制管企业质证书识别新技术探索研究  

Research on New Technologies of Quality Certificates Identification forSteel Pipe Enterprises

作　　者：杜强娜 曹宇航 贾云峰 DU Qiangna;CAO Yuhang;JIA Yunfeng(Zhongyou BSS(Qinhuangdao)Petropipe Co.,Ltd.,Qinhuangdao 066206,Hebei China;CNPC Baoji Petroleum Pipe Industry Co.,Ltd.,Baoji 721008,Shaanxi,China;Chinese National Engineering Research Center for Petroleum and Natural Gas Tubular Goods Co.,Ltd.,Xi'an 710018,China)

机构地区：[1]中油宝世顺(秦皇岛)钢管有限公司,河北秦皇岛066206 [2]中国石油集团宝石管业有限公司,陕西宝鸡721008 [3]中油国家石油天然气管材工程技术研究中心有限公司,西安710018

出　　处：《焊管》2024年第11期64-68,共5页Welded Pipe and Tube

摘　　要：数字化是智能制造钢管企业中的一个重要方面,智能识别系统更是企业智能化发展的关键环节。针对当前传统OCR (optical character recognition)技术在处理证书类图片时存在的准确性不高、处理效率低等问题,开发了一种基于标签式人工智能识别质证书的方法,并总结了一套适合钢管企业质证书识别的标准流程。结果表明,经过图像采集及预处理、AI数据识别、识别数据后处理等步骤后,可将质证书图像文档转化为结构化数据,有效地提高了质证书管理效率。Digitalization is an important aspect of intelligent manufacturing for steel pipe enterprises,and intelligent identification system is a key link in the intelligent development of enterprises.In view of the low accuracy and low efficiency of traditional OCR technology in processing certificate type image,a method of quality certificate recognition based on label artificial intelligence is developed,and a set of standard process for quality certificate recognition for steel pipe enterprises is summarized.The results show that after image acquisition and preprocessing,AI data recognition and post⁃processing of recognition data,the image documents of quality certificate can be transformed into structured data,which effectively improves the efficiency of quality certificate management.

关 键 词：数字化转型 制管企业 质证书 OCR 标签 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]