基于卷积神经网络的石英纤维复合材料损伤缺陷太赫兹智能识别  

Intelligent identification of damage defects in quartz fiber compositesusing terahertz technique based on convolutional neural network

作　　者：李涛 薛刚 霍自祥 王保民 李晓岭 杨召南 LI Tao;XUE Gang;HUO Zixiang;WANG Baomin;LI Xiaoling;YANG Zhaonan(Department of Software,Handan University,Handan 056005,China;Department of Computer,Handan Vocational College of Science and Technology,Handan 056046,China)

机构地区：[1]邯郸学院软件学院,河北邯郸056005 [2]邯郸科技职业学院计算机系,河北邯郸056046

出　　处：《河北大学学报（自然科学版）》2022年第6期665-672,共8页Journal of Hebei University(Natural Science Edition)

基　　金：邯郸市科学技术与发展计划项目(21422031026)。

摘　　要：利用太赫兹时域光谱对石英纤维复合材料(quartz fiber reinforced polymer,QFRP)内部分层缺陷进行检测,通过搭建一维卷积神经网络模型,实现不同位置和不同深度损伤缺陷的准确识别,验证结果准确率在90%以上.根据识别结果构建复合材料的缺陷检测图像与实际太赫兹成像图结果一致,且具有高清晰度和对比度.太赫兹技术结合卷积神经网络能够实现非极性材料的智能识别.In this paper,terahertz time-domain spectroscopy was used to detect the delamination defects in quartz fiber reinforced polymer(QFRP),and a one-dimensional convolutional neural network was built to realize the accurate identification of damage defects at different positions and depths,and the accuracy of the verification results was more than 90%.The defect detection image of the composite constructed according to the recognition results has high definition and contrast,which was consistent with the actual terahertz image.Terahertz technology combined with convolutional neural network can realize the intelligent recognition of non-polar materials.

关 键 词：太赫兹时域光谱 石英纤维复合材料 分层缺陷 智能识别 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术] V19[自动化与计算机技术—计算机科学与技术]