Research on Automated Defect Classification Based on Visual Sensing and Convolutional Neural Network-Support Vector Machine for GTA-Assisted Droplet Deposition Manufacturing Process
Research on Automated Defect Classification Based on Visual Sensing and Convolutional Neural Network-Support Vector Machine for GTA-Assisted Droplet Deposition Manufacturing Process
复制标题
基于视觉传感和卷积神经网络-支持向量机的GTA辅助液滴沉积制造工艺缺陷自动分类研究
DOI：
10.3390/met11040639
复制
发表时间：
2021-04
期刊：
影响因子：
2.9
通讯作者：
Zhengying Wei
中科院分区：
文献类型：
--
作者：
Chen Ma;Haifei Dang;Jun Du;Pengfei He;Minbo Jiang;Zhengying Wei
本文提出了一种新型金属增材制造工艺，该工艺由钨极气体电弧（GTA）和液滴沉积制造（DDM）相结合。由于涉及熔滴冲击、铺展、表面预熔等复杂的物理冶金过程，常常会出现熔敷层未熔合、溢流、不连续等缺陷。为了确保 GTA 辅助 DDM 零件的质量，实施了基于视觉传感的在线监控。目前的研究还侧重于通过卷积神经网络-支持向量机（CNN-SVM）的方式进行自动缺陷分类，以避免手动识别的低效率和偏差。 98.9% 的最佳准确率，处理图像的执行时间约为 12 毫秒，证明我们的模型足以用于过程的实时反馈控制。
This paper proposes a novel metal additive manufacturing process, which is a composition of gas tungsten arc (GTA) and droplet deposition manufacturing (DDM). Due to complex physical metallurgical processes involved, such as droplet impact, spreading, surface pre-melting, etc., defects, including lack of fusion, overflow and discontinuity of deposited layers always occur. To assure the quality of GTA-assisted DDM-ed parts, online monitoring based on visual sensing has been implemented. The current study also focuses on automated defect classification to avoid low efficiency and bias of manual recognition by the way of convolutional neural network-support vector machine (CNN-SVM). The best accuracy of 98.9%, with an execution time of about 12 milliseconds to handle an image, proved our model can be enough to use in real-time feedback control of the process.
登录
查看更多内容
影响因子：
4.6
作者：
L. Rodríguez-Cobo;R. Ruiz-Lombera;O. Conde;J. López-Higuera;A. Cobo;J. Mirapeix
通讯作者：
L. Rodríguez-Cobo;R. Ruiz-Lombera;O. Conde;J. López-Higuera;A. Cobo;J. Mirapeix
DOI：
10.1088/1757-899x/402/1/012159
发表时间：
2018-09
期刊：
IOP Conference Series: Materials Science and Engineering
影响因子：
--
作者：
S. E. Florence;V. Samsingh;Vimaleswar Babureddy
通讯作者：
S. E. Florence;V. Samsingh;Vimaleswar Babureddy
影响因子：
4.6
作者：
Azimi SM;Britz D;Engstler M;Fritz M;Mücklich F
通讯作者：
Mücklich F
DOI：
10.3390/ma13245643
发表时间：
2020-12-10
期刊：
Materials (Basel, Switzerland)
影响因子：
--
作者：
Wu Y;Cui B;Xiao Y
通讯作者：
Xiao Y
影响因子：
2.1
作者：
L. Yin;Jinzhao Wang;Huiqin Hu;Shanguo Han;Yupeng Zhang
通讯作者：
L. Yin;Jinzhao Wang;Huiqin Hu;Shanguo Han;Yupeng Zhang