IP Library › Granted Patent US 12,461,511
Granted Patent B2
US 12,461,511 · App. 17/658,386 · Granted Nov 4, 2025

Development of a product using a process control plan digital twin

Inventors: Guijun Wang (Bellevue, WA); Joseph R. Dvorak (Everett, WA); Lu Yue (Bellevue, WA); Jeff Miller (Everett, WA); Edward Li (Everett, WA); Raluca M. Dumitrache (Everett, WA); Christopher Matsuoka (Tukwila, WA); Priya Sukumaran (Bangalore, IN); Michael J. Christian (Berkeley, MO); Tripti Mandal (Bangalore, IN)
Assignee: The Boeing Company
G05B19/41865G05B19/4183G05B19/41885G06F30/15G06Q50/04
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12,461,511
App. No.
17/658,386
Granted
Nov 4, 2025
Kind
B2
Abstract

A method of developing a product is provided that includes generating a digital system model (DSM) that describes the product and a manufacturing process for the product, and generating a digital twin (DTw) of an instance of a component of the manufacturing process, the DTw including a digital replica of the instance. The method includes receiving attribute data for attributes of process/process characteristics subject to sources of variation that affect product quality. The digital replica is executed with input of the attribute data, and thereby updating the DTw to replicate the instance of the component of the manufacturing process as performed. A data analysis of the manufacturing process is performed based on the DTw as updated, and the manufacturing process is modified based on the data analysis to reduce variability in one or more product characteristics. The DTws of multiple instances may be used to generate further improvement.

Claims (52)

1 . An apparatus for developing a product, the apparatus comprising:

a memory configured to store computer-readable program code; and

processing circuitry configured to access the memory, and execute the computer-readable program code to cause the apparatus to at least:

generate a digital system model (DSM) of authoritative data that describes the product and a manufacturing process for producing the product, including machinery, materials, methods, facility and manpower used during the manufacturing process;

generate digital twins (DTws) of a plurality of respective instances of a component of the manufacturing process from the DSM, the DTws including digital replicas of the instances of the component of the manufacturing process including one or more of the machinery, materials, methods, facility or manpower used during the manufacturing process, wherein the component of the manufacturing process includes a control plan that identifies process characteristics and control methods for sources of variation to which the process characteristics are subject;

receive attribute data measured as multiple runs of the manufacturing process are performed to produce multiples of the product, the attribute data for attributes of the process characteristics identified by the control plan that are subject to the sources of variation of one or more of the machinery, materials, methods, facility or manpower that cause variation in product characteristics;

execute the digital replicas with input of the attribute data, and thereby update the DTws to replicate the respective instances of the component of the manufacturing process as performed, wherein updating the DTws comprises updating the plurality of respective instances of the control plan using the attribute data for the attributes of the process characteristics identified by the control plan;

perform a data analysis of the manufacturing process based on the DTws as updated by at least extracting a correlation of measurements of a plurality of manufacturing variables and quality metrics, wherein the manufacturing variables comprise environmental control data and machine attributes, and wherein the quality metrics comprise quality classifications of manufactured products; and

modify the product or the manufacturing process based on the data analysis to reduce variability in one or more of the product characteristics by at least encoding the correlation to generate a machine control dataset and feeding the machine control dataset to a machine that performs the manufacturing process.

2 . The apparatus of claim 1 , wherein the control plan further identifies verification and validation methods for the attributes of the process characteristics, and

wherein the apparatus caused to generate the DTws of the plurality of respective instances of the component includes the apparatus caused to generate a DTw of an instance of the control plan, and the apparatus caused to modify the manufacturing process includes the apparatus caused to modify one or more of the control methods.

3 . The apparatus of claim 1 further, wherein the apparatus is caused to establish a digital thread from the DTws that links the authoritative data of the DSM, and the attribute data measured as the manufacturing process is performed.

4 . The apparatus of claim 1 , wherein the apparatus caused to generate the DSM includes the apparatus caused to:

access a metamodel of the component of the manufacturing process that specifies a logical schema for the component; and

encode the authoritative data for the component according to the logical schema.

5 . The apparatus of claim 1 , wherein the component of the manufacturing process further includes one or more of the machinery used during the manufacturing process, the one or more of the machinery expressed as computer models stored in a catalog, separate and distinct from the DSM and the DTws, and

wherein the apparatus caused to generate the DSM includes the apparatus caused to generate the DSM that calls out the computer models, and the apparatus caused to generate the DTws includes the apparatus caused to generate instances of the computer models stored in the catalog.

6 . The apparatus of claim 1 , wherein the component of the manufacturing process further includes one or more of the methods used during the manufacturing process, the one or more of the methods expressed as algorithms stored in a catalog, separate and distinct from the DSM and the DTws, and

wherein the apparatus caused to generate the DSM includes the apparatus caused to generate the DSM that calls out the methods, and the apparatus caused to generate the DTws includes the apparatus caused to generate instances of the algorithms stored in the catalog.

7 . The apparatus of claim 1 , wherein the component of the manufacturing process further includes one or more of the machinery and methods used during the manufacturing process, and the apparatus caused to generate the DTws includes the apparatus caused to:

identify the one or more of the machinery and methods from the DSM; and

generate the DTws including instances of computer models and algorithms that express the one or more of the machinery and methods.

8 . The apparatus of claim 7 , wherein the apparatus caused to generate the DTws further includes the apparatus caused to configure the DTws in which the instances of the computer models and algorithms are connected with sources of the attribute data.

9 . The apparatus of claim 8 , wherein the apparatus caused to execute the digital replicas includes the apparatus caused to execute the computer models and algorithms, with input of the attribute data from the sources of the attribute data.

10 . The apparatus of claim 1 , wherein performing the data analysis of the manufacturing process includes extracting a correlation of measurements of multiple manufacturing variables and quality metrics.

11 . The apparatus of claim 1 , wherein the data analysis is performed based on the DTws as updated from execution of the digital replicas to replicate the multiple instances of the component, and

wherein the apparatus caused to modify the product or the manufacturing process includes the apparatus caused to modify the authoritative data of the DSM based on the data analysis of the multiple instances of the component.

12 . A method of developing a product, the method comprising:

generating a digital system model (DSM) of authoritative data that describes the product and a manufacturing process for producing the product, including machinery, materials, methods, facility and manpower used during the manufacturing process;

generating digital twins (DTws) of a plurality of respective instances of a component of the manufacturing process from the DSM, the DTws including digital replicas of the instances of the component of the manufacturing process including one or more of the machinery, materials, methods, facility or manpower used during the manufacturing process, wherein the component of the manufacturing process includes a control plan that identifies process characteristics and control methods for sources of variation to which the process characteristics are subject;

receiving attribute data measured as multiple runs of the manufacturing process are performed to produce multiples of the product, the attribute data for attributes of the process characteristics identified by the control plan that are subject to the sources of variation of one or more of the machinery, materials, methods, facility or manpower that cause variation in product characteristics;

executing the digital replicas with input of the attribute data, and thereby updating the DTws to replicate the respective instances of the component of the manufacturing process as performed;

performing a data analysis of the manufacturing process based on the DTws as updated by at least extracting a correlation of measurements of a plurality of manufacturing variables and quality metrics, wherein the manufacturing variables comprise environmental control data and machine attributes, and wherein the quality metrics comprise quality classifications of manufactured products; and

modifying the product or the manufacturing process based on the data analysis to reduce variability in one or more of the product characteristics by at least encoding the correlation to generate a machine control dataset and feeding the machine control dataset to a machine that performs the manufacturing process.

13 . The method of claim 12 , wherein the control plan further identifies verification and validation methods for the attributes of the process characteristics, and

wherein generating the DTws of the respective instances of the component includes generating a DTw of an instance of the control plan, and modifying the manufacturing process includes modifying one or more of the control methods.

14 . The method of claim 12 further comprising establishing a digital thread from the DTws that links the authoritative data of the DSM, and the attribute data measured as the manufacturing process is performed.

15 . The method of claim 12 , wherein generating the DSM includes:

accessing a metamodel of the component of the manufacturing process that specifies a logical schema for the component; and

encoding the authoritative data for the component according to the logical schema.

16 . The method of claim 12 , wherein the component of the manufacturing process further includes one or more of the machinery used during the manufacturing process, the one or more of the machinery expressed as computer models stored in a catalog, separate and distinct from the DSM and the DTws, and

wherein generating the DSM includes generating the DSM that calls out the computer models, and generating the DTws includes generating instances of the computer models stored in the catalog.

17 . The method of claim 12 , wherein the component of the manufacturing process further includes one or more of the methods used during the manufacturing process, the one or more of the methods expressed as algorithms stored in a catalog, separate and distinct from the DSM and the DTws, and

wherein generating the DSM includes generating the DSM that calls out the methods, and generating the DTws includes generating instances of the algorithms stored in the catalog.

18 . The method of claim 12 , wherein the component of the manufacturing process further includes one or more of the machinery and methods used during the manufacturing process, and generating the DTws includes:

identifying the one or more of the machinery and methods from the DSM; and

generating the DTws including instances of computer models and algorithms that express the one or more of the machinery and methods.

19 . The method of claim 18 , wherein generating the DTws further includes configuring the DTws in which the instances of the computer models and algorithms are connected with sources of the attribute data.

20 . The method of claim 19 , wherein executing the digital replicas includes executing the computer models and algorithms, with input of the attribute data from the sources of the attribute data.

21 . The method of claim 12 , wherein performing the data analysis of the manufacturing process includes extracting a correlation of measurements of multiple manufacturing variables and quality metrics.

22 . The method of claim 12 , wherein the data analysis is performed based on the DTws as updated from execution of the digital replicas to replicate the multiple instances of the component, and

wherein modifying the product or the manufacturing process includes modifying the authoritative data of the DSM based on the data analysis of the multiple instances of the component.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Apr 7, 2022
From: WANG, GUIJUN; DVORAK, JOSEPH R.; YUE, LU; MILLER, JEFF; LI, EDWARD; DUMITRACHE, RALUCA M.; MATSUOKA, CHRISTOPHER; SUKUMARAN, PRIYA; CHRISTIAN, MICHAEL J.; MANDAL, TRIPTI
To: THE BOEING COMPANY
Reel/Frame 059535/0245 →
Priority Claims (1)
IN 202111021830 · May 14, 2021 · national
Continuity (1)
Related Publication 20220365518A1 · Nov 17, 2022
References Cited (30)
US 6035305A · Stevey et al. · 2000 [cited by applicant]
US 6681145B1 · Greenwood et al. · 2004 [cited by applicant]
US 8239362B1 · Frazier · 2012 [cited by applicant]
US 8880381B2 · Mattikalli et al. · 2014 [cited by applicant]
US 8983881B2 · Fox et al. · 2015 [cited by applicant]
US 10204323B1 · Miller et al. · 2019 [cited by applicant]
US 11631060B2 · Davis · 2023 [cited by examiner]
US 20090138874A1 · Beck et al. · 2009 [cited by applicant]
US 20180137219A1 · Goldfarb · 2018 [cited by examiner]
US 20180196409A1 · Ben-Bassat · 2018 [cited by examiner]
US 20180362190A1 · Chambers · 2018 [cited by examiner]
US 20190304673A1 · Neti · 2019 [cited by examiner]
US 20200265329A1 · Thomsen · 2020 [cited by examiner]
US 20200334402A1 · Grefen · 2020 [cited by applicant]
US 20200394351A1 · Roemerman · 2020 [cited by examiner]
US 20220067233A1 · Blackwell · 2022 [cited by examiner]
US 20220083926A1 · Miller · 2022 [cited by examiner]
US 20220100851A1 · Mehrotra · 2022 [cited by examiner]
US 20220229424A1 · Linder · 2022 [cited by examiner]
US 20220277119A1 · Brucksch · 2022 [cited by examiner]
EP 3968110A1 · 2022 [cited by applicant]
Reid, J. & Rhodes, D. Digital System Models: An investigation of the non-technical challenges and research needs. 2016 Conference on Systems Engineering Research, Systems Engineering Advancement Research Initiative, Mas… [cited by applicant]
Magni, A. et al. Leveraging Digital Twin Technology in Model-Based Systems Engineering. Intelligent Systems Technology, Inc., Los Angeles, CA, and Research and Engineering, Washington, DC, published Jan. 30, 2019, 13 pa… [cited by applicant]
Aerospace Series—Requirements for Advanced Product Quality Planning and Production Part Approval Process. AS9145, Aerospace Standard, SAE International. Issued Nov. 2016. 29 pages. [cited by applicant]
Canadian Intellectual Property Office, Office Action and Search Report Issued in Application No. 3,155,163, Feb. 8, 2024, 7 pages. [cited by applicant]
Extended European Search Report in the corresponding European patent application No. 22167923, mailed Sep. 30, 2022. 2 pages. [cited by applicant]
Digital Twin: Definition & Value. An AIAA and AIA Position Paper, authored by the AIAA Digital Engineering Integration Committee, AIAA and Aerospace Industries Association (AIA), pp. 1-16, Dec. 1, 2020. 16 pages. Retrie… [cited by applicant]
Wagner, R. et al. Digital DNA in quality control cycles of high-precision products. CIRP Annals, Elsevier BV, vol. 69, No. 1, pp. 373-376, Jan. 1, 2020. 4 pages. <DOI: 10.1015/j.cirp.2020.03.020>. [cited by applicant]
European Patent Office, Office Action Issued in Application No. 22167923.6, Jan. 31, 2025, Netherlands, 10 pages. [cited by applicant]
Canadian Intellectual Property Office, Office Action Issued in Application No. 3,155,163, May 23, 2025, 7 pages. [cited by applicant]