期刊文献+
共找到2篇文章
< 1 >
每页显示 20 50 100
MODEL RECONSTRUCTION FROM CLOUD DATA FOR RAPID PROTOTYPE MANUFACTURING 被引量:1
1
作者 张丽艳 周儒荣 周来水 《Transactions of Nanjing University of Aeronautics and Astronautics》 EI 2001年第2期170-175,共6页
Model reconstruction from points scanned on existing physical objects is much important in a variety of situations such as reverse engineering for mechanical products, computer vision and recovery of biological shapes... Model reconstruction from points scanned on existing physical objects is much important in a variety of situations such as reverse engineering for mechanical products, computer vision and recovery of biological shapes from two dimensional contours. With the development of measuring equipment, cloud points that contain more details of the object can be obtained conveniently. On the other hand, large quantity of sampled points brings difficulties to model reconstruction method. This paper first presents an algorithm to automatically reduce the number of cloud points under given tolerance. Triangle mesh surface from the simplified data set is reconstructed by the marching cubes algorithm. For various reasons, reconstructed mesh usually contains unwanted holes. An approach to create new triangles is proposed with optimized shape for covering the unexpected holes in triangle meshes. After hole filling, watertight triangle mesh can be directly output in STL format, which is widely used in rapid prototype manufacturing. Practical examples are included to demonstrate the method. 展开更多
关键词 reverse engineering model reconstruction cloud data data filtering hole filling
下载PDF
基于时序上采样卷积神经网络的风机叶片结冰检测 被引量:4
2
作者 姜娜 严蜜 李柠 《控制与决策》 EI CSCD 北大核心 2022年第8期2017-2025,共9页
风电机组叶片结冰检测对风电机组的安全性、可靠性以及经济性具有非常重要的现实意义.针对风电机组运行观测数据的非平衡和单点无时序性问题,提出一种基于过采样和时序上采样卷积神经网络的风机叶片结冰检测方法.首先,采用数据自适应综... 风电机组叶片结冰检测对风电机组的安全性、可靠性以及经济性具有非常重要的现实意义.针对风电机组运行观测数据的非平衡和单点无时序性问题,提出一种基于过采样和时序上采样卷积神经网络的风机叶片结冰检测方法.首先,采用数据自适应综合过采样算法对原始非平衡数据集进行重采样,实现对非平衡数据集的均衡;然后,提出并构建一种时序上采样卷积神经网络模型,将原始单点向量型数据进行重构并上采样为二维网格型数据,同时将其自动映射成为稀疏的特征表示,实现准确的风机叶片结冰检测功能;最后,将所提出方法在真实风场采集的数据集上进行验证.实验结果表明,所提出的风机叶片结冰检测方法在数据集非平衡且采集条件有限(单点无时序性数据)的情况下,具有一定的有效性、稳定性和可行性. 展开更多
关键词 叶片结冰检测 非平衡数据 向量型数据 时序上采样 一维卷积神经网络 深度学习
原文传递
上一页 1 下一页 到第
使用帮助 返回顶部