Machine Learning Generated Process Parameters for Additive Manufacturing

Research

This project seeks to create an intuitive Additive Manufacturing User Interface (AMUI) for an end-to-end additive manufacturing system, specifically tailored for metal 3D printing. It will enable individuals without prior technical expertise to effortlessly upload 3D models and configure the necessary processing conditions for their builds. 

Utilizing surrogate models and analytical solutions, researchers aim to automatically determine the optimal printing parameters for processes such as Laser Powder Bed Fusion (LPBF) and effectively mitigate potential sources of defects like keyholing and spatter.

The quality of the computed process parameters will be validated with prints from LPBF equipment such as the EOS M290. The primary goal of this project is to simplify the additive manufacturing process and train operators  on process windows to seamlessly produce vital components. This not only streamlines the process but also ensures the production of high-quality, reliable parts critical to various applications following the highest of industry standard guidelines.

Principal Investigator
Amir Barati Farimani
Additional Investigator
Jack Beuth
Anthony Rollett
Related Links
ARL AI-Enabled Additive Manufacturing
Research Areas
AI and machine learning
Materials development
Process development
Qualification and certification
Robotics and automation