US 11,698,623 B2
Methods and apparatus for machine learning predictions of manufacture processes
Valerie R. Coffman, Washington, DC (US); Yuan Chen, Rockville, MD (US); Luke S. Hendrix, Bethesda, MD (US); William J. Sankey, College Park, MD (US); Joshua Ryan Smith, Washington, DC (US); and Daniel Wheeler, Darnestown, MD (US)
Assigned to Xometry, Inc., Gaithersburg, MD (US)
Filed by Xometry, Inc., Gaithersburg, MD (US)
Filed on May 23, 2022, as Appl. No. 17/750,549.
Application 17/750,549 is a continuation of application No. 16/928,499, filed on Jul. 14, 2020, granted, now 11,347,201.
Application 16/928,499 is a continuation of application No. 16/786,454, filed on Feb. 10, 2020, granted, now 10,712,727, issued on Jul. 14, 2020.
Application 16/786,454 is a continuation of application No. 16/395,940, filed on Apr. 26, 2019, granted, now 10,558,195, issued on Feb. 11, 2020.
Application 16/395,940 is a continuation of application No. 16/046,519, filed on Jul. 26, 2018, granted, now 10,274,933, issued on Apr. 30, 2019.
Application 16/046,519 is a continuation of application No. 15/340,338, filed on Nov. 1, 2016, granted, now 10,281,902, issued on May 7, 2019.
Prior Publication US 2022/0365509 A1, Nov. 17, 2022
Int. Cl. G05B 19/4097 (2006.01); G06N 20/00 (2019.01); G05B 19/401 (2006.01); G06F 30/00 (2020.01); G06N 20/20 (2019.01); G06N 5/04 (2023.01)
CPC G05B 19/4097 (2013.01) [G05B 19/401 (2013.01); G06F 30/00 (2020.01); G06N 5/04 (2013.01); G06N 20/00 (2019.01); G06N 20/20 (2019.01); G05B 2219/35134 (2013.01); G05B 2219/35499 (2013.01); Y02P 90/02 (2015.11)] 2 Claims
OG exemplary drawing
 
1. A non-transitory memory device including instructions stored thereon for directing one or more computer processors to provide a graphical interface tool for providing predictions of manufacturing processes, the instructions comprising steps for:
receiving by the graphical interface tool an electronic file including a digital model representative of a physical object to be manufactured;
receiving by the graphical interface tool at least one manufacturing parameter taken from a group consisting of: an identification of a manufacturing machine, an identification of a fabrication material, or an identification of a manufacturing process; and
returning by the graphical interface tool, in near real-time or faster, responsive information associated with manufacturing the physical object, the responsive information including information related at least to a predictive value generated by a predictive engine;
wherein the predictive value generated by the predictive engine is generated by the predictive engine based at least in part upon (a) at least one of a set of parameters associated with the digital model or information derived from the set of parameters, and (b) one or more neural network machine learning models, at least one of the one or more neural network machine learning models trained using a collection of digital models of a domain of mechanical objects;
wherein the at least one predictive value corresponds to one or more of the following: predicted cost, set-up time, cycle time, a number of Computer Numerical Control (CNC) operations, requirement of a mill machine, requirement of a lathe machine, requirement of a sheet metal process, a type of blank used, or a type of fixture used; and
wherein at least one of the one or more neural network machine learning models is selected from an available set of a plurality of neural network machine learning models based upon the received manufacturing parameter.