Machine Learning for 3D Printing Optimization
Sara McMains, Professor
Mechanical Engineering, Computer Science
Closed. This professor is continuing with Fall 2024 apprentices on this project; no new apprentices needed for Spring 2025.
Additive Manufacturing (aka 3D Printing) is a set of relatively novel manufacturing techniques that were originally used for prototyping but are increasingly used to fabricate end-use parts, which requires higher quality manufacturing.
The goal of this project is to build a machine learning model that can quickly and accurately predict 3D printed part quality.
We are working to create practical and industrially relevant tools that provide design and manufacturing feedback for 3D printing. Unlike existing research efforts in machine learning for this application that create synthetic data that are often not representative of 3D printed parts, we have compiled a database of 3D printed parts using CAD repositories (e.g. FabWave, Thingiverse). The parts we compile are rotated in a series of orientations, labeled by printing orientation quality, and we have two machine learning pipelines already built.
Role: The researcher who joins our project will be responsible for (a) building machine learning models to predict optimal build orientation or part distortion, (b) running FEM analysis, or (c) helping to develop and evaluate new approaches for efficient hyperparameter tuning.
Qualifications: Desirable skills: Familiarity/experience with python (bonus for coding machine learning models in python) or finite element analysis (FEA) or databases in JavaScript. We don't expect students to have prior experience in multiple areas.
Day-to-day supervisor for this project: Sara Shonwiler, Graduate Student
Hours: 6-8 hrs
Engineering, Design & Technologies Mathematical and Physical Sciences