Communications of the ACM
Accelerating the Discovery of Materials for 3D Printing
The data-driven system that accelerates the process of discovering new materials for three-dimensional (3D) printing that have multiple mechanical properties.
Credit: Mike Foshey et al
Massachusetts Institute of Technology (MIT) researchers have developed a less costly and less wasteful machine learning system for finding new three-dimensionally-printable materials.
The team worked with scientists at German chemical company BASF on an optimization algorithm to execute trial-and-error discovery.
A material developer chooses ingredients, enters their chemical compositions into the algorithm, and classifies desired mechanical properties; the algorithm refines ingredient amounts and checks how each formula impacts the material's properties before yielding the optimized compound.
The developer combines, processes, and tests the sample to determine performance, and feeds results to the algorithm so it can decide on another formula to test.
MIT's Mike Foshey said, "Rather than having a chemist who can only do a couple of iterations over a span of days, our system can do hundreds of iterations over the same time span."
From MIT News
View Full Article
Abstracts Copyright © 2021 SmithBucklin, Washington, DC, USA
No entries found