High-Precision Real-Time Pores Detection in LPBF using Thermal Energy Density (TED) Signals

Abstract

Pore formation during Laser Powder Bed Fusion (LPBF) has long posed challenges in metal 3D printing, significantly affecting the mechanical properties of the final product. Porosity frequently occurs because of an unstable keyhole formation, triggered by an excess laser energy. Traditional approaches for detecting pores rely heavily on CT scanning, a time-consuming and costly method unsuitable for large-scale production. In response to these limitations, we have developed a real-time pore detection method using thermal sensor data, offering a more efficient, cost-effective alternative for quality control during the LPBF process. Our method, validated against CT-scanned pore counts, provides a high degree of accuracy, achieving an R^2 value of 0.94 between the across eight sample prints. This approach also effectively tracks pore formation trends as the layer-wise printing pattern changes, providing timely insights into product quality, which may serve as important datapoints for real-time adaptive parameters optimization in the future. In contrast to prior machine learning-based techniques, which were limited by high computational costs and lacked direct validation strategy, the method intr