In laser powder bed fusion (LPBF), melt pool instability can lead to the development of pores in printed parts, reducing the part’s structural strength. While camera-based monitoring systems have been introduced to improve melt pool stability, these systems only measure melt pool stability in limited, indirect ways. We propose that melt pool stability can be improved by explicitly encoding stability into LPBF monitoring systems through the use of temporal features and pore density modelling. We introduce the temporal features, in the form of temporal variances of common LPBF monitoring features (e.g., melt pool area, intensity), to explicitly quantify printing stability. Furthermore, we introduce a neural network model trained to link these video features directly to pore densities estimated from the CT scans of previously printed parts. This model aims to reduce the number of online printer interventions to only those that are required to avoid porosity. These contributions are then implemented in a full LPBF monitoring system and tested on prints using 316L stainless steel. Results showed that our explicit stability quantification improved the correlation between our predicted pore densities and true pore densities by up to 42%.
Automated defect detection is a critical component of modern industrial quality control. However, it is particularly difficult to identify subtle defects such as scratches on metallic surfaces. Therefore, this paper investigates the effectiveness of multiview deep learning approaches for improved defect detection by implementing and comparing early and late fusion methodologies. We propose MV-UNet, a novel early fusion architecture that aligns and aggregates multiview features using a transformation block to enhance detection accuracy. To evaluate performance, we conduct our experiments on a recorded metallic plates dataset, comparing the traditional single-view inspection to both late and early fusion methods. Our results demonstrate that both the early and late fusion methods improve detection accuracy over the mono-view baseline, with our MV-UNet achieving the hightest F1-score (0.942). Additionally, we introduce adapted precision–recall metrics designed for segmentation-based defect detection, addressing the limitations of traditional IoU-based evaluations. These tailored metrics more accurately reflect defect localization performance, particularly for thin, elongated scratches. Our findings highlight the advantages of early fusion for industrial defect detection, providing a robust and scalable approach to multiview analysis.
X-ray computed tomography (X-CT) plays an important role in non-destructive quality inspection and process evaluation in metal additive manufacturing, as several types of defects such as keyhole and lack of fusion pores can be observed in these 3D images as local changes in material density. Segmentation of these defects often relies on threshold methods applied to the reconstructed attenuation values of the 3D image voxels. However, the segmentation accuracy is affected by unavoidable X-CT reconstruction features such as partial volume effects, voxel noise and imaging artefacts. These effects create false positives, difficulties in threshold value selection and unclear or jagged defect edges. In this paper, we present a new X-CT defect segmentation method based on preprocessing the X-CT image with a 3D total variation denoising method. By comparing the changes in the histogram, threshold selection can be significantly better, and the resulting segmentation is of much higher quality. We derive the optimal algorithm parameter settings and demonstrate robustness for deviating settings. The technique is presented on simulated data sets, compared between low- and high-quality X-CT scans, and evaluated with optical microscopy after destructive tests.