检索规则说明:AND代表“并且”;OR代表“或者”;NOT代表“不包含”;(注意必须大写,运算符两边需空一格)
检 索 范 例 :范例一: (K=图书馆学 OR K=情报学) AND A=范并思 范例二:J=计算机应用与软件 AND (U=C++ OR U=Basic) NOT M=Visual
作 者:张晓龙[1] 程晓颖 ZHANG Xiaolong;CHENG Xiaoying(School of Mechanical Engineering,Zhejiang Sci-Tech University,Hangzhou 310018,China)
出 处:《自动化与仪表》2024年第10期91-95,共5页Automation & Instrumentation
摘 要:碳纤维复合材料在生产使用过程中,损伤检测一直是关注的一大焦点。锁相热成像检测和超声波C扫描检测是两种常用的检测方式,但各自存在着局限性。超声波C扫描适用于材料内部深层损伤的检测而对浅层损伤信息不敏感,锁相热成像适用于浅层损伤信息的检测,难以反映材料深层次的损伤。针对此问题,该文提出一种基于非下采样剪切波变换结合脉冲耦合神经网络图像融合的算法,将锁相热像图和超声C扫描图像进行图像融合。结果表明,融合图像可以显著提高图像的清晰度和感知质量,并且将损伤面积的误差从39.1%降低到23.8%。Damage detection has been a major focus of attention during the production and use of carbon fiber reinforced plastic.Lock-in thermography and ultrasonic C-scan are two commonly used detection methods,but each has its own limitations.Ultrasonic C-scan is suitable for the detection of deep damage within the material and is not sensitive to shallow damage information,while lock-in thermography is suitable for the detection of shallow damage information,which is difficult to reflect the deep damage of the material.To address this problem,this paper proposes an image fusion algorithm based on non-subsampled shear wave transform combined with pulse-coupled neural network to fuse lock-in thermography and ultrasonic C-scan images.The results show that the fused image can significantly improve the clarity and perceptual quality of the image,and reduce the error of damage area from 39.1%to 23.8%.
关 键 词:锁相热成像 超声波C扫描 图像融合 非下采样剪切波变换 碳纤维复合材料 脉冲耦合神经网络
分 类 号:TP399[自动化与计算机技术—计算机应用技术]
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在链接到云南高校图书馆文献保障联盟下载...
云南高校图书馆联盟文献共享服务平台 版权所有©
您的IP:216.73.216.26