...@xjtu.edu.cn 19 07 2025 10 11 2025 08 12 2025 © 2026 Emerald Publishing Limited 2026 Emerald Publishing Limited Licensed re-use rights only Deep learning Point cloud processing Accurate prediction Surface monitoring Wire-arc directed energy deposition Key Research...

... evaluation at speeds over 4,100 nozzles/s. Originality/value This study proposes a novel hybrid detection framework that combines interpretable image features with deep learning-based classification. It significantly enhances the current capabilities of printhead condition monitoring. The proposed system...

.... This study aims to compare the performance of various deep learning (DL) models in detecting these defects individually (warping/no warping, stringing/no stringing and cracking/no cracking) as well as combinedly (warping, stringing, cracking and no defect). Design/methodology/approach A Raspberry Pi...

... Limited Licensed re-use rights only Design for additive manufacturing Topology optimization Deep learning Convolutional neural network Transfer learning Conditional generative adversarial network Additive manufacturing (AM) technologies have been widely implemented by various...

.... Originality/value Experimental results show that the improved YOLOv3 model can solve the problem of poor performance of traditional defect detection models and other deep learning models. And the proposed model can meet the requirements of WAAM quality monitoring. Cheng Huang can be contacted...

... dozens of experiments. A deep learning method is used for bead modeling and control. To adaptively control the bead geometry in real-time, a closed-loop control system was developed based on the bead model and in situ monitoring. Findings A series of experiments were conducted to train, test...