IP Library › Granted Patent US 12,734,761
Granted Patent B2
US 12,734,761 · App. 18/351,904 · Granted Sep 15, 2026

Splitting multidimensional printing models based on vulnerability metrics

Inventors: Jeremy R. Fox (Georgetown, TX); Jessica Nahulan (Markham, CA); Carolina Garcia Delgado (Zapopan, MX); Tiberiu Suto (Franklin, NY)
Assignee: International Business Machines Corporation
B29C64/393G06F3/121G06F3/1256B33Y50/02
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 12,734,761
App. No.
18/351,904
Granted
Sep 15, 2026
Kind
B2
Abstract

A computer-implemented method, a computer system and a computer program product split a virtual printing model according to a probability of multidimensional printing failure. The method includes obtaining a virtual printing model of a multidimensional object, where the virtual printing model comprises print layers. The method also includes determining that a printing risk score for a location on the multidimensional object is above a printing risk threshold. The method further includes mapping a set of print layers of the virtual printing model to the location on the multidimensional object. Lastly, the method includes sending the print layers of the virtual printing model to a multidimensional printer, wherein a mapped set of print layers is sent first.

Claims (65)

1 . A computer-implemented method for splitting multidimensional print jobs according to a probability of multidimensional printing failure, the computer-implemented method comprising:

receiving a virtual printing model of a multidimensional object, wherein the virtual printing model comprises print layers for a multidimensional printer;

splitting the virtual printing model into sets of print layers, wherein each set of print layers corresponds to a location of the multidimensional object that are sized according to requirements of the multidimensional printer;

determining a printing risk score for each location on the multidimensional object;

determining at least one of the printing risk score being above a printing threshold,

identifying a set of print layers of the virtual printing model as a vulnerable location on the multidimensional object based on the at least one of the printing risk score being above a printing threshold;

sending the set of print layers associated with the vulnerable location of the virtual printing model to a first printer in decreasing order of printing risk score;

sending remaining print layers of the virtual printing model to a second printer; and

detecting a print failure at the first printer;

in response to detecting the print failure at the first printer, blocking the second printer from printing the remaining print layers of the virtual printing model.

2 . The computer-implemented method of claim 1 , further comprising:

determining that a first printing risk score for a first location on the multidimensional object is higher than a second printing risk score for a second location on the multidimensional object, wherein both the first printing risk score and the second printing risk score are above the printing risk threshold;

identifying a first set of print layers of the virtual printing model associated with the first location on the multidimensional object and a second set of print layers of the virtual printing model associated with the second location on the multidimensional object; and

sending the first set of print layers of the virtual printing model to the multidimensional printer prior to the second set of print layers of the virtual printing model.

3 . The computer-implemented method of claim 1 , wherein the determining the printing risk score for the location on the multidimensional object further comprises using a machine learning model to predict the probability of multidimensional printing failure based on crowdsourced object printing failure data.

4 . The computer-implemented method of claim 1 , further comprising:

displaying the virtual printing model of the multidimensional object to a user, wherein a displayed virtual printing model includes an indication of the location on the multidimensional object;

monitoring user interactions with the location on the multidimensional object; and

updating the printing risk score for the location on the multidimensional object based on the user interactions.

5 . The computer-implemented method of claim 1 , further comprising:

identifying a type of the multidimensional object; and

updating the printing risk score for the location on the multidimensional object based on an identified type of multidimensional object.

6 . The computer-implemented method of claim 1 , further comprising generating a recommendation for a filament material to be used at the location on the multidimensional object based on the printing risk score for the location on the multidimensional object.

7 . A computer system for splitting multidimensional print jobs according to a probability of multidimensional printing failure, the computer system comprising:

one or more processors, one or more computer-readable memories, and one or more computer-readable storage media;

program instructions, stored on at least one of the one or more computer-readable storage media, when executed by at least one of the one or more processors via at least one of the one or more computer-readable memories, cause at least one of the one or more processors to receive a virtual printing model of a multidimensional object, wherein the virtual printing model comprises print layers for a multidimensional printer;

program instructions, stored on at least one of the one or more computer-readable storage media, when executed by at least one of the one or more processors via at least one of the one or more computer-readable memories, cause at least one of the one or more processors to split the virtual printing model into sets of print layers, wherein each set of print layers corresponds to a location of the multidimensional object that are sized according to requirements of the multidimensional printer;

program instructions, stored on at least one of the one or more computer-readable storage media, when executed by at least one of the one or more processors via at least one of the one or more computer-readable memories, cause at least one of the one or more processors to determine a printing risk score for each location on the multidimensional object;

program instructions, stored on at least one of the one or more computer-readable storage media, when executed by at least one of the one or more processors via at least one of the one or more computer-readable memories, cause at least one of the one or more processors to, in response to the printing risk score being above a printing risk threshold, identify the set of print layers of the virtual printing model as a vulnerable location on the multidimensional object;

program instructions, stored on at least one of the one or more computer-readable storage media, when executed by at least one of the one or more processors via at least one of the one or more computer-readable memories, cause at least one of the one or more processors to send the set of print layers associated with the vulnerable location of the virtual printing model to a first printer in decreasing order of printing risk score;

program instructions, stored on at least one of the one or more computer-readable storage media, when executed by at least one of the one or more processors via at least one of the one or more computer-readable memories, cause at least one of the one or more processors to send remaining print layers of the virtual printing model to a second printer; and

program instructions, stored on at least one of the one or more computer-readable storage media, when executed by at least one of the one or more processors via at least one of the one or more computer-readable memories, cause at least one of the one or more processors to, in response to detecting a print failure at the first printer, blocking the second printer from printing the remaining print layers of the virtual printing model.

8 . The computer system of claim 7 , further comprising:

program instructions, stored on at least one of the one or more computer-readable storage media, when executed by at least one of the one or more processors via at least one of the one or more computer-readable memories, cause at least one of the one or more processors to determine that a first printing risk score for a first location on the multidimensional object is higher than a second printing risk score for a second location on the multidimensional object, wherein both the first printing risk score and the second printing risk score are above the printing risk threshold;

program instructions, stored on at least one of the one or more computer-readable storage media, when executed by at least one of the one or more processors via at least one of the one or more computer-readable memories, cause at least one of the one or more processors to identify a first set of print layers of the virtual printing model associated with the first location on the multidimensional object and a second set of print layers of the virtual printing model associated with the second location on the multidimensional object; and

program instructions, stored on at least one of the one or more computer-readable storage media, when executed by at least one of the one or more processors via at least one of the one or more computer-readable memories, cause at least one of the one or more processors to send the first set of print layers of the virtual printing model to the multidimensional printer prior to the second set of print layers of the virtual printing model.

9 . The computer system of claim 7 , wherein the determining the printing risk score for the location on the multidimensional object further comprises using a machine learning model to predict the probability of multidimensional printing failure based on crowdsourced object printing failure data.

10 . The computer system of claim 7 , further comprising:

program instructions, stored on at least one of the one or more computer-readable storage media, when executed by at least one of the one or more processors via at least one of the one or more computer-readable memories, cause at least one of the one or more processors to display the virtual printing model of the multidimensional object to a user, wherein a displayed virtual printing model includes an indication of the location on the multidimensional object;

program instructions, stored on at least one of the one or more computer-readable storage media, when executed by at least one of the one or more processors via at least one of the one or more computer-readable memories, cause at least one of the one or more processors to monitor user interactions with the location on the multidimensional object; and

program instructions, stored on at least one of the one or more computer-readable storage media, when executed by at least one of the one or more processors via at least one of the one or more computer-readable memories, cause at least one of the one or more processors to update the printing risk score for the location on the multidimensional object based on the user interactions.

11 . The computer system of claim 7 , further comprising:

program instructions, stored on at least one of the one or more computer-readable storage media, when executed by at least one of the one or more processors via at least one of the one or more computer-readable memories, cause at least one of the one or more processors to identify a type of the multidimensional object; and

program instructions, stored on at least one of the one or more computer-readable storage media, when executed by at least one of the one or more processors via at least one of the one or more computer-readable memories, cause at least one of the one or more processors to update the printing risk score for the location on the multidimensional object based on an identified type of multidimensional object.

12 . The computer system of claim 7 , further comprising generating a recommendation for a filament material to be used at the location on the multidimensional object based on the printing risk score for the location on the multidimensional object.

13 . A computer program product for splitting multidimensional print jobs according to a probability of multidimensional printing failure, the computer program product comprising:

program instructions, stored on at least one of the one or more computer-readable storage media, when executed by at least one of one or more processors via at least one of the one or more computer-readable memories, cause at least one of the one or more processors to receive a virtual printing model of a multidimensional object, wherein the virtual printing model comprises print layers for a multidimensional printer;

program instructions, stored on at least one of the one or more computer-readable storage media, when executed by at least one of the one or more processors via at least one of the one or more computer-readable memories, cause at least one of the one or more processors to split the virtual printing model into sets of print layers, wherein each set of print layers corresponds to a location of the multidimensional object that are sized according to requirements of the multidimensional printer;

program instructions, stored on at least one of the one or more computer-readable storage media, when executed by at least one of the one or more processors via at least one of the one or more computer-readable memories, cause at least one of the one or more processors to determine a printing risk score for each location on the multidimensional object;

program instructions, stored on at least one of the one or more computer-readable storage media, when executed by at least one of the one or more processors via at least one of the one or more computer-readable memories, cause at least one of the one or more processors to, in response to the printing risk score being above a printing risk threshold, identify the set of print layers of the virtual printing model as a vulnerable location on the multidimensional object;

program instructions, stored on at least one of the one or more computer-readable storage media, when executed by at least one of the one or more processors via at least one of the one or more computer-readable memories, cause at least one of the one or more processors to send the set of print layers associated with the vulnerable location of the virtual printing model to a first printer in decreasing order of printing risk score;

program instructions, stored on at least one of the one or more computer-readable storage media, when executed by at least one of the one or more processors via at least one of the one or more computer-readable memories, cause at least one of the one or more processors to send remaining print layers of the virtual printing model to a second printer; and

program instructions, stored on at least one of the one or more computer-readable storage media, when executed by at least one of the one or more processors via at least one of the one or more computer-readable memories, cause at least one of the one or more processors to, in response to detecting a print failure at the first printer, blocking the second printer from printing the remaining print layers of the virtual printing model.

14 . The computer program product of claim 13 , further comprising:

program instructions, stored on at least one of the one or more computer-readable storage media, when executed by at least one of the one or more processors, cause at least one of the one or more processors to determine that a first printing risk score for a first location on the multidimensional object is higher than a second printing risk score for a second location on the multidimensional object, wherein both the first printing risk score and the second printing risk score are above the printing risk threshold;

program instructions, stored on at least one of the one or more computer-readable storage media, when executed by at least one of the one or more processors, cause at least one of the one or more processors to identify a first set of print layers of the virtual printing model associated with the first location on the multidimensional object and a second set of print layers of the virtual printing model associated with the second location on the multidimensional object; and

program instructions, stored on at least one of the one or more computer-readable storage media, when executed by at least one of the one or more processors, cause at least one of the one or more processors to send the first set of print layers of the virtual printing model to the multidimensional printer prior to the second set of print layers of the virtual printing model.

15 . The computer program product of claim 13 , wherein the determining the printing risk score for the location on the multidimensional object further comprises using a machine learning model to predict the probability of multidimensional printing failure based on crowdsourced object printing failure data.

16 . The computer program product of claim 13 , further comprising:

program instructions, stored on at least one of the one or more computer-readable storage media, when executed by at least one of the one or more processors, cause at least one of the one or more processors to display the virtual printing model of the multidimensional object to a user, wherein a displayed virtual printing model includes an indication of the location on the multidimensional object;

program instructions, stored on at least one of the one or more computer-readable storage media, when executed by at least one of the one or more processors, cause at least one of the one or more processors to monitor user interactions with the location on the multidimensional object; and

program instructions, stored on at least one of the one or more computer-readable storage media, when executed by at least one of the one or more processors, cause at least one of the one or more processors to update the printing risk score for the location on the multidimensional object based on the user interactions.

17 . The computer program product of claim 13 , further comprising:

program instructions, stored on at least one of the one or more computer-readable storage media, when executed by at least one of the one or more processors, cause at least one of the one or more processors to identify a type of the multidimensional object; and

program instructions, stored on at least one of the one or more computer-readable storage media, when executed by at least one of the one or more processors, cause at least one of the one or more processors to update the printing risk score for the location on the multidimensional object based on an identified type of multidimensional object.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Jul 13, 2023
From: FOX, JEREMY R.; NAHULAN, JESSICA; GARCIA DELGADO, CAROLINA; SUTO, TIBERIU
To: INTERNATIONAL BUSINESS MACHINES CORPORATION
Reel/Frame 064247/0130 →
Continuity (1)
Related Publication 20250018657A1 · Jan 16, 2025
References Cited (31)
US 7313777B1 · Yang et al. · 2007 [cited by applicant]
US 8713519B2 · Lininger · 2014 [cited by examiner]
US 9636871B2 · Butler et al. · 2017 [cited by applicant]
US 9846556B2 · Cudak et al. · 2017 [cited by applicant]
US 10000024B2 · Jang · 2018 [cited by applicant]
US 10611086B2 · Gain · 2020 [cited by examiner]
US 10692185B2 · Wang · 2020 [cited by applicant]
US 20120105903A1 · Pettis · 2012 [cited by examiner]
US 20140058959A1 · Isbjornssund · 2014 [cited by examiner]
US 20140074274A1 · Douglas · 2014 [cited by examiner]
US 20140291886A1 · Mark · 2014 [cited by examiner]
US 20150321425A1 · Stava · 2015 [cited by examiner]
US 20160086258A1 · Romes · 2016 [cited by examiner]
US 20160210312A1 · Webb · 2016 [cited by examiner]
US 20170031639A1 · Cudak · 2017 [cited by examiner]
US 20170220946A1 · Thielen et al. · 2017 [cited by applicant]
US 20180260089A1 · Hudson · 2018 [cited by examiner]
US 20190278254A1 · Kumar · 2019 [cited by examiner]
US 20200167648A1 · Siegl · 2020 [cited by examiner]
US 20220138500A1 · Levinshtein · 2022 [cited by applicant]
US 20220297380A1 · Lipowitch · 2022 [cited by applicant]
US 20220301106A1 · Liu · 2022 [cited by applicant]
US 20220392156A1 · Yngesjö · 2022 [cited by applicant]
US 20240157652A1 · Reddy · 2024 [cited by examiner]
CN 110119255A · 2019 [cited by applicant]
CN 216658924U · 2022 [cited by applicant]
CN 114818401A · 2022 [cited by examiner]
Beamler, “Printability Check”, Beamler.com, May 5, 2018, 9 pgs, Retrieved from the Internet: <https://www.beamler.com/printability-check/>. [cited by applicant]
CDI, “3D & 4D Technology Market Is Expected to Reach USD 931.17B”, Contrive Datum Insights, Globenewswire.com, [accessed Jun. 6, 2023], 8 pgs., Retrieved from the Internet: <https://www.globenewswire.com/en/news-release… [cited by applicant]
IBM, “3D Printing in the Transportation Industry”, IBM.com, [accessed Jun. 6, 2023], 5 pgs., Retrieved from the Internet: <https://www.IBM.com/thought-leadership/institute-business-value/en-us/report/3d-printing>. [cited by applicant]
Menon, et al., “PULSE: Self-Supervised Photo Upsampling via Latent Space Exploration of Generative Models”, arXiv:2003.03808v3 [cs.CV], Jul. 20, 2020, 20 pgs. [cited by applicant]