AI-powered, Machine Agnostic AM In Process Part Qualification

Today, most operations work to perfect the function of individual Additive Manufacturing machines producing material repeatably with known properties for fixed geometries. This is done over months or years of process optimisation and material property testing at a cost that easily can surpass millions of dollars.
The objective of this research project is to advance the distributed Additive Manufacturing (AM) of critical structural components by developing methods to predict part lifespan directly from data gathered during the manufacturing process.
This approach aims to make predictions applicable across different machines, materials, locations, and part geometries.
The project seeks to present an alternative to the current machine-centric qualification process in AM
By exploring a new paradigm, this research aims to enable real-time predictions of part life for every unique AM component, ensuring that parts can be produced on any machine, at any location, and for any geometry, while guaranteeing their performance