US 11,693,388 B2
Methods and apparatus for machine learning predictions of manufacturing processes
Valerie R. Coffman, Washington, DC (US); Mark Wicks, Alexandria, VA (US); and Daniel Wheeler, Darnestown, MD (US)
Assigned to Xometry, Inc., Gaithersburg, MD (US)
Filed by Xometry, Inc., Gaithersburg, MD (US)
Filed on Aug. 10, 2021, as Appl. No. 17/398,409.
Application 17/398,409 is a continuation of application No. 16/454,756, filed on Jun. 27, 2019, granted, now 11,086,292, issued on Aug. 10, 2021.
Application 16/454,756 is a continuation of application No. 16/113,835, filed on Aug. 27, 2018, granted, now 10,338,565, issued on Jul. 2, 2019.
Application 16/113,835 is a continuation of application No. 15/721,208, filed on Sep. 29, 2017, granted, now 10,061,300, issued on Aug. 28, 2018.
Prior Publication US 2021/0365003 A1, Nov. 25, 2021
This patent is subject to a terminal disclaimer.
Int. Cl. G05B 19/4097 (2006.01); G06N 7/00 (2023.01); G06N 3/12 (2023.01); G06N 20/00 (2019.01); G06N 20/20 (2019.01); G06N 3/126 (2023.01); G06N 7/01 (2023.01); G06N 5/04 (2023.01); G06N 3/045 (2023.01)
CPC G05B 19/4097 (2013.01) [G06N 3/126 (2013.01); G06N 7/01 (2023.01); G06N 20/00 (2019.01); G06N 20/20 (2019.01); G05B 2219/35134 (2013.01); G05B 2219/35204 (2013.01); G06N 3/045 (2023.01); G06N 5/04 (2013.01)] 22 Claims
OG exemplary drawing
 
1. One or more non-transitory computer memory devices storing software instruction for controlling one or more processors to provide:
a graphical user interface configured to receive, at a processor and from a remote compute device, a manufacturing process request, wherein the manufacturing process request includes a digital model representative of a physical object to be manufactured; and
a predictive engine configured to generate at least one non-deterministic predictive value associated with manufacturing the physical object, wherein the predictive engine is configured based at least in part upon the digital model or upon a set of features derived from the digital model, and based at least in part upon one or more machine learning models;
wherein at least one of the one or more machine learning models is trained using a set of previously manufactured physical objects; and
wherein the graphical user interface is also configured to provide a prediction report associated with manufacturing the physical object, the prediction report including information based upon the at least one non-deterministic predictive value.