作　　者： ; ;

机构地区： 中国计量学院机电工程学院

出　　处： 《机械设计与研究》 2012年第4期73-78,共6页

摘　　要： 探讨了基于扩展的自组织特征映射神经网络的扫描式密集数据采集的测头半径三维补偿。构建了测头半径三维补偿神经网络模型及其训练算法。首先经过训练,神经网络将整个数字化点群数据分成许多子区域,每个子区域用一个微切平面逼近;然后对子区域的分类核心,即神经元位置权重,沿微切平面法矢方向进行修正;最后根据微切平面的法线,对测头半径进行三维补偿。算例表明所创建的测头半径三维补偿神经网络模型有效可行。 Based on the extended self- organizing feature map （ESOFM） neural network, an approach to the probe radius 3D compensation of the coordinate measuring machine for the dense 3D scattered measuring data is devel- oped. After the neural network is trained, the whole scattered data are divided into sub - regions, which and the classi- fication core of each sub - regian are represented by the weight vector of the neurons. Every sub - region is approxima- ted by a tangent plane. Then the neuron location weights of the probe radius 3D compensation model are adjusted along the normal vectors of the tangent plane. Finally, the probe radius is compensated according to the normal vector of the tangent plane. The method is validated experimentally by three examples.

关 键 词： 三坐标测量机 测头半径补偿 神经网络 微切平面 矩形网格 密集散乱数据

领　　域： [机械工程]