摘要
针对点云分割结果完整度和逼真度较低的问题,研究基于数字孪生技术的变电站快速建模点云分割方法。使用三维激光扫描技术采集变电站点云数据,依据特征点的密度初步分割变电站点云数据,运用随机森林深入分割难以确定分类的边缘点云数据,引入数字孪生技术实现变电站快速建模。实验结果表明,该方法能很好地保留变电站各区域的边缘轮廓和纹理特征,模型完整度和逼真度较高,且对结构简单的单一设备,以及大规模、结构复杂的变电站均具有优良的快速建模效果。
Aiming at the problem of low integrity and fidelity of point cloud segmentation results,a rapid modeling point cloud segmentation method for substation based on digital twin technology is studied.The three-dimensional laser scanning technology is used to collect the substation point cloud data,and the substation point cloud data are preliminarily segment according to the density of characteristic points.The random forest is used to deeply segment the edge point cloud data that are difficult to determine the classification,and the digital twin technology is introduced to realize the rapid modeling of the substation.The experimental results show that the method can preserve the edge contour and texture features of each region of the substation well.The model has high integrity and fidelity,and has excellent rapid modeling effect for single equipment with simple structure and large-scale and complex substation.
作者
范子恺
王菲
任佳依
王球
张楠
王俊
FAN Zikai;WANG Fei;REN Jiayi;WANG Qiu;ZHANG Nan;WANG Jun(Economic and Technological Research Institute of State Grid Jiangsu Electric Power Co.,Ltd.,Nanjing 210000,China)
出处
《微型电脑应用》
2024年第3期117-120,共4页
Microcomputer Applications
关键词
数字孪生
变电站
快速建模
点云分割
特征提取
digital twins
substation
rapid modeling
point cloud segmentation
feature extraction
