Improved Process Parameter Optimization using Machine Learning

August 09, 2022 | Categories:

This presentation will be a briefing on the technical results of an America Makes program that recently completed. The program was focused on demonstrating a machine learning-enabled approach to process parameter development. Senvol and Northrop Grumman demonstrated in a side-by-side comparison that a machine learning-enabled approach to process parameter development was substantially more accurate and sophisticated than a traditional approach.

In the program, there were 219,856 different possible parameter combinations to choose from. The project team used a ML approach to optimally select which parameter sets to use to best achieve multiple different performance requirements.

The project culminated in a validation build, where it was demonstrated that the ML-enabled approach successfully selected parameter sets that met all performance requirements, whereas the traditional approach led to the selection of parameter sets that failed to meet the performance requirements.

This presentation will explain how the machine learning approach is different from traditional approaches, detail the technical results of this program, and walk the audience through the steps that a user can take to rapidly find optimal parameters while minimizing data generation time and costs.

A ML approach can be used for any AM machine, AM material or AM process, so understating how the ML approach can help an AM user rapidly optimize process parameters will benefit all AM users.