Recognition of Weld Defect Types

您当前的位置：

首页 >

文章列表页 >

Recognition of Weld Defect Types

更新时间：2025-07-09

- Recognition of Weld Defect Types
- Vol. 44, Issue 7, Pages: 100-103(2010)
- 作者机构：
  
  西安交通大学机械制造系统工程国家重点实验室,西安,710049
- 作者简介：
- 基金信息：
- DOI：
  CLC： TN911.7
- Online First：10 July 2010，
  
  Published：2010
- 稿件说明：
移动端阅览
Recognition of Weld Defect Types[J]. 2010, 44(7): 100-103.
DOI：

Recognition of Weld Defect Types[J]. 2010, 44(7): 100-103. DOI：

摘要

针对焊缝射线检测图像中缺陷类型识别准确度较低的问题

提出了一种基于直接多类支持向量机的缺陷类型识别方法.该方法将焊缝缺陷类型识别问题转化为一个约束优化问题

采用由缺陷边缘特征和区域特征构成的特征向量对缺陷进行描述

解决了在实际训练样本较少的情况下

提高缺陷类型识别准确度的问题.实验表明

该方法的识别准确度为94.25%

比一对一支持向量机和多层感知神经网络的高

并且通过引入区域特征提高了特征组的缺陷描述能力.

Abstract

To improve the recognition accuracy of weld defects in the radiographic image

a method based on direct multiclass support vector machine(SVM)is proposed to recognize the defect types

where the recognition of weld defects is regarded as a constrained optimization problem

and the edge-based features and region-based features of the weld defect are employed as the feature vector. This method solves the difficulty of achieving higher accuracy under a small training set. The experimental results demonstrate that the recognition accuracy of the method gets 94.25%

higher than that of the one-versus-one SVM and multi-layer perceptron(MLP)neural network

and the introduced region-based features improve the characterization capability of the feature group.

关键词

Keywords

references

LIAO T W. Classification of welding flaw types with fuzzy expert systems [J]. Expert Systems with Applications, 2003,25(1):101-111.

LIM T Y, RATNAM M M, KHALID M A. Automatic classification of weld defects using simulated data and an MLP neural network [J].Insight, 2007,49(3):154-159.

MERY D, DASILVAR R, CALOBAL P, et al. Pattern recognition in the automatic inspection of aluminium castings [J]. Insight, 2003,45(7):475-483.

WANG G, LIAO T W. Automatic identification of different types of welding defects in radiographic images [J]. NDT E International, 2002,35(8):519-528.

ZHANG Xiaoguang, ZHU Zhencai, XU Jihua, et al. The classification algorithm of defects in weld image based on asymmetrical SVM [C]∥International Conference on Control and Automation. Piscataway, NJ, USA: IEEE, 2005:1215-1219.

ZHANG Xiaoguang, XU Jianjian, GE Guangying. Defects recognition on X-ray images for weld inspection using SVM [C]∥Proceedings of 2004 International Conference on Machine Learning and Cybernetics. Piscataway, NJ, USA: IEEE, 2004:3721-3725.

边肇祺, 张学工. 模式识别 [M]. 第2版. 北京: 清华大学出版社, 2000.

SILVA R R, CALA L P, SIQUEIRA M H S, et al. Pattern recognition of weld defects detected by radiographic test [J]. NDT E International, 2004,37(6):461-470.

EFRON B, TIBSHIRANI R J. An introduction to the bootstrap [M].London,UK:Chapman Hall, 1997.

HSU C W, CHANG C C, LIU C J.A practical guide to support vector classification [EB/OL]. [2010-03-20].http:∥www.csie.ntu.edu.tw/～cjlin/liblinear/.

焊缝缺陷的水淹没分割算法.西安交通大学学报, 2010,44(3):90-94.

复杂体制雷达辐射源信号时频原子特征提取方法.西安交通大学学报, 2010,44(4):108-113.

利用小波分解和支持向量机的心理意识真实性识别研究.西安交通大学学报, 2010,44(4):119-124.

一类支持向量机的设备状态自适应报警方法.西安交通大学学报, 2009,43(11):61-65.

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Segmentation of Weld Defects Based on Water-Flooding Principle

Energy Efficiency Optimization of the Cryogenic Air Separation Process for Electronic-Grade Ultra Pure Nitrogen

Numerical Simulation of the Energy Conversion Process in Thermoacoustic Engines with Different Stack Materials

Research on the Electrohydrodynamic Effects of Ionic Liquid-Modified Fuels

Integrated and Joint Design Optimization of Centrifugal Compressor Impeller and Casing Treatment at Multiple Working Points

Related Author

李成

Related Institution

State Key Laboratory for Manufacturing System Engineering, Xi'an Jiao tong University

⁰