Evaluating in-situ melt pool monitoring for defects detection in laser powder bed fusion

Abstract Laser Powder Bed Fusion (L-PBF) enables unprecedented design freedom but is prone to process-induced defects, including porosity and lack of fusion, stemming from unstable thermal dynamics. Melt Pool Monitoring (MPM) has emerged as a viable in-situ technique for real-time anomaly detection during L-PBF. This study investigates the efficacy of the EOSTATE MPM system in identifying thermal irregularities induced by geometric features, focusing on two cases: unsupported overhangs and reverse hourglass structures with narrowed walls. Tests were carried out on IN718 and MS1 alloys to investigate the material-specific signal behaviour. Grey value (GV) intensity and deviation information were correlated with visual inspection and macrostructural examination. It is evident from the results that MPM successfully identifies thermal anomalies related to heat accumulation and constricted conduction, but small near-surface defects tend to go undetected due to sensor resolution and angular positioning limitations. The findings indicate MPM’s capability for layer-specific thermal diagnostics and the need for the integration of sensor fusion and machine learning to enhance real-time defect classification and adaptive control mechanisms.