning and low image requirements
Author:
Affiliation:

(Binhai Power Supply Branch of State Grid Tianjin Electric Power Company,Tianjin 300450,China)

  • 摘要
  • | |
  • 访问统计
  • |
  • 参考文献 [23]
  • | | | |
  • 文章评论
    摘要:

    继电保护装置压板布局方式逐步向简约化、标准化转变,客观上为压板智能化巡视提供了条件,但受限于实际场景,往往无法提供足够大小和分辨率的压板图像用于压板识别。为此,提出一种基于图像增强和目标识别深度神经网络来识别低分辨率保护压板图像的方法。图像增强网络使用来自目标识别网络的协作学习信号,将极低分辨率的图像增强为更清晰和信息更丰富的图像,使得具有高分辨率图像训练权重的目标识别网络主动参与图像增强网络的学习,并且利用图像增强网络的输出作为增强学习数据,以提高其对极低分辨率对象的识别性能。通过在各种低分辨率图像基准数据集上的实验,验证该方法能够提高保护压板图像的重建和性能的分类。

    Abstract:

    The layout about pressure plate of relay protection devices is gradually changing towards simplicity and standardization, which objectively provides conditions for intelligent inspection of the pressure plate. However, due to the actual scene, it is often impossible to provide pressure plate images with sufficient size and resolution for pressure plate recognition. To this end, a method based on image enhancement and deep neural network for target recognition is proposed to recognize pressure plate images with low resolution. The image enhancement network uses collaborative learning signals from the target recognition network to enhance extremely low-resolution images into clearer and more informative images, so that the target recognition network with high-resolution image training weights actively participates in the learning of the image enhancement network; and then the output of the image enhancement network is utilized as enhanced learning data, to improve the recognition performance for very low-resolution objects. Experiments on various benchmark datasets with low-resolution image verify that this method can improve the reconstruction and classification performance of pressure plate images.

    参考文献
    [1] 郑胤,陈权崎,章毓晋.深度学习及其在目标和行为识别中的新进展[J].中国图象图形学报,2014,19(2):175-184. ZHENG Yin,CHEN Quanqi,ZHANG Yujin.Deep learning and its new progress in object and behavior recognition[J].Journal of Image and Graphics,2014,19(2): 175-184.
    [2] 曲景影,孙显,高鑫.基于CNN模型的高分辨率遥感图像目标识别[J].国外电子测量技术,2016,35(8):45-50. QU Jingying,SUN Xian,GAO Xin.Remote sensing image target recognition based on CNN model[J].Foreign Electronic Measurement Technology,2016,35(8): 45-50.
    [3] 张文达,许悦雷,倪嘉成,等.基于多尺度分块卷积神经网络的图像目标识别算法[J].计算机应用,2016,36(4):1033-1038. ZHANG Wenda,XU Yuelei,NI Jiacheng,et al.Image target recognition method based on multi-scale block convolutional neural network[J].Journal of Computer Applications,2016,36(4): 1033-1038.
    [4] 袁朝晖,付文龙,李佰霖,等.基于多策略分割融合与形态特征辨识的变电站保护压板状态识别[J].电力系统保护与控制,2022,50(1):98-106. YUAN Zhaohui,FU Wenlong,LI Bailin,et al.Protection platen status recognition for a smart substation based on multi-strategy segmentation and fusion and morphological feature identification[J].Power System Protection and Control,2022,50(1):98-106.
    [5] 潘成成,卢泉,胡立坤,等.基于颜色分离与形态特征分析的保护压板定位及状态识别研究[J].电测与仪表,2023,60(4):71-77. PAN Chengcheng,LU Quan,HU Likun,et al.Research of platen location and status recognition based on color separation and morphological features analysis[J].Electrical Measurement & Instrumentation,2023,60(4): 71-77.
    [6] 刘佳音,李翰山,张晓倩.基于深度学习的炸点图像识别与处理方法[J].探测与控制学报,2024,46(1):70-77. LIU Jiayin,LI Hanshan,ZHANG Xiaoqian.A deep learning based explosive point image recognition and processing method[J].Journal of Detection & Control,2024,46 (1): 70-77.
    [7] 熊鹏文,陈志远,廖俊杰,等.基于改进卷积注意力机制的触觉图像识别[J].东南大学学报(自然科学版),2024,54(1):175-182. XIONG Pengwen,CHEN Zhiyuan,LIAO Junjie,et al.Tactile image recognition based on improved convolutional attention mechanism[J].Journal of Southeast University (Natural Science Edition),2024,54 (1): 175-182.
    [8] CAO Q,ZHANG W,ZHU Y.Deep learning-based classification of the polar emotions of "moe"-style cartoon pictures[J].Tsinghua Science and Technology,2021,26(3): 275-286.
    [9] 艾上美,周剑峰,张必朝,等.基于改进SSD算法的光伏组件缺陷检测研究[J].智慧电力,2023,51(12):53-58. AI Shangmei,ZHOU Jianfeng,ZHANG Bichao,et al.Defect detection of photovoltaic modules based on improved SSD algorithm[J].Smart Power,2023,51(12):53-58.
    [10] 黄悦华,陈照源,陈庆,等.基于边缘计算和改进YOLOv5s算法的输电线路故障实时检测方法[J].电力建设,2023,44(1): 91-99. HUANG Yuehua,CHEN Zhaoyuan,CHEN Qing,et al.Real-time detection method for transmission line faults applying edge computing and improved YOLOv5s algorithm[J].Electric Power Construction,2023,44(1): 91-99.
    [11] LI D,HUANG J,LI Y.Progressive representation adaptation for weakly supervised object localization[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2020,42(6): 1424-1438.
    [12] HE K,ZHANG X,REN S,et al.Delving deep into rectifiers: surpassing human-level performance on imagenet classification[C]//IEEE International Conference on Computer Vision (ICCV),Santiago,Chile,2015.
    [13] WANG Z,CHANG S,YANG Y,et al.Studying Very low resolution recognition using deep networks[C]//IEEE Conference on Computer Vision and Pattern Recognition (CVPR),Las Vegas,NV,USA,2016.
    [14] PENG X,HOFFMAN J,YU S X.Fine-to-coarse knowledge transfer for low-res image classification[C]//IEEE International Conference on Image Processing (ICIP),Phoenix,AZ,USA,2016.
    [15] MUDUNURI S P,SANYAL S,BISWAS S.GenLR-Net: deep framework for very low resolution face and object recognition with generalization to unseen categories[C]//IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW),Salt Lake City,UT,USA,2018.
    [16] CAI D,CHEN K,QIAN Y,et al.Convolutional low-resolution fine-grained classification[J].Pattern Recognition Letters,2019,19(2): 119-125.
    [17] KIM J,LEE J K,LEE K M.Accurate image super-resolution using very deep convolutional networks[C]//IEEE Conference on Computer Vision & Pattern Recognition,Las Vegas,NV,USA,2016.
    [18] 孙景博,王阳,杨晓帆,等.中国风光资源气候风险时空变化特征分析[J].中国电力,2023,56(5): 1-10. SUN Jingbo,WANG Yang,YANG Xiaofan,et al.Analysis of spatial and temporal variation character of climate risks of wind and solar resources in China[J].Electric Power,2023,56(5): 1-10.
    [19] 汤健,田昊,夏恒,等.基于多元特征异构集成深度学习的图像识别模型及其应用[J].北京工业大学学报,2024,50(1):27-37. TANG Jian,TIAN Hao,XIA Heng,et al.Image recognition model and its application based on multi feature heterogeneous ensemble deep learning[J].Journal of Beijing University of Technology,2024,50 (1): 27-37.
    [20] 陈泰龙,马玫,陈少磊,等.基于多尺度优化卷积神经网络的配电网电缆局部放电图像识别[J].供用电,2023,40(11):105-111. CHEN Tailong,MA Mei,CHEN Shaolei,et al.Cable fault diagnosis of distribution network based on multi-scale optimized convolutional neural network[J].Distribution & Utilization,2023,40(11):105-111.
    [21] 魏业文,李梅,解园琳,等.基于改进Faster-RCNN的输电线路巡检图像检测[J].电力工程技术,2022,41(2): 171-178. WEI Yewen,LI Mei,XIE Yuanlin,et al.Transmission line inspection image detection based on improved Faster-RCNN[J].Electric Power Engineering Technology,2022,41(2): 171-178.
    [22] MAHENDRAN A,VEDALDI A.Understanding deep image representations by inverting them[C]//IEEE Conference on Computer Vision and Pattern Recognition (CVPR),Boston,MA,USA,2015.
    [23] YU Y L,LI X Z,LIU F X.E-DBPN: enhanced deep back-projection networks for remote sensing scene image superresolution[J].IEEE Transactions on Geoscience and Remote Sensing,2020,58(8): 5503-5515.
    相似文献
    引证文献
    网友评论
    网友评论
    分享到微博
    发 布
引用本文

彭桂喜,袁思遥,高梓寒,等.基于深度学习低图像要求的继电保护压板状态自动识别方法[J].电力科学与技术学报,2024,39(2):134-142.
PENG Guixi, YUAN Siyao, GAO Zihan, et al. Automatic recognition method on pressing plate state of relay protection based on deep learning and low image requirements[J]. Journal of Electric Power Science and Technology,2024,39(2):134-142.

复制
分享
文章指标
  • 点击次数:143
  • 下载次数: 502
  • HTML阅读次数: 0
  • 引用次数: 0
历史
  • 在线发布日期: 2024-05-29
文章二维码