华南理工大学学报(自然科学版) ›› 2019, Vol. 47 ›› Issue (3): 70-77.doi: 10.12141/j.issn.1000-565X.180383

• 机械工程 • 上一篇    下一篇

大型钢结构无损云检测的可信度融合评估

洪晓斌1 子文江1 余蓉1 罗宗强1† 何振威2    

  1. 1. 华南理工大学 机械与汽车工程学院,广东 广州 510640;
    2. 深圳中集智能科技有限公司,广东 深圳 518035
  • 收稿日期:2018-07-26 修回日期:2018-11-22 出版日期:2019-03-25 发布日期:2019-01-31
  • 通信作者: 罗宗强( 1966-) ,男,博士,教授级高工,主要从事高性能金属材料研究与检测、加工研究 E-mail:mezqluo@scut.edu.cn
  • 作者简介:洪晓斌( 1979-) ,男,博士,教授,博士生导师,主要从事无损检测技术与装备、无人智能测控技术及应用研究
  • 基金资助:
    广东省重大科技专项项目( 2017B030305001) ; 广州市科技计划项目( 201704020052,201802020021) ; 国家质量 监督检验检疫总局科技计划项目( 2017QK064)

Fusion Assessment on the Credibility of Cloud Nondestructive Testing for Large-Scale Steel Structures

 HONG Xiaobin1 ZI Wenjiang1 YU Rong1 LUO Zongqiang1 HE Zhenwei 2   

  1.  1. School of Mechanical and Automotive Engineering,South China University of Technology,Guangzhou 510640, Guangdong,China; 2. Shenzhen CIMC Intelligent Technology Co. ,Ltd. ,Shenzhen 518035,Guangdong,China
  • Received:2018-07-26 Revised:2018-11-22 Online:2019-03-25 Published:2019-01-31
  • Contact: 罗宗强( 1966-) ,男,博士,教授级高工,主要从事高性能金属材料研究与检测、加工研究 E-mail:mezqluo@scut.edu.cn
  • About author:洪晓斌( 1979-) ,男,博士,教授,博士生导师,主要从事无损检测技术与装备、无人智能测控技术及应用研究
  • Supported by:
    Supported by the Major Science and Technology Project of Guangdong Province( 2017B030305001) 

摘要: 针对大型钢结构采用单一无损检测方法经常难以实现被检测对象的完整准确评 估问题,利用多种无损检测方法进行综合检测是有效手段,其中综合检测结果可信度评定 是关键. 首先,设计基于 Hadoop 的大型钢结构无损云检测系统架构,分析大型钢结构无损 云检测 Hadoop 架构的信息流; 接着定义大型钢结构无损云检测数据可信度融合的 D-S 证 据理论联合算子,提出基于 D-S 证据理论的多源数据可信度 MapReduce 融合算法; 最后, 建立大型钢管塔结构检测实验平台,对可视化内窥检测、涡流检测和超声波检测等多源数 据可信度进行了融合评估实验. 结果表明,云检测数据可信度 MapReduce 融合算法有效 提高了各个单一检测手段的缺陷检出率,可满足大型钢结构无损云检测的实际需求.

关键词: Hadoop, D-S 证据理论, MapReduce, 大型钢结构

Abstract: For the problem that single testing method is difficult to achieve comprehensive assessment of the object,the comprehensive testing using a variety of nondestructive testing methods is suggested to be effective,in which the credibility assessment of comprehensive test results is critical. In the investigation,firstly,the cloud nondestructive testing system architecture for large-scale steel structures was designed based on Hadoop,and the information flow of large-scale steel structures cloud nondestructive testing Hadoop architecture was analyzed. Then,the D-S evidence theory joint operator of credibility fusion of large-scale steel structures cloud nondestructive testing data was defined,and the multi-source data credibility MapReduce fusion algorithm based on D-S evidence theory was proposed. Finally,a large steel tube tower structure testing experimental platform was established,and the credibility of visual endoscopic inspection,eddy current testing and conventional ultrasonic inspection multisource data was tested by fusion evaluation. The results show that the detection rate of defects in each single testing method is improved by the MapReduce fusion algorithm for the credibility of cloud testing data. It meets the cloud nondestructive testing requirements of large-scale steel structures

Key words: Hadoop, D-S evidence theory, MapReduce, large-scale steel structure

中图分类号: