基于改进Mask R-CNN的输电线路安全检测方法研究

扫码查看

原文链接

万方数据
维普

中文摘要：随着全球电力需求的持续增长和电力网络的不断扩展,输电线路的安全性与稳定性尤为重要.输电线路在连接发电厂和用户的过程中,承担着可靠输送电能的重要职责.为提升输电线路的安全,研究提出一种基于掩膜区域卷积神经网络(Mask Region Convolutional Neural Network,Mask R-CNN)的输电线路安全检测模型,并引入特征金字塔网络(Feature Pyramid Network,FPN)对其进行改进.实验结果表明,在数据集尺寸为 500 时,改进Mask R-CNN模型的准确率为 0.91,损失函数值为 0.01.改进的Mask R-CNN模型能够有效提升输电线路缺陷检测的精度,具有较高的实用价值,能够提高电力系统的安全监控水平.

外文标题：Transmission Line Safety Detection Method Based on Improved Mask R-CNN

外文摘要：With the continuous growth of global electricity demand and the continuous expansion of power networks,the safety and stability of transmission lines are particularly important.The transmission line plays an important role in reliably transmitting electrical energy during the process of connecting power plants and users.In order to improve the safety of transmission lines,a transmission line safety detection model based on Mask Region Convolutional Neural Network(Mask R-CNN)is proposed,and a Feature Pyramid Network(FPN)is introduced to improve it.The experimental results show that when the data set size is 500,the accuracy of the improved Mask R-CNN model is 0.91,and the loss function value is 0.01.The research results show that the improved Mask R-CNN model can effectively improve the accuracy of transmission line defect detection,has high practical value,and can improve the security monitoring level of power system.

外文关键词：

transmission linessecurity testingMask Region Convolutional Neural Network(Mask R-CNN)Feature Pyramid Network(FPN)

作者：

王铭晟

展开 >

作者单位：

国网平山县供电公司,河北石家庄 050400

关键词：

输电线路安全检测掩膜区域卷积神经网络(Mask R-CNN) 特征金字塔网络(FPN)

出版年：

2024

DOI：