基于支持向量机的焊缝超声TOFD缺陷分类识别

详细信息    查看全文 | 推荐本文 |

英文篇名：Classification and Recognition of Weld Defects by Ultrasonic TOFD Based on Support Vector Machine 作者：伏喜斌 英文作者：FU Xibin;Xiamen Special Equipment Inspection Institute;School of Mechanical Engineering and Automation,Fuzhou University; 关键词：超声TOFD ; 焊缝缺陷 ; 支持向量机 ; 分类识别 英文关键词：ultrasonic TOFD;;weld defect;;support vector machine;;classification and recognition 中文刊名：WSJC 英文刊名：Nondestructive Testing 机构：厦门市特种设备检验检测院;福州大学机械工程及自动化学院; 出版日期：2018-06-10 出版单位：无损检测 年：2018 期：v.40;No.399 基金：福建省自然科学基金项目(2015J01234) 语种：中文; 页：WSJC201806015 页数：6 CN：06 ISSN：31-1335/TG 分类号：58-63

摘要

为了实现对大型厚壁压力容器焊缝缺陷的准确识别,提高缺陷评定的准确性和检测效率,在基于标记的改进分水岭TOFD检测图像分割的基础上,结合典型缺陷图像的纹理特征,从图像空间域和频域特征,分别利用局部相位量化和局部二值模式获取缺陷区域的局部邻域特征参数,将二者特征参数进行归一化融合,再将融合特征向量用支持向量机进行分类识别。试验结果表明,检测图像4×4分块后提取的熔合特征识别率最优,分类识别正确率达到87.10%。
        In order to realize the accurate identification of weld defects in large-scale thick-walled pressure vessels and to improve the accuracy of defect evaluation and detection efficiency,based on the mark-based improved watershed time flight of diffraction(TOFD)image segmentation and combined with the texture features of typical defect images,local phase quantization and local binary patterns are used respectively from the image spatial domain and frequency domain characteristics.The localized two value model can provide the local neighborhood characteristic parameters of the defect region,and through the normalization and fusion of the two feature parameters,the fusion feature vector is then classified by the support vector machine.The experimental results show that the fusion feature recognition rate proposed after detecting the 4 and 4 block of the image is the best,and the classification recognition accuracy rate reaches 87.1%.

引文

[1]林尚扬,于丹,于静伟.压力容器焊接新技术及其应用[J].压力容器,2009,26(11):1-6.
    [2]MERAZI-MEKSEN T,BOUDRAA M,BOUDRAA B.Mathematicalmorphology for TOFD image analysis and automatic crack detection[J].Ultrasonics,2014,54(6):1642-1648.
    [3]BASKARAN G,RAO C L,BALASUBRAMANIAM K.Simulation of the TOFD technique using the finite element method[J].Or Insight,2007,49(11):641-646.
    [4]BOHCIK M,MICIAN M,KONR R,et al.Ultrasonic testing of butt weld joint by TOFD technique[J].Manufacturing Technology,2017,17(6):842-847.
    [5]HABIBPOUR-LEDARI A,HONARVAR F.Three dimensional characterization of defects by ultrasonic time-of-flight diffraction(TOFD)technique[J].Journal of Nondestructive Evaluation,2018,37(1):14.
    [6]宋克臣,颜云辉,陈文辉,等.局部二值模式方法研究与展望[J].自动化学报,2013,39(6):730-744.
    [7]李岚,师飞龙,徐楠楠.自适应加权局部相位量化的人脸识别[J].光电工程,2012,39(12):138-142.
    [8]丁世飞,齐丙娟,谭红艳.支持向量机理论与算法研究综述[J].电子科技大学学报,2011,40(1):2-10.