This presentation showcases an ongoing STTR project funded by the Navy. The technology that is being developed in this STTR is a data-driven machine learning algorithm with key capabilities that will enable a user to reduce the time, cost and resources required to characterize additive manufacturing (AM) materials and AM processes for metal parts. The algorithm being developed is material, machine and process agonistic. Moreover, the algorithm would “learn” from previous data sets and apply those learnings to new data sets, thereby decreasing the amount of data needed in the future. The Navy intends to use this algorithm to assist in developing statistically substantiated material properties in hopes of reducing conventional material characterization and testing that is needed to develop design allowables.
This presentation will outline our approach for using machine learning to investigate the relationships between process parameters, process signatures, material properties, and mechanical performance of metallic components. We will discuss why a data-driven machine learning algorithm was employed over other modeling approaches along with its advantages and disadvantages. We will also discuss some of the data that we have collected and demonstrate some of the algorithm’s capabilities.
- Understand the basics of how machine learning can be applied to AM and what are some of the advantages and disadvantages of using machine learning over other modeling approaches.
- Understand a framework with which to analyze the relationships between process parameters, process signatures, material properties, and mechanical performance of metallic components.
- Understand the capabilities of the algorithm that is being developed for the Navy STTR and how the Navy and other AM users intend on using the algorithm.