射线数字检测中底片数字化及缺陷信息库建立方法研究  

A Method of Film Digitization and Defect Information Database Establishment on Ray Digital Detection

作　　者：王鹏[1] 杜卫东 汪立新 张峰 宋明大 王泽民[1] 吕志刚[1] 

机构地区：[1]西安工业大学电子信息工程学院,西安710032 [2]山东省特种设备检验研究院,济南250101

出　　处：《科学技术与工程》2012年第26期6644-6647,6656,共5页Science Technology and Engineering

基　　金：陕西省教育厅专项科研计划资助项目(11JK0921);山东省科技厅科技发展计划项目(2010GWZ20402);山东省质检总局科研项目(2009KYZ22);质检工艺性行业科研专项(201010030)资助

摘　　要：在无损检测中,针对压力容器焊缝结构复杂、检测焊缝底片缺陷时定级比较困难,并且底片长期保存和查询存在困难的问题,设计了射线检测底片数字化仪器与底片缺陷信息库系统软件。并根据数字化底片的缺陷的特征,提出了一种基于神经网络的底片焊缝缺陷的识别方法。并建立了缺陷信息库。试验结果表明该仪器能够快速实现底片的数字化,并对底片中的焊缝缺陷定位识别率达到90%以上,提高了射线检测的效率。In nondestructive testing, a film digitizer for ray detection and software of film detect information da- tabase system is designed. For the complex structure of pressure vessel weld, the difficult to rate the weld film de- fects and the difficulties of long-term preservation and query. According to the characteristics of digital film defects, a film weld defect recognition method is put forward based on neural networks and establish defect information data- base. The results show that the instrument can quickly achieve the digitization of the film, and the recognition rate of the weld defect location is more than 90%, thus improve the efficiency of the ray detection.

关 键 词：底片数字化 焊缝缺陷 缺陷信息库 缺陷识别 

分 类 号：TP336[自动化与计算机技术—计算机系统结构]