Granted Patent B2

US 11,731,368 · App. 17/444,619 · Granted Aug 22, 2023

Inventors: Vadim Pinskiy (Wayne, NJ); Matthew C. Putman (Brooklyn, NY); Damas Limoge (Brooklyn, NY); Aswin Raghav Nirmaleswaran (Brooklyn, NY)

Assignee: Nanotronics Imaging, Inc.

B33Y50/02B22F10/30B22F10/85B22F12/90B29C64/209B29C64/393B33Y10/00G06F18/2411G06F18/295G06N3/04G06V10/764G06V10/82G06V10/993B22F10/12B22F10/18B22F10/25B22F10/28

Abstract

Claims (99)

1. An additive manufacturing system, comprising:

a print head that is configured to print an object in a layer-by-layer manner;

an image sensor configured to capture an image of a printed layer of the object; and

a computing system in communication with the image sensor and the print head, the computing system configured to perform operations comprising:

receiving the image from the image sensor;

generating a low-resolution version of the image;

applying a binary error classifier to the low-resolution version of the image to determine whether an error is present in the printed layer of the object;

determining, based on an output from the binary error classifier, that the error is present in the printed layer of the object;

in response to determining that the error is present in the printed layer of the object, applying an extrusion classifier to a high-resolution version of the image to generate an extrusion quality score indicating a quality of extrusion of material in the printed layer of the object; and

adjusting a value of a parameter of the print head based on the extrusion quality score to print a subsequent layer of the object.

2. The additive manufacturing system of claim 1 , further comprising:

generating a cropped version of the low-resolution version of the image by identifying a region of interest that includes a mesh pattern representative of the extrusion quality score.

3. The additive manufacturing system of claim 1 , wherein the operations further comprise:

receiving a second image of the subsequent layer of the object;

generating a second low-resolution version of the second image;

applying a failure classifier to the second low-resolution version of the second image;

determining, based on a second classification obtained from the failure classifier, that a non-recoverable failure is present in the subsequent layer of the object; and

in response to determining that the non-recoverable failure is present in the subsequent layer, terminate printing of the object.

4. The additive manufacturing system of claim 1 , wherein the operations further comprise:

receiving a second image of the subsequent layer of the object;

generating a second low-resolution version of the second image;

applying the binary error classifier to the second low-resolution version of the second image to determine whether a second error is present in the printed layer of the object;

determining, based on a second output from the binary error classifier, that the second error is not present in the printed layer of the object; and

continuing printing of additional layers.

5. The additive manufacturing system of claim 1 , wherein the operations further comprise:

receiving a second image of the subsequent layer of the object;

generating a second low-resolution version of the second image;

applying the binary error classifier to the second low-resolution version of the second image to determine whether a second error is present in the printed layer of the object;

determining, based on a second output from the binary error classifier, that the second error is present in the printed layer of the object;

in response to determining that the second error is present in the subsequent layer of the object, applying the extrusion classifier to a second high-resolution version of the image to generate a second extrusion quality score indicating a quality of extrusion of material in the subsequent layer of the object; and

adjusting a second value of a second parameter of the print head based on the second extrusion quality score to print a second subsequent layer of the object.

6. The additive manufacturing system of claim 1 , wherein the operations further comprise:

applying a failure classifier to the low-resolution version of the image to determine that a non-recoverable failure is not present.

7. The additive manufacturing system of claim 1 , wherein applying the extrusion classifier to the high-resolution version of the image comprises:

identifying a centroid of the image based on an infill density of the printed layer;

generating a window positioned about the centroid in the high-resolution version of the image; and

applying the extrusion classifier to the window.

8. A method, comprising:

receiving, by a computing system, an image of a printed layer on an object, the printed layer generated by a print head configured to print the object in a layer-by-layer manner;

generating, by the computing system, a low-resolution version of the image;

applying, by the computing system, a binary error classifier to the low-resolution version of the image to determine whether an error is present in the printed layer of the object;

determining, by the computing system and based on an output from the binary error classifier, that the error is present in the printed layer of the object;

in response to determining that the error is present in the printed layer of the object, applying, by the computing system, an extrusion classifier to a high-resolution version of the image to generate an extrusion quality score indicating a quality of extrusion of material in the printed layer of the object; and

adjusting, by the computing system, a value of a parameter of the print head based on the extrusion quality score to print a subsequent layer of the object.

9. The method of claim 8 , further comprising:

generating, by the computing system, a cropped version of the low-resolution version of the image by identifying a region of interest that includes a mesh pattern representative of the extrusion quality score.

10. The method of claim 8 , further comprising:

receiving, by the computing system, a second image of the subsequent layer of the object;

generating, by the computing system, a second low-resolution version of the second image;

applying, by the computing system, a failure classifier to the second low-resolution version of the second image;

determining, by the computing system and based on a second classification obtained from the failure classifier, that a non-recoverable failure is present in the subsequent layer of the object; and

in response to determining that the non-recoverable failure is present in the subsequent layer, terminate, by the computing system, printing of the object.

11. The method of claim 8 , further comprising:

receiving, by the computing system, a second image of the subsequent layer of the object;

generating, by the computing system, a second low-resolution version of the second image;

applying, by the computing system, the binary error classifier to the second low-resolution version of the second image to determine whether a second error is present in the printed layer of the object;

determining, by the computing system and based on a second output from the binary error classifier, that the second error is not present in the printed layer of the object; and

continuing, by the computing system, printing of additional layers.

12. The method of claim 8 , further comprising:

receiving, by the computing system, a second image of the subsequent layer of the object;

generating, by the computing system, a second low-resolution version of the second image;

applying, by the computing system, the binary error classifier to the second low-resolution version of the second image to determine whether a second error is present in the printed layer of the object;

determining, by the computing system and based on a second output from the binary error classifier, that the second error is present in the printed layer of the object;

in response to determining that the second error is present in the subsequent layer of the object, applying, by the computing system, the extrusion classifier to a second high-resolution version of the image to generate a second extrusion quality score indicating a quality of extrusion of material in the subsequent layer of the object; and

adjusting, by the computing system, a second value of a second parameter of the print head based on the second extrusion quality score to print a second subsequent layer of the object.

13. The method of claim 8 , further comprising:

applying, by the computing system, a failure classifier to the low-resolution version of the image to determine that a non-recoverable failure is not present.

14. The method of claim 8 , further comprising, wherein applying, by the computing system, the extrusion classifier to the high-resolution version of the image comprises:

identifying a centroid of the image based on an infill density of the printed layer;

generating a window positioned about the centroid in the high-resolution version of the image; and

applying the extrusion classifier to the window.

15. A non-transitory computer readable medium comprising one or more sequences of instructions, which, when executed by one or more processors, causes a computing system to perform operations comprising:

receiving, by the computing system, an image of a printed layer on an object, the printed layer generated by a print head configured to print the object in a layer-by-layer manner;

generating, by the computing system, a low-resolution version of the image;

applying, by the computing system, a binary error classifier to the low-resolution version of the image to determine whether an error is present in the printed layer of the object;

determining, by the computing system and based on an output from the binary error classifier, that the error is present in the printed layer of the object;

in response to determining that the error is present in the printed layer of the object, applying, by the computing system, an extrusion classifier to a high-resolution version of the image to generate an extrusion quality score indicating a quality of extrusion of material in the printed layer of the object; and

adjusting, by the computing system, a value of a parameter of the print head based on the extrusion quality score to print a subsequent layer of the object.

16. The non-transitory computer readable medium of claim 15 , further comprising:

generating, by the computing system, a cropped version of the low-resolution version of the image by identifying a region of interest that includes a mesh pattern representative of the extrusion quality score.

17. The non-transitory computer readable medium of claim 15 , further comprising:

receiving, by the computing system, a second image of the subsequent layer of the object;

generating, by the computing system, a second low-resolution version of the second image;

applying, by the computing system, a failure classifier to the second low-resolution version of the second image;

determining, by the computing system and based on a second classification obtained from the failure classifier, that a non-recoverable failure is present in the subsequent layer of the object; and

in response to determining that the non-recoverable failure is present in the subsequent layer, terminate, by the computing system, printing of the object.

18. The non-transitory computer readable medium of claim 15 , further comprising:

receiving, by the computing system, a second image of the subsequent layer of the object;

generating, by the computing system, a second low-resolution version of the second image;

applying, by the computing system, the binary error classifier to the second low-resolution version of the second image to determine whether a second error is present in the printed layer of the object;

determining, by the computing system and based on a second output from the binary error classifier, that the second error is present in the printed layer of the object;

in response to determining that the second error is present in the subsequent layer of the object, applying, by the computing system, the extrusion classifier to a second high-resolution version of the image to generate a second extrusion quality score indicating a quality of extrusion of material in the subsequent layer of the object; and

adjusting, by the computing system, a second value of a second parameter of the print head based on the second extrusion quality score to print a second subsequent layer of the object.

19. The non-transitory computer readable medium of claim 15 , further comprising:

applying, by the computing system, a failure classifier to the low-resolution version of the image to determine that a non-recoverable failure is not present.

20. The non-transitory computer readable medium of claim 15 , wherein applying, by the computing system, the extrusion classifier to the high-resolution version of the image comprises:

identifying a centroid of the image based on an infill density of the printed layer;

generating a window positioned about the centroid in the high-resolution version of the image; and

applying the extrusion classifier to the window.

Assignments (2)

Continuity (9)