Systems and methods for synthesizing a diamond using machine learning

Patent metadata

Field	Value
Publication number	US-12072299-B2
Application number	US-202318220150-A
Country	US
Kind code	B2
Filing date	Jul 10, 2023
Priority date	May 22, 2020
Publication date	Aug 27, 2024
Grant date	Aug 27, 2024

Abstract

Disclosed herein are systems and methods for synthesizing a diamond using a diamond synthesis machine. A processor receives a plurality of images of a diamond during synthesis within a diamond synthesis machine, each of the plurality of images captured within a time period. The processor executes a diamond state prediction machine learning model using the plurality of images to obtain a predicted data object, the predicted data object indicating a predicted state of the diamond within the diamond synthesis machine at a time subsequent to the time period. The processor detects a predicted defect, a number of defects, defect types, and/or sub-features of such defects and/or other characteristics (e.g., a predicted shape, size, and/or other properties of predicted contours for the diamond and/or pocket holder) of the predicted state of the diamond. The processor adjusts operation of the diamond synthesis machine.

First claim

What we claim is:

1. A method for synthesizing a crystal using a synthesis machine, comprising:
receiving, by a processor, a plurality of images of a crystal during synthesis within a synthesis machine, the plurality of images captured;
generating, by the processor, a data object based on the plurality of images, the data object indicating a predicted state of the crystal within the synthesis machine at a time subsequent to the capture of the plurality of images;
detecting, by the processor, a predicted defect in the crystal based on the predicted state of the crystal; and
adjusting, by the processor, operation of the synthesis machine responsive to detecting the defect.

2. The method of claim 1 , wherein the predicted defect comprises an improper shape, an improper size, or a crystallographic defect.

3. The method of claim 1 , wherein the data object comprises a predicted image depicting the crystal in the predicted state, and wherein the predicted image comprises a plurality of pixels, the method further comprising:
extracting, by the processor, a plurality of classification labels for the plurality of pixels of the predicted image,
wherein detecting the predicted defect in predicted state of the crystal comprises detecting, by the processor, the predicted defect based on the plurality of classification labels.

4. The method of claim 3 , wherein extracting the plurality of classification labels comprises extracting, by the processor, classification labels indicating a side of the crystal, a type of object, or a type of defect for the plurality of pixels of the predicted image.

5. The method of claim 1 , wherein generating the data object comprises generating, by the processor, the data object based on the plurality of images and a schedule of operating parameters of the synthesis machine to obtain the predicted data object, the schedule of operating parameters of the synthesis machine corresponding to times in which the plurality of images were captured.

6. The method of claim 5 , wherein the schedule of operating parameters further comprises a first set of operating parameters for the synthesis machine for a first time between the capture of the plurality of images and the time subsequent to the capture of the plurality of images.

7. The method of claim 1 , wherein generating the data object comprises:
converting, by the processor, the plurality of images into a multi-dimensional vector corresponding to a predicted first state of the crystal at a first time-step subsequent to the capture of the plurality of images; and
generating, by the processor, the predicted data object based on the multi-dimensional vector.

8. The method of claim 1 , wherein the data object comprises a predicted image depicting the crystal in the predicted state, and wherein detecting the predicted defect comprises:
evaluating, by the processor, a shape of the crystal depicted in the predicted image according to a set of crystal defect rules; and
detecting, by the processor, a macroscopic defect, microscopic defect, a center defect, or an edge defect in the crystal responsive to determining the shape of the crystal satisfies a crystal defect rule.

9. The method of claim 1 , further comprising:
receiving, by the processor, a second plurality of images of a second crystal during synthesis within the synthesis machine, each of the second plurality of images captured within a second time period;
generating, by the processor, a second data object based on the second plurality of images, the second predicted data object indicating a second predicted state of the second crystal within the synthesis machine at a second time subsequent to the second time period;
determining, by the processor, there are not any defects in the crystal in the second predicted state; and
generating, by the processor, a record indicating no defects were detected in the crystal in the second predicted state.

10. The method of claim 1 , wherein adjusting operation of the synthesis machine comprises adjusting, by the processor, a pressure or a temperature of the synthesis machine.

11. The method of claim 1 , wherein the predicted data object comprises a predicted image depicting the crystal in the predicted state, and wherein detecting the predicted defect in the crystal depicted in the predicted image comprises:
identifying, by the processor, a contour of the predicted defect from the predicted image; and
detecting, by the processor, the predicted defect in response to identifying the contour.

12. The method of claim 1 , wherein the data object comprises a predicted image depicting the crystal in the predicted state, and wherein detecting the predicted defect in the crystal depicted in the predicted image comprises:
identifying, by the processor, a contour of the crystal or a crystal holder based on the predicted image;
identifying, by the processor, a size or shape of the crystal based on the contour; and
detecting, by the processor, the predicted defect in response to identifying the size or shape.

13. The method of claim 1 , wherein the image comprises an optical image or a thermal image.

14. A system for synthesizing a crystal using a synthesis machine, the system comprising:
a processor configured to execute instructions stored on a non-transitory computer-readable medium to:
receive a plurality of images of a crystal during synthesis within a synthesis machine, the plurality of images captured;
generate a data object based on the plurality of images, the data object indicating a predicted state of the crystal within the synthesis machine at a time subsequent to the capture of the plurality of images;
detect a predicted defect in the crystal based on the predicted state of the crystal; and
adjust operation of the synthesis machine responsive to detecting the defect.

15. The system of claim 14 , wherein the predicted data object comprises a predicted image depicting the crystal in the predicted state, wherein the predicted image comprises a plurality of pixels, and wherein the processor is further configured to:
extract a plurality of classification labels for the plurality of pixels for the predicted image,
wherein the processor is configured to detect the predicted defect in the crystal based on the plurality of classification labels for the plurality of pixels.

16. The system of claim 15 , wherein the processor is configured to extract the plurality of classification labels by extracting classification labels indicating a side of the crystal, a type of object, or a type of defect for the plurality of pixels of the predicted image.

17. The system of claim 14 , wherein the processor is configured to generate the data object by generating the data object based on the plurality of images and a schedule of operating parameters of the synthesis machine to obtain the predicted data object, the schedule of operating parameters of the synthesis machine corresponding to times in which the plurality of images were captured.

18. The system of claim 17 , wherein the schedule of operating parameters further comprises a first set of operating parameters for the synthesis machine for a first time between the capture of the plurality of images and the time subsequent to the capture of the plurality of images.

19. The system of claim 14 , wherein the processor is configured to generate the data object by:
converting the plurality of images into a multi-dimensional vector corresponding to a predicted first state of the crystal at a first time-step subsequent to the capture

Assignees

• Fraunhofer Usa Inc
• Univ Maryland

Inventors

• Mekala Rohan Reddy
• Muehle Matthias
• Porter Adam
• Lindvall Mikael
• Becker Michael

Classifications

• G06T7/564

  from contours · CPC title

• G01N2021/8854

  Grading and classifying of flaws · CPC title

• G01N2021/8887

  based on image processing techniques · CPC title

• G06T5/50

  using two or more images, e.g. averaging or subtraction · CPC title

• G01N2021/95615

  with stored comparision signal · CPC title