Vision system for identifying support structures of 3D printed components

Patent metadata

Field	Value
Publication number	US-12496782-B2
Application number	US-202118003755-A
Country	US
Kind code	B2
Filing date	Jul 8, 2021
Priority date	Jul 9, 2020
Publication date	Dec 16, 2025
Grant date	Dec 16, 2025

Abstract

A system and method are described for post-processing a 3D printed component. For example, support structures for the 3D printed component may be removed during post-processing. In the system and method, a first image of a component is stored in memory. A second image of a 3D printed component corresponding to the component is also captured. One or more cutting paths between the 3D printed component and the support structures is then determined based on the first image and the second image. The 3D printed component may then be autonomously separated from the support structures by cutting through the cutting path.

First claim

The invention claimed is:

1 . A method of post-processing a 3D printed component, comprising:
storing a first image of a component in memory; determining a cutting path between the 3D printed component and a support structure attached to the 3D printed component based on the first image, in which the cutting path is visible or in which regions are generated to define the component and the support structure; capturing a second image of an actual 3D printed component, the actual 3D printed component corresponding to the component of the first image; in response to the second image differing from the first image beyond a threshold, updating the first image to adjust the first image and the cutting path, wherein the first image is updated based on differences between the first image and the second image; and outputting the adjusted cutting path to a post-processing system for further processing of the 3D printed component.

2 . The method according to claim 1 , wherein the post-processing system is a cutting system, and further comprising cutting through the 3D printed component or the support structure along the cutting path to separate the 3D printed component from the support structure.

3 . The method according to claim 2 , wherein the cutting comprises milling, laser cutting or sawing through the 3D printed component or the support structure.

4 . The method according to claim 2 , wherein a plurality of the first image are stored in the memory, at least some of the plurality of the first image includes the 3D printed component and the support structure attached thereto, and further including learning a location of a connection between the 3D printed component and the support structure from the plurality of the first image with machine learning or artificial intelligence.

5 . The method according to claim 2 , wherein a plurality of the second image are captured from different 3D printed components, each of the plurality of the second image includes the 3D printed component and the support structure attached thereto, and further including learning a location of a connection between the 3D printed component and the support structure from the plurality of the second image with machine learning or artificial intelligence.

6 . The method according to claim 2 , wherein the first image is a synthetic image and/or wherein the second image is an RGB image, depth image, cloud of points or line scan.

7 . The method according to claim 1 , wherein a plurality of the first image are stored in the memory, at least some of the plurality of the first image includes the 3D printed component and the support structure attached thereto, and further including learning a location of a connection between the 3D printed component and the support structure from the plurality of the first image with machine learning or artificial intelligence.

8 . The method according to claim 1 , wherein a plurality of the second image are captured from different 3D printed components, each of the plurality of the second image includes the 3D printed component and the support structure attached thereto, and further including learning a location of a connection between the 3D printed component and the support structure from the plurality of the second image with machine learning or artificial intelligence.

9 . The method according to claim 1 , wherein the first image is a synthetic image and/or wherein the second image is an RGB image, depth image, cloud of points or line scan.

10 . The method according to claim 1 , further comprising a database of a plurality of the first image and a plurality of the second image, wherein the cutting path is determined based on machine learning or artificial intelligence using the database.

11 . The method according to claim 1 , wherein the first image is generated from a CAD model of the component and/or wherein the first image is captured from another 3D printed component; and
wherein the first image is updated based on the differences between the first image and the second image.

12 . The method according to claim 11 , wherein two different second images of the 3D printed component are captured of two different regions of the 3D printed component, each second image being of a different region, and two different regions in the first image corresponding to the two different regions of the 3D printed component are updated based on the two different second images.

13 . The method according to claim 1 , wherein the cutting path is through the support structure and is spaced away from the 3D printed component.

14 . The method according to claim 1 , wherein the support structure is attached to a base upon which the 3D printed component is formed or wherein the support structure is attached at opposite sides to different portions of the 3D printed component.

15 . The method according to claim 1 , wherein the 3D printed component and the support structure are both metallic and/or
wherein the 3D printed component and the support structure are both the same material with the same curing.

16 . The method according to claim 1 , wherein the support structure comprises a plurality of support members spaced apart from each other and parallel to each other.

17 . A method of removing a support structure from a 3D printed component, comprising the steps of:
storing a first image of a component in memory; determining a cutting path between the 3D printed component and a support structure attached to the 3D printed component based on the first image, in which the cutting path is visible or in which regions are generated to define the component and the support structure; capturing a second image of an actual 3D printed component, the actual 3D printed component corresponding to the component of the first image; in response to the second image differing from the first image beyond a threshold, updating the first image to adjust the first image and the cutting path, wherein the first image is updated based on differences between the first image and the second image; outputting the adjusted cutting path to a post-processing system for further processing of the 3D printed component; and removing the support structure from the actual 3D printed component via the pot-processing system.

18 . The method according to claim 17 ,
wherein the first image is updated periodically based on differences between the first image and the second image of the actual 3D printed component.

Assignees

• Maranò Stefano
• Abb Schweiz Ag

Inventors

• Jacimovic Jacim
• Capon Elisabet
• Lymperopoulos Ioannis
• Cortinovis Andrea
• Maranò Stefano

Classifications

• B22F10/30

  Process control · CPC title

• B22F10/40

  Structures for supporting workpieces or articles during manufacture and removed afterwards · CPC title

• B22F10/60

  Treatment of workpieces or articles after build-up · CPC title

• B33Y40/20

  Post-treatment, e.g. curing, coating or polishing · CPC title

• B33Y50/02

  for controlling or regulating additive manufacturing processes · CPC title