This study investigates the influence of resistive pre-heating of the feedstock wire (here called hot-wire) on the stability of laser-directed energy deposition of Duplex stainless steel. Data acquired online during depositions as well as metallographic investigations revealed the process characteristic and its stability window. The online data, such as electrical signals in the pre-heating circuit and images captured from side-view of the process interaction zone gave insight on the metal transfer between the molten wire and the melt pool. The results show that the characteristics of the process, like laser-wire and wire-melt pool interaction, vary depending on the level of the wire pre-heating. In addition, application of two independent energy sources, laser beam and electrical power, allows fine-tuning of the heat input and increases penetration depth, with little influence on the height and width of the beads. This allows for better process stability as well as elimination of lack of fusion defects. Electrical signals measured in the hot-wire circuit indicate the process stability such that the resistive pre-heating can be used for in-process monitoring. The conclusion is that the resistive pre-heating gives additional means for controlling the stability and the heat input of the laser-directed energy deposition.

Defect detection on the computed tomography (CT) images plays an important role in the development of metallic additive manufacturing (AM). Although some deep learning techniques have been adopted in the CT image-based defect detection problem, it is still a challenging task to accurately detect small-size defects in the presence of undesirable noises. In this paper, a novel defect detection method, namely, the depth-connected region-based convolutional neural network (DC-RCNN), is proposed to detect small defects and reduce the influence of noises. In particular, a saliency-guided region proposal method is first developed to generate small-size region proposals with the aim to accommodate the small defects. Then, the main architecture of DC-RCNN is proposed to extract and connect the consistent features across multiple frames, thereby reducing the influence of randomly distributed noises. Moreover, the transfer learning technique is utilized to improve the generalization ability of the proposed DC-RCNN. In order to verify the effectiveness and superiority, the proposed method is applied to the real-world AM data for defect detection. The experimental validations show that the proposed DC-RCNN is able to detect the small-size defects under noises and outperforms the original RCNN method in terms of detection accuracy and running time.