The XGBoost model offers a feature importance metric that will help to elucidate possible relationships between the process data and observed defects.
We then train a XGBoost machine learning model to predict localized defects-specifically soot–using only the mapped process data of builds from a laser powder bed fusion process as input features. In this work we demonstrate how these inherently temporal data may be mapped spatially by leveraging scan path information. This information may be used for process monitoring and defect detection however, little has been done to leverage this data from the machines for more than just coarse-grained process monitoring. The data from these sensors offer rich information about the consistency of the fabrication process within a build and across builds. In powder bed fusion additive manufacturing, machines are often equipped with in-situ sensors to monitor the build environment as well as machine actuators and subsystems. 3Materials Science and Technology Division, Oak Ridge National Laboratory, Oak Ridge, TN, United States.2Manufacturing Demonstration Facility, Oak Ridge National Laboratory, Knoxville, TN, United States.1Electrification and Energy Infrastructures Division, Oak Ridge National Laboratory, Oak Ridge, TN, United States.William Halsey 1,2*, Derek Rose 1, Luke Scime 1,2, Ryan Dehoff 2,3 and Vincent Paquit 1,2
0 kommentar(er)
