High-Precision and Ultraspeed Monitoring of Melt-Pool Morphology in Laser-Directed Energy Deposition Using Deep Learning
Jiayu Yang, Guan Liu, Wei Zhu, Yingjie Zhang, Wenbin Zhou, Defu Liu, Yongcheng Lin
Abstract
Laser-directed energy deposition (L-DED) is an advanced additive manufacturing technology primarily adopted in metal three-dimensional printing systems. The L-DED process is characterized by various defects, thus necessitating the extensive use of in-situ monitoring to enable real-time adjustments of process parameters by detecting molten-pool features. To address the challenge of accurately extracting the molten-pool morphology from an undetached spatter, an innovative monitoring method based on the U-Net (U-shaped network) is proposed herein. A lightweight architecture accelerates the processing speed, whereas an enhanced loss function incorporating weight maps augments the segmentation precision. The model performance is evaluated by comparing its segmentation accuracy and processing speed with those of the conventional U-Net, using the mean intersection over union (MIoU) as the segmentation metric. The improved model demonstrates superior segmentation accuracy at the interface between the molten pool and spatter, with a peak MIoU of 0.9798 achieved on the test set. Furthermore, this model processes each image in an extremely short time of 17.9 ms. Using this segmentation algorithm, the error in extracting the molten-pool width from single-track experiments is within 0.1 mm. The proposed method for monitoring the molten-pool morphology is suitable for deployment in online monitoring systems, thus providing a foundation for subsequent process-parameter regulation.