“Correlative Analytics of Downskin Surface Roughness Outcomes Using Systematic Data Science Workflows
Date:
Laser Powder Bed Fusion (LBPF) is a widely adopted AM technology owing to the demonstrated benefits in design freedom and part consolidation for complex components. However, due to the complex and multiscale process physics that governs the process, ensuring consistent quality is an ongoing challenge. Data science is a promising tool to better understand the interaction between the LPBF process physics and the uncertainty in laser-material interaction phenomena. In this study we attempt to correlate downskin surface roughness outcomes to parameterized and simulated process inputs. The study specifically focusses on data collected from 4405 and maraging steel specimens built with different overhang angles. The data from multiple builds was consolidated and subjected to a systematic and data-centric analytics workflow. In our study, the dataset quality guides the process of developing descriptive, diagnostic and predictive insights. We share these insights, along with broader implications of using data-centric workflows.