融合局部和全局特征的铸件缺陷检测

doi:10.3969/j.issn.0255-8297.2024.05.004

摘要/Abstract

摘要： 铝合金铸件已经广泛应用于汽车、飞机等重要工业，其质量直接影响到机械零部件的安全使用。针对铝合金铸件的X射线图像表面和内部缺陷多样化和细微问题，提出了一种融合局部和全局特征的X射线图像铸造缺陷检测方法。首先，将高效通道注意力模块和经典网络ResNet-50进行融合构成新的基础卷积神经网络，以新的网络为骨干构建双分支网络模型。然后，提出了细节信息定位提取（detailed information location and extraction,DILE）模块，该模块定位到包含丰富判别性信息的局部区域。最后，将由DILE得到的局部图像结合原始图像作为网络的输入，构建了一个融合局部和全局特征的双分支网络模型。对全局区域的学习有助于在复杂背景下提取有意义的细微信息，对局部区域的学习可以进一步提高分类效果。该方法在真实汽车铸件的X射线图像数据集上进行测试训练，测试集准确率达98.3%。实验结果表明，该方法相较于其他常规方法更有效。

关键词: 深度学习, 铸件缺陷无损检测, 注意力机制, X射线图像

Abstract: Aluminum alloy casting has been widely used in automobile, aircraft and other important industries, where its quality directly affects the safety of mechanical parts. Aiming at the diversification and minuteness of defects in the surface and interior of the X-ray images of aluminum alloy casting, a casting defect detection method based on local and global features was proposed. Firstly, an efficient channel attention module efficient channel attention is fused with the classical network resnet-50 to form a new basic convolutional neural network, which serves as the backbone for constructing a double-branch network model. Then, a detailed information location and extraction (DILE) module is proposed, which located the local area containing rich discriminant information. Finally, combining the local image obtained by DILE with the original image as the input to the network, a double branch network model integrating local and global features is constructed. The global region learning aids in extracting meaningful subtle information in complex background, while the learning of local region further improves the classification effectiveness. The method was tested and trained on an X-ray image data set of real automobile castings, achieving a test set accuracy of 98.3%. Experimental results show that this method is more effective than conventional methods.

Key words: deep learning, non-destructive testing of casting defects, attention mechanism, X-ray image

中图分类号:

TP391.41

栗莎, 王永雄, 王哲, 陈旭, 何嘉欣. 融合局部和全局特征的铸件缺陷检测[J]. 应用科学学报, 2024, 42(5): 757-768.

LI Sha, WANG Yongxiong, WANG Zhe, CHEN Xu, HE Jiaxin. Casting Defect Detection Based on Local and Global Features[J]. Journal of Applied Sciences, 2024, 42(5): 757-768.

参考文献

[1] Dursun T, Soutis C. Recent developments in advanced aircraft aluminium alloys [J]. Materials & Design, 2014, 56: 862-871.
[2] Miller W S, Zhuang L, Bottema J, et al. Recent development in aluminium alloys for the automotive industry [J]. Materials Science and Engineering: A, 2000, 280(1): 37-49.
[3] Fut P, Pribuloy A, Fedorko G, et al. Failure analysis of a railway brake disc with the use of casting process simulation [J]. Engineering Failure Analysis, 2019, 95: 226-238.
[4] Ingle V, Sorte M. Defects, root causes in casting process and their remedies: review [J]. International Journal of Engineering Research and Applications, 2017, 7(3): 47-54.
[5] 李杨, 李根, 周云方. 搅拌摩擦焊缺陷无损检测技术研究进展[J]. 焊接技术, 2020(2): 4. Li Y, Li G, Zhou Y F. Research progress of nondestructive testing technology for friction stir welding defects [J]. Welding Technology, 2020(2): 4. (in Chinese)
[6] 张辉, 张邹铨, 陈煜嵘, 等. 工业铸件缺陷无损检测技术的应用进展与展望[J]. 自动化学报, 2022, 48(4): 935-956. Zhang H, Zhang Z Q, Chen Y R, et al. Application advance and prospect of nondestructive testing technology for industrial casting defects [J]. Acta Automatica Sinica, 2022, 48(4): 935-956. (in Chinese)
[7] Mittal S, Dutta M K, Issac A. Non-destructive image processing based system for assessment of rice quality and defects for classification according to inferred commercial value [J]. Measurement, 2019, 148: 106969.
[8] Mery D, Arteta C. Automatic defect recognition in X-ray testing using computer vision [C]//2017 IEEE Winter Conference on Applications of Computer Vision (WACV), 2017: 1026- 1035.
[9] Ferguson M, Ak R, Lee Y T, et al. Detection and segmentation of manufacturing defects with convolutional neural networks and transfer learning [DB/OL]. 2018[2022-04-06] https://arxiv.org/abs/1808.02518.
[10] Wu B, Zhou J X, Yang H Q, et al. An ameliorated deep dense convolutional neural network for accurate recognition of casting defects in X-ray images [J]. Knowledge-Based Systems, 2021, 226(6): 107096.
[11] Hu C F, Wang Y X. An efficient CNN model based on object-level attention mechanism for casting defects detection on radiography images [J]. IEEE Transactions on Industrial Electronics, 2020, 67(12): 10922-10930.
[12] Wang Y X, Hu C F, Chen K, et al. Self-attention guided model for defect detection of aluminium alloy casting on X-ray image-ScienceDirect [J]. Computers & Electrical Engineering, 2020, 88: 106821.
[13] Jiang L L, Wang Y X, Tang Z H, et al. Casting defect detection in X-ray images using convolutional neural networks and attention-guided data augmentation [J]. Measurement, 2021, 170: 108736.
[14] Simonyan K, Zisserman A. Very deep convolutional networks for large-scale image recognition [DB/OL]. 2014[2022-04-06]. http://arxiv.org/abs/1409.1556.
[15] He K M, Zhang X Y, Ren S Q, et al. Deep residual learning for image recognition [C]//2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016: 770-778.
[16] Zhou Z H. A brief introduction to weakly supervised learning [J]. National Science Review, 2018, 5(1): 44-53.
[17] Wang Q, Wu B, Zhu P, et al. ECA-Net: efficient channel attention for deep convolutional neural networks [C]//IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2020: 11531-11539.
[18] Zhang F, Li M, Zhai G S, et al. Multi-branch and multi-scale attention learning for finegrained visual categorization [C]//27th International Conference on Multimedia Modeling. Cham: Springer, 2021: 136-147.
[19] Hu J, Shen L, Albanie S, et al. Squeeze-and-excitation networks [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2020, 42(8): 2011-2023.
[20] Deng J, Dong W, Socher R, et al. ImageNet: a large-scale hierarchical image database [C]//2009 IEEE Conference on Computer Vision and Pattern Recognition, 2009: 248-255.
[21] Chollet F. Xception: deep learning with depthwise separable convolutions [C]//2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017: 1800-1807.
[22] Hu T, Qi H. See better before looking closer: weakly supervised data augmentation network for fine-grained visual classification [DB/OL]. 2019[2022-04-06] https://arxiv.org/abs/1901.09891.
[23] Selvaraju R R, Cogswell M, Das A, et al. Grad-CAM: visual explanations from deep networks via gradient-based localization [C]//2017 IEEE International Conference on Computer Vision (ICCV), 2017: 618-626.