摘要
在小径铜管钎焊结构的X射线数字化图像中,由于钎焊缺陷影像的尺寸、形态及对比度差异大,导致缺陷难以实现自动识别.为解决这一问题,通过多尺度特征表示与Biformer注意力机制相结合,提出一种基于TransUNet改进的缺陷分割模型AM-TransUNet.使用结合SimAM注意力机制的Res2Net模块替换基线模型TransUNet编码器部分的ResNet模块,以提升模型的多尺度特征提取能力和对复杂背景下缺陷局部细节特征的捕捉能力;在编码器末端级联Biformer动态稀疏注意力机制,以提高模型的检测速度和对全局信息的捕捉能力.利用构建的小径铜管X射线图像数据集进行缺陷分割试验,研究结果表明,AM-TransUNet模型的准确率、召回率比基线模型分别提高了2.8%和3.2%,HD95比基线模型减少了13.2,检测灵敏度优于径向0.5 mm的未钎透缺陷,AM-TransUNet缺陷分割模型具有更高的可靠性;同时,AM-TransUNet模型的检测速度比基线模型提高了9帧/s,模型参数量减小了66 M.
In the X-ray digital images of soldered copper pipes with small diameters,the significant variations in size,shape,and contrast of soldering defect images make it difficult to achieve automatic defect recognition.To address this issue,an improved defect segmentation model,namely AM-TransUNet,based on TransUNet was proposed,which combined multi-scale feature representation with the Biformer attention mechanism.The Res2Net module,combined with the SimAM attention mechanism,replaced the ResNet module in the encoder of the baseline TransUNet model,enhancing the model’s multi-scale feature extraction capabilities and ability to capture local defect details in complex backgrounds.Additionally,the Biformer dynamic sparse attention mechanism was cascaded at the end of the encoder to improve detection speed and enhance the model’s ability to capture global information.Defect segmentation experiments conducted on a constructed X-ray image dataset of small-diameter copper pipes demonstrate that the AM-TransUNet model achieves 2.8%and 3.2%improvement in precision and recall,respectively,compared to the baseline model.Moreover,the HD95 metric is reduced by 13.2,and the model shows superior sensitivity in detecting unfused defects with a radial dimension of 0.5 mm.The results indicate that the AM-TransUNet model has higher reliability in defect segmentation.Meanwhile,the detection speed of the AM-TransUNet model is improved by 9 frame/s over the baseline model,and the number of model parameters is reduced by 66 M.
作者
杨莉华
赵金宪
李金晓
刘海春
李庆生
贾涛
迟大钊
YANG Lihua;ZHAO Jinxian;LI Jinxiao;LIU Haichun;LI Qingsheng;JIA Tao;CHI Dazhao(School of Computer and Information Engineering,Heilongjiang University of Science and Technology,Harbin,150022,China;State Key Laboratory of Precision Welding&Joining of Materials and Structures,Harbin Institute of Technology,Harbin,150001,China;PipeChina Engineering Quality Supervision and Inspection Company,Beijing,100013,China)
出处
《焊接学报》
北大核心
2025年第7期100-106,共7页
Transactions of The China Welding Institution
基金
国家自然科学基金资助项目(52375328)。
关键词
小径铜管
钎焊缺陷
射线检测
深度学习
缺陷分割
copper pipe with small diameter
soldering defect
X-ray testing
deep learning
defect segmentation
