X射线检测方法被广泛应用于焊缝内部缺陷的检测过程，但检测过程主要依靠人工查看X射线图像对产品质量做出评级，此种检测方式效率低且需要操作人员丰富的检测经验，难以满足批量检测需求，亟需借助卷积神经网络的方法提升其检测效率。因此提出一种复合卷积层网络结构的CC-ResNet模型，将不同尺度的卷积核复合为一层卷积，替换单个卷积核结构，并对模型训练过程中的损失函数进行优化。使用车间产品焊缝X射线图像建立数据集，通过对CC-ResNet网络模型进行实验可得，其平均召回率和平均准确率为98.52%和95.23%，与其他网络模型相比提高了缺陷检测能力，为车间进行焊缝缺陷的智能化和批量化检测提供了算法基础。
The X-ray detection method is widely used in the detection of weld internal defects， but in the detection process， product quality is rated mainly by manually viewing X-ray images. This detection method is inefficient， and requires rich experience of operators， which is difficult to meet the needs of batch detection. It is thus urgent to improve the detection efficiency with the help of the convolution neural network. This paper proposes a CC-ResNet model with composite convolution layer network structure， which combines convolution cores of different scales into one layer of convolution， replaces the original single convolution core structure， and optimizes the loss function in the process of model training. A data set is established by using the weld X-ray images of workshop products. Experiment on CC-ResNet network model shows that the average recall rate and accuracy are 98.52% and 95.23%， respectively. Compared with other network models， the model proposed can improve the defect detection ability， providing an algorithm basis for intelligent and batch detection of weld defects in the workshop.
[1] SUN Y, SUN H Y, BAI P, et al. Real-time automatic detection of weld defects in X-ray images[J]. Transactions of the China Welding Institution, 2004, 25(2): 115-118, 122 (in Chinese). 孙怡, 孙洪雨, 白鹏, 等. X射线焊缝图像中缺陷的实时检测方法[J]. 焊接学报, 2004, 25(2): 115-118, 122.
[2] STAUDE A, BARTSCHER M, EHRIG K, et al. Quantification of the capability of micro-CT to detect defects in castings using a new test piece and a voxel-based comparison method[J]. NDT & E International, 2011, 44(6): 531-536.
[3] WANG F, ZHU J J. Application of machine vision in welding defect detection in complex environment[J]. Welding Technology, 2017, 46(5): 127-133 (in Chinese). 王飞, 朱建江. 机器视觉在复杂环境下焊接缺陷检测的应用研究[J]. 焊接技术, 2017, 46(5): 127-133.
[4] MIN X J. The development and design of the repair welding procedure of the thick wall duplex stainless steel piping[J]. China Welding, 2017(1): 60-64.
[5] ZHI Z L, JIANG H Q, YANG D Y, et al. A deep learning fusion model of wave and image data for weld defect recognition[J]. Journal of Xi'an Jiaotong University, 2021, 55(5): 73-82 (in Chinese). 支泽林, 姜洪权, 杨得焱, 等. 图谱数据深度学习融合模型及焊缝缺陷识别方法[J]. 西安交通大学学报, 2021, 55(5): 73-82.
[6] YANG L, JIANG H Q. Weld defect classification in radiographic images using unified deep neural network with multi-level features[J]. Journal of Intelligent Manufacturing, 2021, 32(2): 459-469.
[7] JIANG H Q, HE S, GAO J M, et al. An improved convolutional neural network for weld defect recognition[J]. Journal of Mechanical Engineering, 2020, 56(8): 235-242 (in Chinese). 姜洪权, 贺帅, 高建民, 等. 一种改进卷积神经网络模型的焊缝缺陷识别方法[J]. 机械工程学报, 2020, 56(8): 235-242.
[8] FAN D, HU A D, HUANG J K, et al. X-ray image defect recognition method for pipe weld based on improved convolutional neural network[J]. Transactions of the China Welding Institution, 2020, 41(1): 7-11, 97 (in Chinese). 樊丁, 胡桉得, 黄健康, 等. 基于改进卷积神经网络的管焊缝X射线图像缺陷识别方法[J]. 焊接学报, 2020, 41(1): 7-11, 97.
[9] LIU T Y, BAO J S, WANG J L, et al. A hybrid CNN–LSTM algorithm for online defect recognition of CO2 welding[J]. Sensors, 2018, 18(12): 4369.
[10]
[11] FERGUSON M, AK R, LEE Y T T, et al. Detection and segmentation of manufacturing defects with convolutional neural net-works and transfer learning[DB/OL]. arXiv preprint:1808.02518, 2018.
[12] ZENG J F, LI Y M, YANG H X, et al. Environmental sound classification method based on multilevel residual network[J]. Journal of Data Acquisition & Processing, 2021, 36(5): 960-968 (in Chinese). 曾金芳, 李友明, 杨恢先, 等. 基于多级残差网络的环境声音分类方法[J]. 数据采集与处理, 2021, 36(5): 960-968.
[13] CHANG H, RAO Z Q, LI Y C, et al. Research on crack detection algorithm of railway tunnel based on improved residual network[J]. Journal of Northeast Normal University (Natural Science Edition), 2021, 53(3): 56-63 (in Chinese). 常惠, 饶志强, 李益晨, 等. 基于改进残差网络的铁路隧道裂缝检测算法研究[J]. 东北师大学报(自然科学版), 2021, 53(3): 56-63.
[14] AL-FALLUJI R A, DALAF KATHEETH Z, ALATHARI B. Automatic detection of COVID-19 using chest X-ray images and modified ResNet18-based convolution neural networks[J]. Computers, Materials & Continua, 2021, 66(2): 1301-1313.
CJA