基于深度学习的列车车轴缺陷超声检测  

Train axle ultrasonic defect detection based on deep learning

作　　者：刘建 罗林[1] 李金龙[1] 高晓蓉[1] 赵波 LIU Jian;LUO Lin;LI Jinlong;GAO Xiaorong;ZHAO Bo(School of Physical Science and Technology,Southwest Jiaotong University,Chengdu 610031,China;Chengdu Lead Science&Technology Co.,Ltd.,Chengdu 610000,China)

机构地区：[1]西南交通大学物理科学与技术学院,成都610031 [2]成都主导科技有限责任公司,成都610000

出　　处：《无损检测》2024年第6期30-35,共6页Nondestructive Testing

摘　　要：针对列车车轴超声检测中缺陷(特别是微小缺陷)检出率和检测效率低的问题,提出了一种基于深度学习的列车车轴缺陷超声检测方法,在YOLO v5s网络的基础上,改进特征提取层结构并加入SE注意力机制,采用实际车轴检测数据、CIVA仿真数据和GAN生成式数据构建了数据集,并进行了验证试验。试验结果表明,通过增加仿真数据和GAN生成式数据样本,所提方法在提高实际车轴超声检测缺陷检出率的同时,可有效检出微小车轴缺陷,其检出率可达99.25%,具有较高的应用价值和前景。Aiming at the low detection rate and slow efficiency of defects(especially minor defects)in train axle ultrasonic detection,a method based on deep learning was proposed.On the basis of YOLO v5s network,the feature extraction layer structure was improved and SE attention mechanism was added.The dataset was constructed using real axle detection data,CIVA simulation data and GAN generated data and validation experiments were conducted.The experimental results showed that by adding simulation data and GAN generated data samples,this proposed method can effectively improve the detection rate of the actual axle ultrasonic detection defects,and the detection rate reached 99.25%,which showed a high application value and prospect.

关 键 词：深度学习 超声检测 车轴缺陷 数据增强 

分 类 号：TG115.28[金属学及工艺—物理冶金]