Automatic identification of flaws is very important for ultrasonic nondestructive testing and evaluation of large shaft.A novel automatic defect identification system is presented.Wavelet packet analysis(WPA)was appli...Automatic identification of flaws is very important for ultrasonic nondestructive testing and evaluation of large shaft.A novel automatic defect identification system is presented.Wavelet packet analysis(WPA)was applied to feature extraction of ultrasonic signal,and optimal Support vector machine(SVM)was used to perform the identification task.Meanwhile,comparative study on convergent velocity and classified effect was done among SVM and several improved BP network models.To validate the method,some experiments were performed and the results show that the proposed system has very high identification performance for large shafts and the optimal SVM processes better classification performance and spreading potential than BP manual neural network under small study sample condition.展开更多
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...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.展开更多
基金Supported by the Research Program of International Technology Collaboration and Communication of Sichuan(2007H12-017)
文摘Automatic identification of flaws is very important for ultrasonic nondestructive testing and evaluation of large shaft.A novel automatic defect identification system is presented.Wavelet packet analysis(WPA)was applied to feature extraction of ultrasonic signal,and optimal Support vector machine(SVM)was used to perform the identification task.Meanwhile,comparative study on convergent velocity and classified effect was done among SVM and several improved BP network models.To validate the method,some experiments were performed and the results show that the proposed system has very high identification performance for large shafts and the optimal SVM processes better classification performance and spreading potential than BP manual neural network under small study sample condition.
