Technical Summary

Defect formation during the powder bed fusion process poses a significant challenge in metal additive manufacturing, as such defects can severely compromise the mechanical performance of printed components. Although process parameter optimisation is crucial for minimising defects, the optimal parameters often vary depending on material composition and part geometry. Re-optimising for each variation is both costly and time-consuming. To address this, Gavin’s research investigates in-situ process monitoring by embedding advanced sensor systems within the LPBF machine. These include acoustic emission, infrared thermography, and eddy current sensing technologies. The data collected during printing is used to train AI algorithms capable of detecting defects in real time and dynamically adjusting process parameters to maintain build quality. In parallel, he is studying the microstructural characteristics of printed samples and establishing correlations with sensor data. This dual focus on defect mitigation and microstructure control aims to ensure consistent, high-performance outputs in additively manufactured NiTi components.