A defect classification algorithm for gas tungsten arc welding process based on unsupervised learning and few-shot learning strategy
Welding defect prediction is the foundation for ensuring welding quality in gas tungsten arc
welding (GTAW). In the prediction process, method based on molten pool vision is the most …
welding (GTAW). In the prediction process, method based on molten pool vision is the most …
A new method for deep learning detection of defects in X-ray images of pressure vessel welds
X Wang, F He, X Huang - Scientific Reports, 2024 - nature.com
Given that defect detection in weld X-ray images is a critical aspect of pressure vessel
manufacturing and inspection, accurate differentiation of the type, distribution, number, and …
manufacturing and inspection, accurate differentiation of the type, distribution, number, and …
Elastic Slow Feature Prototypical Network for Few-Shot Fault Diagnosis of Industrial Processes
B Zhang, L Li, G Liang, C Tan, F Dong - IEEE Sensors Journal, 2024 - ieeexplore.ieee.org
Most industrial process data are highly dynamic and nonlinear with time-varying
characteristics, which poses great challenges to industrial fault diagnosis tasks. In addition …
characteristics, which poses great challenges to industrial fault diagnosis tasks. In addition …
Automatic Identification of Complex Defects in Pressurized Vessel Welds Based on Meta-Learning-Fine-Tuning
Y Dai, S Li, P Yi, J Yu - papers.ssrn.com
The welds of pressure vessels are susceptible to defects under long-term operation in
complex and harsh environments with alternating loads and corrosion. The existing …
complex and harsh environments with alternating loads and corrosion. The existing …