点击次数：

论文类型： 会议论文

发表时间： 2010-01-01

收录刊物： EI、Scopus

期号： PART 2

页面范围： 613-618

摘要： Due to the inherent limitations of structure and dimensional, it is difficult to measure the surface roughness of micro-heterogeneous surface in deep hole. In this paper, the microscopic image of micro-heterogeneous surface is obtained by the long working distance lenses of digital microscopic camera, firstly. Thereafter, two artificial neural network models, which take microscopic image features as the inputs, are presented to measure the surface roughness. Then, experiments on the microscopic image acquisition and roughness calibration are conducted. Finally, the analysis results indicate that the proposed measurement method is efficient and effective for evaluating the microcosmic surface roughness of micro-heterogeneous surface in deep hole. ? 2010 IEEE.