火炮摇架焊缝缺陷智能分类  

Intelligent classification of weld defects of artillery cutter

作　　者：刘文婧[1] 张蓉 LIU Wenjing;ZHANG Rong(Mechanical Engineering School,Inner Mongolia University of Science and Technology,Baotou O14010,China)

机构地区：[1]内蒙古科技大学机械工程学院,内蒙古包头014010

出　　处：《内蒙古科技大学学报》2024年第1期66-70,共5页Journal of Inner Mongolia University of Science and Technology

基　　金：国家自然科学基金(52075270);内蒙古自治区自然科学基金(2022MS05006)。

摘　　要：针对火炮摇架结构复杂,焊缝内部缺陷检测效果不理想,选择对非平面物体和复杂结构体均适用的超声相控阵检测技术对摇架焊缝缺陷进行检测。将得到的超声相控阵图谱与ResNeXt网络模型相结合,实现焊缝缺陷的智能分类。将SK卷积单元引入ResNeXt网络模型,对摇架焊缝缺陷进行定性分析。改进后的网络模型比原ResNeXt网络的分类准确率提升5.5%,最终达到98.2%。For the complex structure of the artillery rocker,the detection of internal defects in the weld seam is not ideal.The ultrason-ic phased array detection technology,which is also applicable to non-planar objects and complex structural bodies,was selected for the detection of defects in the weld seam of the rocker.The obtained ultrasonic phased aray mapping was combined with the ResNeXt net-work model to achieve intelligent classification of weld defects.SK convolutional units were also introduced into the ResNeXt network model for the qualitative analysis of rocker weld defects.The improved network model shows 5.5%improvement in classification accu-racy compared to the original ResNeXt network,eventually reaching 98.2%.

关 键 词：火炮摇架 焊缝缺陷 超声相控阵检测技术 卷积神经网络 智能分类 

分 类 号：TH17[机械工程—机械制造及自动化]