MIT CSAIL and BASF scientists have developed a new data driven system to accelerate the discovery of new 3D printing materials.
According to the scientists, the new machine-learning system costs less, generates less waste, and can be more innovative than manual discovery methods.
“Materials development is still very much a manual process,” says CSAIL mechanism engineer and co-lead author Mike Foshey.
“A chemist goes into a lab, mixes ingredients by hand, makes samples, tests them, and comes to a final formulation.”
“But 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.”
The new trial-and-error process enables a material developer to select a few ingredients, input details on their chemical compositions into the algorithm, and define the mechanical properties the new material should have.
The algorithm then increases and decreases the amounts of those components and checks how each formula affects the material’s properties, before arriving at the ideal combination.
This done, the developer mixes, processes, and tests that sample to find out how the material actually performs.
These results are then reported to the algorithm, which automatically learns from the experiment and uses the new information to decide on another formulation to test.
The scientists have created a free, open-source materials optimization platform called AutoOED that incorporates the same optimization algorithm, allowing scientists to create their own optimization.
One of the first tests for the system was using it to optimize formulations for a new 3D printing ink that hardens when it is exposed to ultraviolet light.
They identified six chemicals to use in the formulations and set the algorithm’s objective to uncover the best-performing material with respect to toughness, compression modulus (stiffness), and strength.
According to the scientists, the algorithm came up with 12 top performing materials that had optimal tradeoffs of the three different properties after testing only 120 samples.
Foshey and his collaborators say the process can be accelerated even further through the use of additional automation.
For instance, robots could be used to operate the dispensing and mixing systems in future versions of the system.
Image and content: MIT CSAIL