2D Profile Reconstruction of Defect in Pipe Ultrasonic Guided Wave Based on LS-SVM with Improved PSO Algorithms
-
摘要: 针对目前超声导波管道检测中缺陷成像研究较少现状,提出了一种基于改进PSO算法的LSSVM的缺陷二维轮廓重构方法。利用试验和有限元软件,获得不同尺度缺陷的回波信号。采用最小二乘网络学习方法,以回波信号数据为输入,二维轮廓数据为输出,建立非线性映射,实现了管道缺陷轴向宽度和径向深度的二维轮廓重构,并与径向基神经网络算法重构结果和一般PSO算法的LS-SVM算法进程进行对比。结果表明:该方法具有更强的泛化能力,是缺陷可视化检测的参考方法。Abstract: According to the situation that the lack of research on ultrasonic guided wave pipe profile reconstruction of defect,a defect profile reconstruction method is proposed based on least square support vector machine(LSSVM) with improved particle swarm optimization(PSO) algorithms. The echo signals of defects with different sizes are obtained experimentally and by using ANSYS software. By using the echo signal data as input and the two dimensional(2D) profile reconstruction data as output,the nonlinear mapping is established to. achieve the 2D profile reconstruction of pipe defect with axial width and radial depth. The reconstructed profile is compared with those obtained by the radial basis function neural network method and LS-SVM method with general PSO algorithm.The experimental results show that the present method has stronger generalization ability and can be used as a reference method for visualized defect detection.
-
Key words:
- computer software /
- defects /
- experiments
-
[1] 周正干,冯海伟. 超声导波检测技术的研究进展[J].无损检测,2006,28(2):57-63Zhou Z G,Feng H W. Progress in research of ultrasonicguided wave testing technique [J]. Chinese Journal ofNondestructive Testing,2006,28(2):57-63 (in Chinese) [2] Li L T,He C F,Wu B,et al. Inspection of hollowsucker rod by using guided wave [C]//Proceedings ofthe Biennial International Pipeline Conference,NewYork: American Society of Mechanical Engineers,2004:1053-1056 [3] Takahiro H,Murase M. Defect imaging with guidedwaves in a pipe[J]. Journal of the Acoustical Society ofAmerica,2005,117(4):2134-2140 [4] 吴斌,邓菲,何存富,等. 基于导波理论的管道缺陷成像研究[J]. 数据采集与处理,2006,21(3):345-349Wu B,Deng F,He C F,et al. Defect pipe imaging basedon guided wave technique[J]. Journal of Data Acquisition& Processing,2006,21(3):345-349 (in Chinese) [5] 纪凤珠,王长龙,梁四祥,等. 基于 LS-SVM 的管道二维漏磁缺陷重构[J]. 西南石油大学学报,2007,29(5):134-136Ji F Z,Wang C L,Liang S X,et al. 2D defectreconstruction of pipeline form magnetic flux leakagesignals based on LS-SVM [J]. Journal of SouthwestPetroleum University,2007,29(5):134-136 (in Chinese) [6] 胡良谋,曹克强,苏新兵,等. 基于加权 LS-SVM 的非线性系统内模控制研究[J]. 机械科学与技术,2012,31(1):101-L M,Cao K Q,Su X B,et al. Research on internalmodel control for nonlinear system based on weightedLS-SVM [J]. Mechanical Science and Technology forAerospace Engineering,2012,31 (1 ): 101-106 (in Chinese) [7] 张轩硕,王建斌,王军阵,等. 基于 LS-SVM 的超声导波管道缺陷二维重构[J]. 西安石油大学学报,2012,27(1):87-90Zhang X S,Wang J B,Wang J Z,et al. 2D profilereconstruction of defect in pipe ultrasonic guided wavebased on LS-SVM [J]. Journal of Xi' an ShiyouUniversity,2012,27(1):87-90 (in Chinese) [8] Cau F,Fanni A,Montisci P,et al. Artificial neuralnetworks for Non-destructive evaluation with ultrasonicwaves in not accessible pipes [C]// Proceedings ofIndustry Applications Conference,2005 [9] 王秀彦,孙雅欣,刘增华,等. ANSYS 二次开发技术在弯管缺陷超声导波检测数值模拟中的应用[J]. 无损检测,2006,28(8):413-X Y,Sun Y X,Liu Z H,et al. Application ofsecond development based on ansys software on simulationof detection defect in curved pipes using ultrasonic guidedwaves [J]. Chinese Journal of Nondestructive Testing,2006,28(8):413-415 (in Chinese) [10] 王建斌,张轩硕,刘兵,等. 基于 SOPC 的管道超声导波检测系统设计[J]. 仪表技术与传感器,2012,(8):53-55Wang J B,Zhang X S,Liu B,et al. Design of ultrasonicguided wave test system for pipeline based on sopc [J].Instrument Technique and Sensor,2012,(8):53-55 (in Chinese) [11] 王军阵,王建斌,张轩硕. 超声导波管道缺陷检测的小波阈值去噪法[J]. 国外电子测量技术,2010,29(8):33-35Wang J Z,Wang J B,Zhang X S. Ultrasonic guided wavepipeline defect detection using wavelet threshold selectionmethod analysis [J]. Foreign Electronic MeasurementTechnology,2010,29(8):33-35 (in Chinese)
点击查看大图
计量
- 文章访问数: 173
- HTML全文浏览量: 27
- PDF下载量: 1
- 被引次数: 0