| 引用本文: | 艾轶博,王楠,阙红波,杨斌,张卫冬.工业CT的高铁齿轮箱体材料缺陷识别[J].哈尔滨工业大学学报,2015,47(10):45.DOI:10.11918/j.issn.0367-6234.2015.10.010 |
| AI Yibo,WANG Nan,QUE Hongbo,YANG Bin,ZHANG Weidong.Material casting defect recognition of high-speed train gearbox shell based on industrial CT technology[J].Journal of Harbin Institute of Technology,2015,47(10):45.DOI:10.11918/j.issn.0367-6234.2015.10.010 |
|
| 摘要: |
| 高铁齿轮箱是高速列车的重要部件,为保障高铁的安全、稳定运行,需要对高铁齿轮箱箱体出厂及检修时的铸件内部缺陷进行检验,并对箱体内部缺陷实现自动、准确的分类和识别.基于此利用三维工业CT技术,设计实验获取到高铁齿轮箱体材料的4种内部缺陷的三维体数据,根据齿轮箱体内部缺陷的物理背景知识,对三维体数据进行特征提取,设计Adaboost_BTSVM多分类算法,实现基于三维工业CT的箱体材料内部缺陷的自动分类识别,并使重点关注的收缩类缺陷的分类准确率达到85%以上、裂纹类缺陷的分类准确率达到100%,为实现高铁齿轮箱箱体材料的缺陷自动识别提供技术保障. |
| 关键词: 模式分类 支持向量机 三维特征提取 高铁齿轮箱体 铸造缺陷 工业CT |
| DOI：10.11918/j.issn.0367-6234.2015.10.010 |
| 分类号:TP391 |
| 基金项目:国家自然科学基金面上项目(61273205)；教育部中央高校基本科研业务费项目(FRF-SD-12-028A)；高等学校学科创新引智计划(B12012). |
|
| Material casting defect recognition of high-speed train gearbox shell based on industrial CT technology |
|
AI Yibo1, WANG Nan1, QUE Hongbo2, YANG Bin1, ZHANG Weidong1
|
|
(1.National Center for Materials Service Safety China, University of Science and Technology Beijing, 100083 Beijing, China; 2.Qishuyan Institute Co., Ltd., China South Locomotive & Rolling Stock Corporation limited, 213011 Changzhou, Jiangshu, China)
|
| Abstract: |
| High-speed train gearbox shell is an important component of high-speed train. In order to protect the operational safety of high-speed train gearbox shell, it is needed to detect the casting internal defect as product testing and maintenance inspection accurately and rapidly. In this paper, based on three-dimensional CT technology the test was developed to detect the casting defects of high-speed train gearbox shell; through the analysis of three-dimensional data of the four kinds detects, three-dimensional geometric features and characteristic values were obtained, and the Adaboost_BTSVM algorithm were used to achieve the automatic classification of casting defects of high-speed train gearbox shell. The according classification accuracy of shrinkage defects can be 85%, and the classification accuracy of crack defects can stand at 100%. These will provide an available automatic identification method for the defect of high-speed train gearbox shell. |
| Key words: pattern classification support vector machine 3D feature extraction high-speed train gearbox shell casting defects industrial CT technology |
