Graph-augmented Segmentation of Complex Shapes in Laser Powder bed Fusion for Enhanced In Situ Inspection

2026-04-27

AI Summary

This work addresses the challenge of insufficient in-situ image segmentation accuracy in laser powder bed fusion (L-PBF), which arises from industrial lighting variations and inter-layer pixel intensity discrepancies. To overcome this, the authors propose a graph-enhanced semantic segmentation approach that integrates a graph neural network (GNN) bottleneck module into the U-Net architecture. This design explicitly models global geometric dependencies among spatial regions, replacing conventional pixel-wise processing strategies. Evaluated on in-situ reconstruction tasks for L-PBF lattice structures, the method significantly outperforms existing benchmarks, achieving improved consistency and accuracy in reconstructing complex geometries under real-world industrial conditions. The results demonstrate its robustness and scalability for in-situ monitoring and geometric validation in additive manufacturing processes.

Technology Category

• Computer Vision: Segmentation
• Machine Learning: Calibration & Uncertainty Quantification
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Systems and Infrastructure for Web, Mobile and WoT: Federated Web and WoT systems, including distributed, federated and edge-based data processing

Abstract

The technological maturity of in situ inspection and monitoring methods in additive manufacturing is steadily increasing, enabling more efficient and practical qualification procedures. In this context, image segmentation of powder bed images in Laser Powder Bed Fusion (L-PBF) has been investigated by various authors, leveraging both edge detection and machine learning approaches to identify deviations from nominal geometry. Despite these developments, several challenges remain, including the sensitivity of segmentation performance to industrial illumination conditions and layer-to-layer variability in pixel intensity patterns. The study addresses these limitations by proposing a graph-augmented segmentation approach. The underlying principle consists of preserving the geometrical information at a global level rather than at pixel-wise level, modeling dependencies and relational information among spatial regions with a Graph Neural Network bottleneck embedded into a U-Net architecture. This allows enhancing the consistency and accuracy of the geometry reconstruction in the presence of spatial and layer-wise photometric variability systematically faced in real data. The method is evaluated against benchmark techniques for the in situ reconstruction of lattice structures produced by L-PBF, demonstrating its potential as a scalable solution for robust in situ inspection and geometric verification in industrial environments.

Problem

• in situ inspection
• image segmentation
• Laser Powder Bed Fusion
• photometric variability
• geometric verification

Innovation

• graph-augmented segmentation
• Graph Neural Network
• U-Net
• in situ inspection
• Laser Powder Bed Fusion