US 11,752,700 B2
Systems and methods for formulating material in a data-driven manner
Michael J. Foshey, Quincy, MA (US); Timothy P. Erps, Salem, MA (US); Mina Konakovic Lukovic, Belgrade (RS); Wojciech Matusik, Lexington, MA (US); Wan Shou, Allston, MA (US); Klaus Stoll, Ludwigshafen (DE); Bernhard Ulrich von Vacano, Ludwigshafen (DE); and Hanns Hagen Goetzke, Ludwigshafen (DE)
Assigned to MASSACHUSETTS INSTITUTE OF TECHNOLOGY, Cambridge, MA (US); and BASF SE
Filed by Massachusetts Institute of Technology, Cambridge, MA (US); and BASF SE, Ludwigshafen am Rhein (DE)
Filed on Oct. 1, 2020, as Appl. No. 17/61,548.
Claims priority of provisional application 62/909,177, filed on Oct. 1, 2019.
Prior Publication US 2021/0095141 A1, Apr. 1, 2021
Int. Cl. B29C 64/393 (2017.01); C09D 11/101 (2014.01); B29C 64/124 (2017.01); B29C 64/112 (2017.01); B33Y 70/00 (2020.01); G06F 18/2415 (2023.01)
CPC B29C 64/393 (2017.08) [B29C 64/112 (2017.08); B29C 64/124 (2017.08); B33Y 70/00 (2014.12); C09D 11/101 (2013.01); G06F 18/24155 (2023.01)] 12 Claims
OG exemplary drawing
 
1. A system for formulating a material, comprising:
a sample automation system configured to output one or more batches of material samples, each batch of the one or more batches including a plurality of material samples, and at least one of the following comprising samples having different properties: (a) the plurality of material samples of each batch, or (b) the material samples of a plurality of batches; and
an optimization engine configured to receive data about the one or more batches of material samples outputted by the sample automation system and output one or more subsequently suggested batches of material samples, each subsequently suggested batch of the one or more subsequently suggested batches including a plurality of subsequently suggested material samples, the plurality of subsequently suggested material samples comprising material samples having a plurality of different formulations selected from a design space comprising a set of possible formulations,
wherein the optimization engine is configured to generate, for each of a plurality of performance objectives, predicted performance characteristics of the design space based on the received data,
wherein the optimization engine is configured to determine, for each of the plurality of performance objectives, a predicted Pareto front based on the predicted performance characteristics of the design space,
wherein the optimization engine is configured to select the plurality of different formulations from untested regions of the design space based on the predicted Pareto front for at least one of the plurality of performance objectives, and
wherein the sample automation system is configured to output one or more additional batches of material samples based on the one or more subsequently suggested batches of material samples outputted by the optimization engine.