应力盘智能控制盘面面形的表征方法及检测技术的研究  

Method for representing the surface and testing technology of stressed-lap in CMAC controller

作　　者：范斌[1] 杨力[1] 曾志革[1] 李晓今[1] 邓建明[1] 万勇建[1] 

机构地区：[1]中国科学院光电技术研究所,成都610209

出　　处：《光学技术》2005年第5期751-753,757,共4页Optical Technique

基　　金：国家863高技术资助项目

摘　　要：分析了CMAC神经网络应力盘智能控制中面形表征及检测的特点,提出了以Zernike多项式系数用于表征应力盘盘面面形的方法,以微位移阵列传感器检测得到的原始数据经插值拟合重构出盘面面型数据,再经Gram-Schimdt正交化后拟合出的Zernike多项式的系数,以此作为CMAC神经网络的输入样本来完成CMAC神经网络的训练。并在实验中初步验证了此方法的可行性。A method for representing the surface and testing technology of stressed-lap was provided base on the analysis ot stressed-lap surface feature in CMAC neural networks. The original data from the micro displacement sensor matrix were interpolated and fitted to reform the surface data of stressed-lap. The coefficient of Zemike polynomial fitted form reformed data by Graan-Schimdt method was lcoked as input sample to finish training the CMAC neural networks. The experiment showed that this method is available to represent and tested the surface of stresed-lap.

关 键 词：光学加工 应力盘 CMAC 

分 类 号：TQ171.6[化学工程—玻璃工业]