基于RBF神经网络的三维网格实体模型重构的研究  

A New Approach to Constructing 3-Dimensional Grid Solid Geometry Model Based on RBF Neural Networks

作　　者：鄢腊梅[1] 袁友伟[1] 周锋[2] 

机构地区：[1]株洲工学院,株洲412008 [2]清华大学自动化系,北京100084

出　　处：《机械科学与技术》2004年第10期1249-1252,共4页Mechanical Science and Technology for Aerospace Engineering

基　　金：国家自然科学基金项目 ( 5 0 2 740 80 );湖南省教育厅重点学科建设项目 ( 0 2C64 3 )资助

摘　　要：提出了一种新的基于RBF神经网络的重构三维网格实体模型的算法 ,输入是未知表面的采样点坐标集 ,输出是该未知表面的三维网格近似。同时提出了一个简便而有效的在三维域上三角形网格的Laplacian光顺造型方案 ,网格光顺的结果能保证重建的结果比较光滑。算法较传统的算法更精确和更可靠。A novel scheme for constructing 3D grid solid ge om etry model is presented which is based on RBF(radial basis function )neural netw orks. The inputs are scattered 3D-data with specified topology. The outputs are 3D solid geometry model. A simple and novel smoothing scheme for triangular mes hes on a 3D non-planar surface region is also presented. The method can improve the robustness and reliability of the traditional approaches. The recovered 3D shape is then shown along with the original surface. In comparison with the trad itional methods, examples show that the algorithm is accurate and reliable.

关 键 词：径向基函数 几何造型 三维表面模型 网格光顺 CAD CAM 人工智能 表面重建 

分 类 号：TP391[自动化与计算机技术—计算机应用技术] TP18[自动化与计算机技术—计算机科学与技术]