基于改进PSO-LSSVM的脉冲涡流缺陷二维轮廓重构

英文篇名：2D Profiled Reconstruction for PEC Defect Based on Improved Particle Swarm Optimization and Least Squares Support Vector Machine
中文刊名：仪表技术与传感器
英文刊名：Instrument Technique and Sensor
作者：钱苏敏 ; 左宪章 ; 张云 ; 常东
英文作者：QIAN Su-min ; ZUO Xian-zhang ; ZHANG Yun ; CHANG Dong (Department of UAV Engineering ; Ordnance Engineering College ; Shijiazhuang 050003 ; China)
中文关键词：二维轮廓重构 ; 粒子群优化 ; 混沌序列 ; 最小二乘支持向量机
英文关键词：2D profiled reconstruction ; particle swarm optimization ; chaotic sequences ; least squares support vector machine
出版日期：2013-08-15
机构：军械工程学院无人机工程系;
年：2013
期：08
出版单位：仪表技术与传感器

摘要

基于最小二乘支持向量机(LSSVM)对脉冲涡流信号构建了缺陷二维轮廓重构模型。以脉冲涡流信号的垂直分量By的正峰值包络作为LSSVM重构模型的输入,缺陷的二维轮廓作为输出,对LSSVM进行网络训练。同时,利用改进的粒子群算法优化模型参数,提出模型泛化能力的评估方法。通过比较基本粒子群算法及改进的粒子群算法的LSSVM模型的重构结果,验证了改进粒子群算法的LSSVM重构模型的有效性。
The 2D profiled reconstruction model was constructed for pulsed eddy current flaw signals with least squares support vector machine(LSSVM).Take the positive peak envelope of the component By as the input of LSSVM with the method of magnetic flux density with PEC signals and 2D profile of defects as output and train for LSSVM network.The paper used improved particle swarm optimization to optimize the model parameters,and presented the assessment methods to model generalization capability.Comparing the reconstructed results of LSSVM model which uses either particle optimization swarm algorithm or improved particle swarm optimization algorithm,it improves the effectiveness of the LSSVM reconstruction model which uses improved particle swarm optimization algorithm.

引文

[1]HUANG C,WU X J,XU Z Y,et al.Pulsed eddy current signal pro-cessing method for signal denoising in ferromagnetic plate testing.NDT&E International,2010,43:648-653.
    [2]HUANG C,WU X J,XU Z Y,et al.Ferromagnetic material pulsed ed-dy current testing signal modeling by equivalent multiple-coil-couplingapproach.NDT&E International,2011,44:163-168.
    [3]杨宾峰,罗飞璐.脉冲涡流无损检测技术应用研究.仪表技术与传感器,2004(8):45-46.
    [4]杨理践,裴磊,杨继华.钢板脉冲涡流检测方法.仪表技术与传感器,2011(7):87-90.
    [5]JI F Z,WANG C L,ZUO X Z,et al.LS-SVM based reconstruction of3-D defect profile from magnetic flux leakage signals.Insight,2007,49(9):516-520.
    [6]纪凤珠,王长龙,梁四洋,等.基于LS-SVM的管道二维漏磁缺陷重构.西南石油大学学报,2007,29(5):134-136.
    [7]KENNEDY J,EBERHART R C.Particle swarm optimization.Proceedingsof the IEEE Conference on Neural Networks,Perth,Australia,1995.
    [8]MYERS C,RABINER L R,ROSENBERG A E.Performance tradeoffsin dynamic time warping algorithms for isolated word recognition.IEEETransactions on Acoustics,Speech and Signal Processing,1980,28(6):623-635.
    [9]SHI Y,EBERHART R C.A modified particle swarm optimizer.Pro-ceedings of the IEEE International Conference on Evolutionary Com-putaion,Washington,1998.
    [10]莫愿斌,陈德钊,胡上序.混沌粒子群算法及其在生化过程动态优化中的应用.化工学报,2006,57(9):2123-2127.
    [11]李海龙,张美琦,刘兰冬,等.一种求解非线性方程组的简化混沌算法.高校理科研究,2010(26):105-106.
    [12]朱童,李小凡,李一琼,等.基于改进粒子群算法的地震标量波方程反演.地球物理学报,2011,54(11):2951-2959.
    [13]陈刚,闫飞,龚啸,等.基于参数优化的最小二乘支持向量机状态估计方法.电力系统保护与控制,2011,39(19):83-88.