高级检索

基于LBP-KPCA特征提取的焊缝超声检测缺陷分类方法

胡宏伟, 张婕, 彭刚, 易可夫, 王磊

胡宏伟, 张婕, 彭刚, 易可夫, 王磊. 基于LBP-KPCA特征提取的焊缝超声检测缺陷分类方法[J]. 焊接学报, 2019, 40(6): 34-39. DOI: 10.12073/j.hjxb.2019400151
引用本文: 胡宏伟, 张婕, 彭刚, 易可夫, 王磊. 基于LBP-KPCA特征提取的焊缝超声检测缺陷分类方法[J]. 焊接学报, 2019, 40(6): 34-39. DOI: 10.12073/j.hjxb.2019400151
HU Hongwei, ZHANG Jie, PENG Gang, YI Kefu, WANG Lei. Defect classification for ultrasonic inspection in weld seam based on LBP-KPCA feature extraction[J]. TRANSACTIONS OF THE CHINA WELDING INSTITUTION, 2019, 40(6): 34-39. DOI: 10.12073/j.hjxb.2019400151
Citation: HU Hongwei, ZHANG Jie, PENG Gang, YI Kefu, WANG Lei. Defect classification for ultrasonic inspection in weld seam based on LBP-KPCA feature extraction[J]. TRANSACTIONS OF THE CHINA WELDING INSTITUTION, 2019, 40(6): 34-39. DOI: 10.12073/j.hjxb.2019400151

基于LBP-KPCA特征提取的焊缝超声检测缺陷分类方法

基金项目: 国家自然科学基金资助项目(51205031);湖南省自然科学基金资助项目(2018JJ2430)

Defect classification for ultrasonic inspection in weld seam based on LBP-KPCA feature extraction

  • 摘要: 焊缝缺陷影响结构安全,缺陷定性是实现结构安全评价的重要基础.研究了一种基于一维局部二元模式(one-dimensional local binary pattern,1-D LBP)算法结合核主成分分析(kernel principal component analysis,KPCA)提取焊缝缺陷回波信号特征的方法.采用1-D LBP算法提取缺陷回波信号的LBP特征,通过KPCA对此LBP特征集进行主成分分析,选取贡献率之和超过90%的前N个主成分作为缺陷分类的特征向量,利用基于径向基核函数的支持向量机(support vector machine,SVM)实现了缺陷类型的自动分类.以夹渣、气孔和未焊透三类焊缝缺陷为对象,开展了缺陷特征提取及分类试验.结果表明,使用LBP-KPCA特征进行缺陷分类时,准确率达到96.7%,优于常规特征,为焊缝缺陷分类及无损评价提供了重要参考.
    Abstract: Weld defects affect the structural safety and the defect classification is important for structural safety evaluation. This paper proposes a method which combines one-dimensional local binary pattern (1-D LBP) algorithm and kernel principal component analysis (KPCA) to extract the characteristics of weld defect echo signal. The 1-D LBP algorithm is used to extract the LBP features of the defect echo signal, and the principal component analysis of the LBP features set is carried out by KPCA. The top N principal components with the contribution rate of more than 90% are selected as the feature vectors for defect classification. The automatic classification of defect types is realized by support vector machine (SVM) based on radial basis function. The experiments of defect features extraction and classification were carried out with the weld defects of slag, porosity and non-penetration. The results show that the accuracy of defect classification is 96.7% when the LBP-KPCA features are used, which is superior to the conventional features. The proposed method provides an important reference for defect classification and nondestructive evaluation of weld defects.
  • [1] Murugan R, Venugobal P R, Thyla P R, et al. Studies on the effect of weld defect on the fatigue behavior of welded structures[J]. China Welding, 2018, 27(1):53-59.
    [2] Mu W, Gao J, Jiang H, et al. Automatic classification approach to weld defects based on PCA and SVM[J]. Insight-Non-Destructive Testing and Condition Monitoring, 2013, 55(10):535-539.
    [3] 胡文刚,刚铁.基于多探头源数据融合的焊缝缺陷识别[J].焊接学报, 2013, 34(3):45-48 Hu Wengang, Gang Tie. Recognition of weld defects based on multi-probe source data fusion[J]. Transactions of the China welding Institution, 2013, 34(3):45-48
    [4] Chen Y, Ma H W, Zhang G M. A support vector machine approach for classification of welding defects from ultrasonic signals[J]. Nondestructive Testing and Evaluation, 2014, 29(3):243-254.
    [5] Gang T, Takahashi Y, Wu L. Intelligent pattern recognition and diagnosis of ultrasonic inspection of welding defects based on neural network and information fusion[J]. Science and Technology of Welding and Joining, 2002, 7(5):314-320.
    [6] Drai R, Khelil M, Benchaala A. Time frequency and wavelet transform applied to selected problems in ultrasonics NDE[J]. NDT&E International, 2002, 35(8):567-572.
    [7] Qu Z, Chong A Y B, Chacon J L F, et al. Study on the laser-based weld surface flaw identification system employing wavelet analysis methodology[J]. Research in Nondestructive Evaluation, 2016, 27(3):137-154.
    [8] Movafeghi A. Using empirical mode decomposition and a fuzzy algorithm for the analysis of weld defect images[J]. Insight-Non-Destructive Testing and Condition Monitoring, 2015, 57(1):35-39.
    [9] Cruz F C, Simas Filho E F, Albuquerque M C S, et al. Efficient feature selection for neural network based detection of flaws in steel welded joints using ultrasound testing[J]. Ultrasonics, 2017, 73:1-8.
    [10] Ojala T, Pietikäinen M, Mäenpää T. Multiresolution gray-scale and rotation invariant texture classification with local binary patterns[J]. IEEE Transactions on Pattern Analysis&Machine Intelligence, 2002(7):971-987.
    [11] Shahriar M R, Ahsan T, Chong U P. Fault diagnosis of induction motors utilizing local binary pattern-based texture analysis[J]. Eurasip Journal on Image and Video Processing, 2013(1):29-39.
    [12] Chatlani N, Soraghan J J. Local binary patterns for 1-D signal processing[C]//201018th European Signal Processing Conference. IEEE, 2010:95-99.
    [13] Huang Y C, Lin C K. Method for displaying words and processing device and computer program product thereof:US 8935165B2[P]. 2015-01-13.
    [14] Kaya Y, Uyar M, Tekin R, et al. 1D-local binary pattern based feature extraction for classification of epileptic EEG signals[J]. Applied Mathematics and Computation, 2014, 243:209-219.
    [15] Hoshyar O, Monhammad S, Habibollah D, et al. A novel method for classification of power quality disturbances based on a new one dimensional local binary pattern approach[C]//2017 IEEE 8th Control and System Graduate Research Colloquium (ICSGRC), Malaysia:IEEE, 2017:225-229.
    [16] McCool P, Chatlani N, Petropoulakis L, et al. 1-D local binary patterns for onset detection of myoelectric signals[C]//2012 IEEE European Signal Processing Conference. Strathclyde, UK:IEEE, 2012:499-503.
    [17] 马再超,赵荣珍,杨文瑛.转子故障特征数据分类的KPCA-BFDA方法[J].振动.测试与诊断, 2013, 33(2):192-198 Ma Zaichao, Zhao Rongzhen, Yang Wenying. KPCA-BFDA for the classification of rotor fault feature data[J]. Journal of Vibration, Measurement&Diagnosis, 2013, 33(2):192-198
    [18] Vapnik V. The nature of statistical learning theory[M]. New York:Springer, 2013.
    [19] Phienthrakul T, Kijsirikul B. Evolutionary strategies for hyperparameters of support vector machines based on multi-scale radial basis function kernels[J]. Soft Computing, 2010, 14(7):681-699.
    [20] Abe S. Support vector machines for pattern classification[M]. London:Springer, 2010.
    [21] Masnata A, Sunseri M. Neural network classification of flaws detected by ultrasonic means[J]. NDT&E International, 1996, 29(2):87-93.
    [22] Tsui P P C, Basir O A. Wavelet basis selection and feature extraction for shift invariant ultrasound foreign body classification[J]. Ultrasonics, 2006, 45(1-4):1-14.
    [23] Liu Z, Xu H. Kernel parameter selection for support vector machine classification[J]. Journal of Algorithms&Computational Technology, 2014, 8(2):163-177.
  • 期刊类型引用(6)

    1. 徐东辉,孟范鹏,孙鹏,郑旭宸,程永超,马志,陈树君. 基于深度学习的GMAW焊接缺陷在线监测. 焊接学报. 2024(03): 114-119+135-136 . 本站查看
    2. 李春凯,王嘉昕,石玗,代悦. GTAW熔池激光条纹动态行为与熔透预测方法研究. 机械工程学报. 2024(06): 236-244 . 百度学术
    3. 朱珍文,张刚,朱明,李春凯,石玗. LNG储罐内罐立缝智能化焊接技术研究思路. 电焊机. 2023(09): 22-28+36 . 百度学术
    4. 任乐,张爱华,常东东,何倩玉,马晶. 基于电弧声的超窄间隙焊接熔合状态识别. 电焊机. 2021(07): 11-16+23+113-114 . 百度学术
    5. 王佳杰,王伟,杜星炜,杨武丙,许建平. 具有自动送丝功能的高效焊接电烙铁设计. 机械制造文摘(焊接分册). 2020(02): 17-21 . 百度学术
    6. 顾玉芬,席保龙,李春凯,石玗,代悦,丁彬. 基于熔池振荡的GTAW熔透实时传感与控制. 电焊机. 2020(12): 5-8+108 . 百度学术

    其他类型引用(11)

计量
  • 文章访问数:  400
  • HTML全文浏览量:  34
  • PDF下载量:  85
  • 被引次数: 17
出版历程
  • 收稿日期:  2018-08-07

目录

    /

    返回文章
    返回