摘要
基于计算机视觉的图像识别和处理技术迅速发展,因此,X射线焊缝图像智能化评片已成为无损X射线检测的研究热点之一。快速准确识别焊缝内部小目标缺陷是智能评片的一个难点,鉴于此,本文提出了一种基于YOLOv5-Tiny的轻量型焊缝缺陷识别方法。首先,在Backbone部分加入注意力机制SELayer,使模型实现持续的性能提升;然后,用GhostBottleneck模块替换Head层中的C3模块,保留边缘信息;最后,去除用于检测大物体的13×13特征层,并将多数普通卷积替换成深度可分离卷积,加快模型的训练与预测。模型分别采用DIoU与CIoU两种损失函数进行训练。实验结果表明:与YOLOv5s模型相比,YOLOv5-Tiny模型的参数量减少了33.6%,处理速度提升了17.5%,预测权重减小了32.8%,更好地实现嵌入式使用,模型的平均精度均值得到提升。
Objective Industrial equipment is prone to various internal welding defects during the process owing to factors such as the manufacturing process and welding environments, such as pores, slag inclusion, and incomplete penetration. However, the problem of small defects in radiographic inspection of weld defects is challenging as well. The most serious problem is the lack of detailed features visible to the naked eye, making it difficult to distinguish between the foreground and background during the inspection process. Therefore, it is essential to detect the internal defects of the weld in realtime. In industrial inspection, the type of X-ray flaw detection images is generally determined and located manually. Manual film evaluation has a high workload and low efficiency, as well as false and missed detection. Deep learning is now widely used in target recognition, thanks to the rapid development of computer and digital image processing technology. In this paper, a weld defect detection algorithm based on lightweight YOLOv5-Tiny is proposed, which is combined with the characteristics of weld internal defects in X-ray images.Methods First, the edges of pores and incomplete penetration are blurred, making it difficult for the model to extract the edge information of defects, resulting in a low model recall rate. Therefore, an attention mechanism SELayer is added to the Backbone part. This mechanism can use limited attention resources to quickly filter out high-value information from a large amount of information, allowing the model to pay more attention to the edge information of defects, retains more edge information, and improve the model’s performance continuously. Second, replace all C3 modules with the Ghost Bttlenecko module in the Head section. The Ghost Bttlenecko module is composed of two Ghost Cnvo modules and a residual edge. The function of the Ghost Cnvo _1 module is to process the input feature map by convolution, normalization, and activation function;the Ghost Cnvo _2 module removes the activation
作者
程松
杨洪刚
徐学谦
李敏
陈云霞
Cheng Song;Yang Honggang;Xu Xueqian;Li Min;Chen Yunxia(School of Mechanical Engineering,Shanghai Dianji University,Shanghai 201306,China;Shanghai University of Electric Power,Shanghai 201306,China)
出处
《中国激光》
EI
CAS
CSCD
北大核心
2022年第21期130-138,共9页
Chinese Journal of Lasers
基金
国家自然科学基金(51809161,52005315)。
关键词
测量
无损检测
YOLOv5
缺陷识别
轻量型模型
measurement
nondestructive examination
YOLOv5
defect identification
lightweight model
