US 12,073,584 B2
Systems, methods, and media for manufacturing processes
Matthew C. Putman, Brooklyn, NY (US); Vadim Pinskiy, Wayne, NJ (US); Andrew Sundstrom, Brooklyn, NY (US); Aswin Raghav Nirmaleswaran, Brooklyn, NY (US); and Eun-Sol Kim, Cliffside Park, NJ (US)
Assigned to Nanotronics Imaging, Inc., Cuyahoga Falls, OH (US)
Filed by Nanotronics Imaging, Inc., Cuyahoga Falls, OH (US)
Filed on Mar. 9, 2021, as Appl. No. 17/195,746.
Application 17/195,746 is a continuation in part of application No. 17/091,393, filed on Nov. 6, 2020.
Claims priority of provisional application 62/986,987, filed on Mar. 9, 2020.
Claims priority of provisional application 62/932,063, filed on Nov. 7, 2019.
Claims priority of provisional application 62/931,448, filed on Nov. 6, 2019.
Claims priority of provisional application 62/931,453, filed on Nov. 6, 2019.
Prior Publication US 2021/0192779 A1, Jun. 24, 2021
Int. Cl. G06T 7/73 (2017.01); G05B 19/402 (2006.01); G05B 19/4093 (2006.01); G06N 20/00 (2019.01)
CPC G06T 7/73 (2017.01) [G05B 19/402 (2013.01); G05B 19/40932 (2013.01); G06N 20/00 (2019.01); G06T 2207/30164 (2013.01)] 17 Claims
OG exemplary drawing
 
1. A manufacturing system, comprising:
a first station and a second station, each of the first station and the second station configured to perform at least one step in a multi-step manufacturing process for a component;
a monitoring platform configured to monitor progression of the component throughout the multi-step manufacturing process; and
a control module configured to dynamically adjust processing parameters of a step of the multi-step manufacturing process to achieve a desired final quality metric for the component, the control module configured to perform operations, comprising:
receiving image data of tooling of the first station, wherein the first station is upstream of the second station;
identifying a set of keypoints on the tooling from the image data, the set of keypoints corresponding to position information of the tooling during processing at the first station;
projecting, by a machine learning model, a final quality metric for the component, based on the set of keypoints, the final quality metric representing a metric quality of the component that cannot be measured until the multi-step manufacturing process is complete; and
assigning the component to a class of components based on a comparison between the projected final quality metric and a canonical final quality metric for the component.