管道裂纹远场涡流检测的定量反演方法研究.pdfVIP

学兔兔 第34卷 第8期 仪 器 仪 表 学 报 Vo1．34 No．8 2013年8月 Chinese Joumal of Scientific Instrument Aug．2013 管道裂纹远场涡流检测的定量反演方法研究水 张 伟，师奕兵，王志刚，敖永才 (电子科技大学自动化工程学院 成都 611731) 摘 要：裂纹缺陷定量反演是管道远场涡流检测中的一个难点问题。首先针对远场涡流检测信号的特点，提出了一种基于最 小均方误差准则的波形逼近技术，用以高精度提取检测信号的波形特征。接着通过建立非线性多项式反演模型、基于一维搜索 寻优的BP神经网络反演模型和基于粒子群搜索寻优的支持向量机反演模型来实现由检测信号波形特征到裂纹缺陷尺寸的定 量反演。仿真结果表明，支持向量机反演模型计算相对误差低于5％，具有较强的抗干扰能力，适合作为裂纹缺陷定量反演的 有力工具。最后，通过实验也验证了这一结果。 关键词：裂纹缺陷；定量反演；波形逼近；粒子群优化；支持向量机 中图分类号：TP391．4 文献标识码：A 国家标准学科分类代码：510．4O Research on the quantitative inverse method of RFEC inspection for pipe cracks Zhang Wei，Shi Yibing，Wang Zhigang，Ao Yongcai (School ofAutomation Engineering，Unive~ity ofElectronic Science and Technology ofChina，Chengdu 611731，China) Abstract：Quantitative inverse of the pipe crack flaw is a difficult problem to be solved in pipe remote field eddy cur— rent(RFEC)inspection．According to the distinctive features of the RFEC detecting signals，a wave—approximating approach based on the minimum mean square error criterion is proposed in this paper，which is used to extract the wave characteristics of the detection signals with hJ gh accuracy．Through establishing the nonlinear polynomial inverse model，the BP neural network inverse model based on one-dimensional optimization and the support vector machine (SVM)inverse model based on particle swarin optimization(PSO)，the quantitative inverse from the wave features of the detecting signals to the crack flaw size is realized．Simulation results show that the SVM inverse model carl achieve a relative error of 5％ ，has strong anti—disturbance capacity，and iS suitable to be an effective tool for the quantitative inverse of the pipeli