Accelerating the discovery of new materials for 3D printing

The growing popularity of 3D printing for manufacturing all sorts of items from customized medical devices to affordable homes has created more claim for new 3D printing materials designed for very specific uses.

To cut down on the time it takes to find these new materials investigationers at MIT have developed a data-driven process that uses machine learning to optimize new 3D printing materials with multiple characteristics like toughness and compression force.

By streamlining materials outgrowth the order lowers costs and lessens the environmental contact by reducing the amount of chemical ruin. The machine learning algorithm could also spur alteration by suggesting sole chemical formulations that ethnical instinct might miss. 

’Materials outgrowth is quiet very much a manual process. A chemist goes into a lab mixes ingredients by hand makes specimens tests them and comes to a terminal formulation. But rather than having a chemist who can only do a couple of iterations over a span of days our order can do hundreds of iterations over the same time span’ says Mike Foshey a habitual engineer and project director in the Computational Design and Fabrication Group (CDFG) of the Computer Science and Artificial Intelligence Laboratory (CSAIL) and co-lead creator of the paper.

Additional creators include co-lead creator Timothy Erps a technical companion in CDFG; Mina Konakovic Lukovic a CSAIL postdoc; Wan Shou a preceding MIT postdoc who is now an helper professor at the University of Arkansas; senior creator Wojciech Matusik professor of electrical engineering and computer science at MIT; and Hanns Hagen Geotzke Herve Dietsch and Klaus Stoll of BASF. The investigation was published today in Science Advances.

Optimizing findy

In the order the investigationers developed an optimization algorithm performs much of the trial-and-error findy process.

A material developer selects a few ingredients inputs details on their chemical compositions into the algorithm and defines the habitual properties the new material should have. Then the algorithm increases and decreases the amounts of those components (like turning knobs on an amplifier) and checks how each formula affects the materials properties precedently arriving at the mental union.

Then the developer mixes processes and tests that specimen to find out how the material verity performs. The developer reports the results to the algorithm which automatically learns from the trial and uses the new information to decide on another formulation to test.

’We ponder for a number of applications this would outperform the customary order owing you can rely more heavily on the optimization algorithm to find the optimal solution. You wouldnt need an expert chemist on hand to preselect the material formulations’ Foshey says.

The investigationers have created a free open-source materials optimization platform named AutoOED that incorporates the same optimization algorithm. AutoOED is a full software package that also allows investigationers to conduct their own optimization.

Making materials

The investigationers tested the order by using it to optimize formulations for a new 3D printing ink that hardens when it is unprotected to ultraviolet light.

They identified six chemicals to use in the formulations and set the algorithms extrinsic to reveal the best-performing material with respect to toughness compression modulus (stiffness) and force.

Maximizing these three properties manually would be especially challenging owing they can be adverse; for entreaty the powerfulest material may not be the stiffest. Using a manual process a chemist would typically try to maximize one property at a time resulting in many trials and a lot of ruin.

The algorithm came up with 12 top performing materials that had optimal tradeoffs of the three different properties behind testing only 120 specimens.

Foshey and his collaborators were surprised by the wide difference of materials the algorithm was able to engender and say the results were far more varied than they expected based on the six ingredients. The order encourages exploration which could be especially advantageous in situations when specific material properties cant be easily finded intuitively.

Faster in the forthcoming

The process could be accelerated even more through the use of additional automation. Researchers mixed and tested each specimen by hand but robots could act the dispensing and mixing orders in forthcoming versions of the order Foshey says.

Farther down the road the investigationers would also like to test this data-driven findy process for uses over developing new 3D printing inks.

’This has wide applications athwart materials science in general. For entreaty if you wanted to design new types of batteries that were higher efficiency and lower cost you could use a order like this to do it. Or if you wanted to optimize paint for a car that performed well and was environmentally well-inclined this order could do that too’ he says.

Because it presents a orderatic access for uniteing optimal materials this work could be a major step toward realizing high accomplishment structures says Keith A. Brown helper professor in the Department of Mechanical Engineering at Boston University.

’The centre on novel material formulations is specially encouraging as this is a factor that is frequently overlooked by investigationers who are constrained by commercially useful materials. And the union of data-driven orders and trialal science allows the team to unite materials in an efficient mode. Since trialal efficiency is something with which all trialers can unite the orders here have a chance of motivating the aggregation to assume more data-driven practices’ he says.

The investigation was supported by BASF