首页 > 论文 > 应用激光 > 37卷 > 6期(pp:888-892)

激光超声缺陷统计特征神经网络识别技术研究

Neural Network Identification of Defect Statististics Characteristics in Laser Ultrasonics

  • 摘要
  • 论文信息
  • 参考文献
  • 被引情况
  • PDF全文
分享:

摘要

针对激光超声检测过程中, 缺陷的分类、定位及特征难以识别的问题, 根据激光超声遇到不同裂纹呈规律性变化的特点, 采用神经网络对在激光超声检测中出现的缺陷特征进行统计识别。对采集到的激光超声信号归一化和规范化后, 首先计算每个信号的均值、均方根值、峰值、峭度等十个统计特征, 并将这些特征组合成一个等长的特征向量, 然后采用径向基(RBF)神经网络识别。经过计算发现总的识别正确率为95%, 部分类型的缺陷识别可以达到100%, 较低的识别正确率也在80%以上。实验结果表明, 该方法能精确、高效地识别裂纹缺陷且对环境的适应能力比较好, 有助于实现对裂纹的定量检测。

Abstract

In the process of laser ultrasonic inspection, the problems of defect classification, location and characteristics of defects are difficult to be identified. According to the characteristics of laser ultrasound to meet different crack show regular change, the neural network is used to perform statistical identification of the defect characteristics in laser ultrasonic testing. The laser ultrasonic signals were collected after normalization and standardization, it calculated the mean value, root mean square value, peak and kurtosis characteristics of ten, and combined these statistic features into an even-length feature vector, Then by using radial basis (RBF) neural network identification. After calculation, the total recognition accuracy is 95%, some types of defects can reach 100%, and the lower recognition accuracy is more than 80%. The experimental results show that the method can accurately and efficiently identify crack defects and better adaptability to the environment, it is helpful to realize quantitative detection of cracks.

Newport宣传-MKS新实验室计划
补充资料

中图分类号:TN247

DOI:10.14128/j.cnki.al.20173705.

基金项目:教育部博士点基金联合资助项目(项目编号: 2013142012007)

收稿日期:2017-06-22

修改稿日期:2017-08-31

网络出版日期:--

作者单位    点击查看

郭华玲:中北大学计算机与控制工程学院, 山西 太原 030051电子测量技术国家重点实验室, 山西 太原 030051
秦峰:中北大学机电工程学院, 山西 太原 030051
郑宾:中北大学计算机与控制工程学院, 山西 太原 030051电子测量技术国家重点实验室, 山西 太原 030051
王余敬:中北大学机电工程学院, 山西 太原 030051

联系人作者:郭华玲(834086353@qq.com)

备注:郭华玲(1976-), 女, 副教授, 博士, 现主要从事激光超声无损检测技术研究,

【1】MIHARA T, OTSUKA Y, CHO H, et al.Time-of-flight diffraction measurement using laser ultrasound[J].Experimental Mechanics, 2006, 46(5): 561-567.

【2】GE HAO, CAI GUIXI, LIU CHANG, et al.Laser ultrasonic detection of flaw in aluminum plate based on modes identification and separation[J].Applied Acoustics, 2013, 32(5): 341-347.
戈浩, 蔡桂喜, 刘畅, 等.基于模态识别与分离的铝板激光超声检测[J].应用声学, 2013, 32(5): 341-347.

【3】WANG JINGSHI, XU XIAODONG, LIU XIAOJUN, et al.Low pass effect of surface defect metal based on laser ultrasonic[J].Acta Physica Sinica, 2008, 57(12): 7765-7769.
王敬时, 徐晓东, 刘晓峻, 等.利用激光超声技术研究表面微裂纹缺陷材料的低通滤波效应[J].物理学报, 2008, 57(12): 7765-7769.

【4】GUAN JIANFEI, SHEN ZHONGHUA, NI XIAOWU, et al.Numerical study on depth evaluation of micro-surface crack by laser generated ultrasonic waves[J].Journal of Test and Measurement Technology, 2010, 24(1): 15-21.
关建飞, 沈中华, 倪晓武, 等.激光超声探测铝板表面微缺陷深度的数值研究[J].测试技术学报, 2010, 24(1): 15-21.

【5】LUO YUKUN, LUO SHITU, LUO FEILU, et al.Realization and improvement of laser ultrasonic signal denoising based on empirical mode decomposition[J].Optics and Precision Engineering, 2013, 21(2): 479-487.
罗玉昆, 罗诗途, 罗飞路, 等.激光超声信号去噪的经验模态分解实现及改进[J].光学 精密工程, 2013, 21(2): 479-487.

【6】ZHANG CHAO, JI HONGLI, QIU JINHAO, et al.Research on interference energy calculation method in laser ultrasonic technique[J].Acta Optica Sinica, 2014, 34(7): 158-166.
张超, 季宏丽, 裘进浩, 等.激光超声检测中干涉特征提取算法的研究[J].光学学报, 2014, 34(7): 158-166.

【7】WANG YUJING, WU YAOJIN, LIU HUI, et al.Experimental study on depth evaluation of micro-surface crack by laser generated acoustic surface waves[J].Applied Acoustics, 2016, 35(1): 36-41.
王余敬, 吴耀金, 刘辉, 等.声表面波检测铝板表面微缺陷深度实验研究[J].应用声学, 2016, 35(1): 36-41.

【8】DENG CHUNZE, SHAN NING, MA YONGZHONG, et al.Theoretical study on laser ultrasonic automatic test system[J].Laser Journal, 2015, 36(9): 33-36.
邓春泽, 单宁, 马永忠, 等.激光超声自动化检测系统理论研究[J].激光杂志, 2015, 36(9): 33-36.

【9】SU CHUN, HU HONGPING, LIU HUI, et al.Defect detection using laser ultrasound based on Kohonen network[J].Mathematics in Practice and Theory, 2014, 44(23): 185-190.
苏纯, 胡红萍, 刘辉, 等.基于Kohonen网络的激光超声缺陷探测研究[J].数学的实践与认识, 2014, 44(23): 185-190.

【10】KONG YA LIN.Research on fault diagnosis method and application for rolling element bearing based on vibration signal[D].Dalian: Dalian University of Technology, 2006.
孔亚林.基于振动信号的滚动轴承故障诊断方法研究[D].大连: 大连理工大学, 2006.

引用该论文

Guo Hualing,Qin Feng,Zheng Bin,Wang Yujing. Neural Network Identification of Defect Statististics Characteristics in Laser Ultrasonics[J]. APPLIED LASER, 2017, 37(6): 888-892

郭华玲,秦峰,郑宾,王余敬. 激光超声缺陷统计特征神经网络识别技术研究[J]. 应用激光, 2017, 37(6): 888-892

您的浏览器不支持PDF插件,请使用最新的(Chrome/Fire Fox等)浏览器.或者您还可以点击此处下载该论文PDF