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
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)

作者简介:

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)

Fund Project:

  • 摘要
  • |
  • 图/表
  • |
  • 访问统计
  • |
  • 参考文献
  • |
  • 相似文献
  • |
  • 引证文献
  • |
  • 资源附件
  • |
  • 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
    相似文献
    引证文献
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:
  • 下载次数:
  • HTML阅读次数:
  • 引用次数:
历史
  • 收稿日期:
  • 最后修改日期:
  • 录用日期:
  • 在线发布日期: 2024-05-29
  • 出版日期: