System and method for additive manufacturing control

Patent metadata

Field	Value
Publication number	US-12269090-B2
Application number	US-202117398604-A
Country	US
Kind code	B2
Filing date	Aug 10, 2021
Priority date	Aug 10, 2021
Publication date	Apr 8, 2025
Grant date	Apr 8, 2025

Abstract

An additive manufacturing apparatus, a computing system, and a method for operating an additive manufacturing apparatus are provided. The method includes obtaining two or more images corresponding to respective build layers at a build plate, wherein each image comprises a plurality of data points comprising a feature and corresponding location at the build plate; removing variation between the features of the plurality of data points; and normalizing each feature to remove location dependence in the plurality of data points.

First claim

What is claimed is:

1. A computing system for an additive manufacturing apparatus, the computing system including one or more processors and one or more memory devices, wherein the one or more memory devices is configured to store instructions that, when executed by the one or more processors, causes the one or more processors to perform operations, the operations comprising:
obtaining two or more images corresponding to respective build layers at a build plate, wherein each image comprises a plurality of data points comprising a feature and corresponding location at the build plate;
removing variation between the features of the plurality of data points;
normalizing each feature to remove location dependence in the plurality of data points; and
operating the additive manufacturing apparatus based on the normalized features.

2. The computing system of claim 1 , the operations comprising:
adjusting an energy parameter based on the normalized feature.

3. The computing system of claim 2 , wherein the energy parameter comprises one or more of a wavelength, power, spot size, or pulse width of an energy beam.

4. The computing system of claim 1 , wherein removing variation between the features comprises determining an average of each feature.

5. The computing system of claim 4 , wherein removing variation between the features comprises fitting the average of each feature to a quadratic function of the location of the plurality of data points.

6. The computing system of claim 1 , the operations comprising:
reducing the two or more images to respective datasets comprising a portion of the plurality of data points.

7. The computing system of claim 1 , the operations comprising:
generating, via a machine learning algorithm, a plurality of datasets corresponding to the two or more images.

8. The computing system of claim 7 , wherein the plurality of datasets comprise a portion of the plurality of data points.

9. The computing system of claim 7 , wherein the machine learning algorithm is a neural network.

10. The computing system of claim 9 , wherein the machine learning algorithm is an autoencoder configured to output the plurality of datasets as a reduced representation of the respective images.

11. A computer-implemented method for operating an additive manufacturing apparatus, the method comprising:
directing, by a computing system, an imaging device to obtain two or more images corresponding to build layers at a build plate, wherein each image comprises a plurality of data points comprising a feature and corresponding location at the build plate;
removing, via the computing system, variation between the features of the plurality of data points;
normalizing, via the computing system, each feature to remove location dependence in the plurality of data points; and
operating the additive manufacturing apparatus based on the normalized features.

12. The computer-implemented method of claim 11 , the method comprising:
adjusting, via the computer system, an energy parameter at an energy beam device based on the normalized feature.

13. The computer-implemented method of claim 11 , the method comprising:
determining, via the computing system, an average of each feature; and
fitting the average of each feature to a quadratic function of the location of the data point.

14. The computer-implemented method of claim 11 , the method comprising:
generating, via a machine learning algorithm, a plurality of datasets corresponding to the two or more images, wherein the machine learning algorithm is configured to output the plurality of datasets as a reduced representation of the respective images.

15. The computer-implemented method of claim 11 , the method comprising:
reducing, via a machine learning algorithm, the two or more images to respective datasets comprising a portion of the plurality of data points; and
removing, via the computing system, variation between the features of the portion of the plurality of data points between the datasets.

16. An additive manufacturing apparatus, the apparatus comprising:
a build unit comprising an energy beam device configured to emit an irradiation beam and an imaging device configured to obtain an image corresponding to a build layer irradiated by the irradiation beam at a build plate; and
a computing system comprising one or more processors and one or more memory devices, wherein the one or more memory devices is configured to store instructions that, when executed by the one or more processors, causes the one or more processors to perform operations, the operations comprising:
obtaining two or more images from the imaging device corresponding to build layers at the build plate, wherein each image comprises a plurality of data points comprising a feature and a corresponding location at the build plate;
removing variation between the features of the plurality of data points; and
normalizing each feature to remove location dependence in the plurality of data points.

17. The additive manufacturing apparatus of claim 16 , the operations comprising:
adjusting an energy parameter at the energy beam device based on the normalized feature.

18. The additive manufacturing apparatus of claim 16 , the operations comprising:
determining an average of each feature; and
fitting the average of each feature to a quadratic function of the location of the data point.

19. The additive manufacturing apparatus of claim 16 , the operations comprising:
generating, via a machine learning algorithm, a plurality of datasets corresponding to the two or more images, wherein the machine learning algorithm is configured to output the plurality of datasets as a reduced representation of the respective images.

20. The additive manufacturing apparatus of claim 16 , the operations comprising:
reducing, via a machine learning algorithm, the two or more images to respective datasets comprising a portion of the plurality of data points; and
removing variation between the features of the portion of the plurality of data points between the datasets.

Assignees

• Gen Electric

Inventors

• Ray Majumder Saikat K
• Iyer Naresh S
• Ping Xiaohu
• Roychowdhury Subhrajit

Classifications

• B29C2049/78805

  Computer or PLC control · CPC title

• B29C2037/903

  by means of a computer · CPC title

• B29C64/00

  Additive manufacturing, i.e. manufacturing of three-dimensional [3D] objects by additive deposition, additive agglomeration or additive layering, e.g. by 3D printing, stereolithography or selective laser sintering · CPC title

• B29C64/10

  Processes of additive manufacturing · CPC title

• G06T2207/20084

  Artificial neural networks [ANN] · CPC title