期刊文献+

基于集成学习PCA多元融合的输电线路图像生成研究 被引量:1

Research on transmission line image generation based on ensemble learning PCA multiple fusion
原文传递
导出
摘要 电力系统巡维图像中存在缺陷的样本图像极少,导致正常样本和缺陷样本不均衡,无法使用深度学习等算法来进一步研究输电线路的故障检测。目前各种基于深度机器学习的图像生成方法均存在分辨率低、缺陷特征不明显等问题,导致生成的样本图像难以满足研究人员的需要。本文提出一种基于集成学习(ensemble learning,EL)的PCA加权平均多元融合(diverse integration,DI)生成方法。采用正常和含有缺陷的输电线路绝缘子图像进行实验,实验结果表明生成图像质量效果明显,可以有效运用于电力系统构建专业的样本库,为后续相关研究提供大数据支撑,也为该领域提出一种新颖可行的研究方法。 There are few defective sample images among patrol images in the power system, leading to an imbalance between normal samples and defective samples, and It is impossible to use algorithms such as deep learning to study the fault detection of transmission lines further.At present, various of image generation methods based on deep machine learning have problems such as low resolution and unconspicuous defect features, which makes it difficult for the generated sample images to meet the needs of researchers.This paper proposes a PCA weighted average(diverse integration, DI) generation method based on(ensemble learning, EL).Experiments were carried out with normal and defective transmission line insulator images.The experimental results show that the quality of the generated images is obvious, which can be effectively used in the construction of a professional sample library for power systems, providing big data support for subsequent related research, and also proposed a new and feasible research idea for this field.
作者 张福正 李琨 李仕林 赵李强 董厚琦 ZHANG Fuzheng;LI Kun;LI Shilin;ZHAO Liqiang;DONG Houqi(School of Information Engineering and Automation,Kunming University of Science and Technology,Kunming,Yunnan 650504»China;Electric Power Research Institute,Yunnan Power Grid Co.,Ltd.,Kunming,Yunnan 650217,China;Nengxun Technology Co.,Ltd.,Kunming,Yunnan 650217,China;School of Economics and Management,North China Electric Power University,Beijing 102206,China)
出处 《光电子.激光》 CAS CSCD 北大核心 2021年第8期841-851,共11页 Journal of Optoelectronics·Laser
基金 云南电网有限责任公司省公司下达科技项目(输电线路缺陷样本自动生成及缺陷智能识别方法研究与模型构建,YNKJXM20190719)资助项目。
关键词 集成学习 深度卷积生成对抗网络 变分自编码器 输电线路 主成分分析算法 图像融合 ensemble learning deep convolution generative adversarial network variational autoencoder transmission lines principal component analysis algorithm image fusion
  • 相关文献

参考文献11

二级参考文献71

  • 1王超,叶中付.基于相似性的图像融合质量的客观评估方法[J].软件学报,2006,17(7):1580-1587. 被引量:14
  • 21.Valiant L G.A Theory of Learnable.Communication of ACM,1984; 27:1134-1142
  • 32.Kearns M,Valiant L G.Learning Boolean Formulae or Factoring.Te- chnical Report TR-1488,Cambridge,MA:Havard University Aiken Computation Laboratory,1988
  • 43.Kearns M,Valiant L G.Crytographic Limitation on Learning Boolean Formulae and Finite Automata.In:Proceedings of the 21st Annual ACM Symposium on Theory of ComputingNew YorkNY:ACM press, 1989:433-444
  • 54.Schapire R E.The Strength of Weak Learnability.Machine Learning, 1990;5:197-227
  • 65.Freund Y.Boosting a Weak Algorithm by Majority.Information and Computation,1995;121(2):256-285
  • 76.Freund Y,Schapire R E.A Decision-Theoretic Generalization of On- Line Learning and an Application to Boosting.Journal of Computer and System Sciences,1997;55(1):119-139
  • 88.Schapire R EFreund YBartlett Y,et al.Boosting the Margin:A New Explanation for the Effectiveness of Voting Methods.The Annals of Statistics,1998;26(5):1651-1686
  • 99.Schapire R E.A Brief Introduction of Boosting.InProceedings of the 16th International Joint Conference on Artificial Intelligence,1999
  • 1010.Schapire R E.A Brief Introduction of Boosting. In: Proceedings of the 16th International joint Conference on Artificial Intelligence1999

共引文献327

同被引文献8

引证文献1

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部