精密零件的工业CT图像测量方法  

Industrial CT image measurement of precision parts

作　　者：吕健 栾传彬 张秀英[2] 蔡玉芳[2] LÜJian;LUAN Chuanbin;ZHANG Xiuying;CAI Yufang(AECC South Industry Co.,Ltd.,Zhuzhou,412002,China;Engineering Research Center of Industrial Computed Tomography Nondestructive Testing of the Ministry of Education,Chongqing University,Chongqing 400044,China)

机构地区：[1]中国航发南方工业有限公司,株洲412002 [2]重庆大学工业CT无损检测教育部工程研究中心,重庆400044

出　　处：《无损检测》2022年第4期28-34,54,共8页Nondestructive Testing

基　　金：国家科技重大专项(2017-VII-0011-0106)。

摘　　要：利用工业CT实现精密零件内部尺寸的高精度测量已逐渐成为产品质量控制的重要技术手段,而CT图像分割和数据拟合是工业CT图像测量的重要环节和难点问题。基于此,采用联合小波变换和RSF模型的图像分割方法对精密零件CT图像轮廓进行精确分割,得到感兴趣轮廓数据,接着采用最小二乘拟合方法得到圆和直线方程,进而测量得到感兴趣对象的直径和角度;同时,对于零件壁厚的测量,采用最小距离搜索法获取壁厚值。多组精密零件的CT图像测量结果表明,该方法测量精度总体优于通用测量软件VG Studio Max的精度,具有一定工程应用价值。Using industrial CT to achieve high-precision measurement of internal dimensions of precision parts has gradually become an important technical means for product quality control, and CT image segmentation and data fitting are the main determinants and difficulties of industrial CT image measurement. In view of this, this paper adopts the image segmentation method of combining wavelet transform and RSF model to accurately segment the CT images of precision parts and to obtain the edge contour data of the region of interest. Hereafter, the least-squares fitting method was used to obtain the circle and line equations, and then measure the diameter and angle values of the object of interest;meanwhile, for the measurement of the wall thickness of the part, the minimum distance search method was used to obtain the wall thickness value. The measurement results of several sets of CT images of precision parts show that the measurement accuracy of WT-RSF method is generally better than that of the general measurement software VG Studio Max, and has certain engineering application value.

关 键 词：CT图像测量 WT-RSF方法 图像分割 最小二乘拟合 最小距离搜索 

分 类 号：TG115.28[金属学及工艺—物理冶金]