Boeing

Additive Manufacturing Data Analytics, Computational Material Modeling

Additive manufacturing (AM) is a digital process that provides critical information across the entire process lifecycle from product definition, manufacturing, test/inspection and final acceptance. This information is comprised of large spatial and temporal data sets that provide insights to the quality of the final manufactured part. These data sets currently reside on disparate systems which can limit correlation and advance AM process understanding and insights This student team worked to integrate these data sets into a "super set" of data that is registered and fuse together using data consolidation and visualization techniques. With the data integrated, this student team would then attempt to apply new computational material science techniques to infer relationship between in process, post process, and material microstructure data. The models, upon validation, could be used to predict material microstructure and resulting part performance based on process parameters and geometric data. The desired outcome this student team worked to accomplish was novel computational material models applied to existing UW data sets through the development of new software packages that enable process to microstructure correlations. This project would be a complementary addition to the UW round robin study, by providing further guidance and funding on the data analytics scope of work.