System and method for quantifying nozzle occlusion in 3D printing
View Patent ↗One embodiment can provide a system for detecting occlusion at an orifice of a three-dimensional (3D) printer nozzle while the printer nozzle is jetting liquid droplets. During operation, the system uses one or more cameras to capture an image of the orifice of the printer nozzle while the 3D printer nozzle is jetting liquid droplets. The system performs an image-analysis operation on the captured image to identify occluded regions within the orifice of the 3D printer nozzle, compute an occlusion fraction based on the determined occluded regions, and generate an output based on the computed occlusion fraction, thereby facilitating effective maintenance of the 3D printer.
1. A computer-executed method for detecting occlusion at an orifice of a three-dimensional (3D) printer nozzle while the printer nozzle is jetting liquid droplets, the method comprising:
capturing, by one or more cameras, an image of the orifice of the 3D printer nozzle while the 3D printer nozzle is jetting liquid droplets;
performing an image-analysis operation on the captured image to identify occluded regions within the orifice of the 3D printer nozzle;
computing an occlusion fraction based on the determined occluded regions; and
generating an output based on the computed occlusion fraction, thereby facilitating effective maintenance of the 3D printer.
2. The computer-executed method of claim 1 , wherein performing the image-analysis operation comprises computing a gray-level co-occurrence matrix (GLCM) for the captured image to obtain a texture-analysis outcome associated with the captured image.
3. The computer-executed method of claim 2 , wherein computing the GLCM further comprises applying a 4×2 offset matrix on pixels of the captured image.
4. The computer-executed method of claim 3 , wherein the 4×2 offset matrix comprises matrix [0,1; −1,1; −1,0; −1,−1].
5. The computer-executed method of claim 2 , further comprising:
applying an adaptive thresholding technique on the texture-analysis outcome to obtain a binary pixel map of the captured image.
6. The method of claim 1 , wherein performing the image-analysis operation comprises:
training a machine-learning model using labeled images of the orifice of the 3D printer nozzle; and
applying the trained machine-learning model on the captured image to identify the occluded regions.
7. The method of claim 1 , wherein performing the image-analysis operation comprises:
training a machine-learning model using a sequence of labeled images of the orifice of the 3D printer nozzle captured over a predetermined time interval; and
applying the trained machine-learning model on a sequence of images of the orifice of the 3D printer nozzle to identify the occluded regions.
8. A non-transitory computer-readable storage medium storing instructions that when executed by a computer cause the computer to perform a method for detecting occlusion at an orifice of a three-dimensional (3D) printer nozzle while the 3D printer nozzle is jetting liquid droplets, the method comprising:
capturing, by one or more cameras, an image of the orifice of the 3D printer nozzle while the 3D printer nozzle is jetting liquid droplets;
performing an image-analysis operation on the captured image to identify occluded regions within the orifice of the 3D printer nozzle;
computing an occlusion fraction based on the determined occluded regions; and
generating an output based on the computed occlusion fraction, thereby facilitating effective maintenance of the 3D printer.
9. The non-transitory computer-readable storage medium of claim 8 , wherein performing the image-analysis operation comprises computing a gray-level co-occurrence matrix (GLCM) for the captured image to obtain a texture-analysis outcome associated with the captured image.
10. The non-transitory computer-readable storage medium of claim 9 , wherein computing the GLCM further comprises applying a 4×2 offset matrix on pixels of the captured image.
11. The non-transitory computer-readable storage medium of claim 10 , wherein the 4×2 offset matrix comprises matrix [0,1; −1,1; −1,0; −1,−1].
12. The non-transitory computer-readable storage medium of claim 9 , wherein the method further comprises applying an adaptive thresholding technique on the texture-analysis outcome to obtain a binary pixel map of the captured image.
13. The non-transitory computer-readable storage medium of claim 8 , wherein performing the image-analysis operation comprises:
training a machine-learning model using labeled images of the orifice of the 3D printer nozzle; and
applying the trained machine-learning model on the captured image to identify the occluded regions.
14. The non-transitory computer-readable storage medium of claim 8 , wherein performing the image-analysis operation comprises:
training a machine-learning model using a sequence of labeled images of the orifice of the 3D printer nozzle captured over a predetermined time interval; and
applying the trained machine-learning model on a sequence of images of the orifice of the 3D printer nozzle to identify the occluded regions.
15. A computer system for detecting occlusion at an orifice of a three-dimensional (3D) printer nozzle while the 3D printer nozzle is jetting liquid droplets, the system comprising:
a processor; and
a storage device coupled to the processor and storing instructions which when executed by the processor cause the processor to perform a method, wherein the method comprises:
capturing, by one or more cameras, an image of the orifice of the 3D printer nozzle while the 3D printer nozzle is jetting liquid droplets;
performing an image-analysis operation on the captured image to identify occluded regions within the orifice of the 3D printer nozzle;
computing an occlusion fraction based on the determined occluded regions; and
generating an output based on the computed occlusion fraction, t thereby facilitating effective maintenance of the 3D printer.
16. The computer system of claim 15 , wherein performing the image-analysis operation comprises computing a gray-level co-occurrence matrix (GLCM) for the captured image to obtain a texture-analysis outcome associated with the captured image.
17. The computer system of claim 16 , wherein computing the GLCM further comprises applying a 4×2 offset matrix on pixels of the captured image, and wherein the 4×2 offset matrix comprises matrix [0,1; −1,1; −1,0; −1,−1].
18. The computer system of claim 16 , wherein the method further comprises applying an adaptive thresholding technique on the texture-analysis outcome to obtain a binary pixel map of the captured image.
19. The computer system of claim 15 , wherein performing the image-analysis operation comprises:
training a machine-learning model using labeled images of the orifice of the 3D printer nozzle; and
applying the trained machine-learning model on the captured image to identify the occluded regions.
20. The computer system of claim 15 , wherein performing the image-analysis operation comprises:
training a machine-learning model using a sequence of labeled images of the orifice of the 3D printer nozzle captured over a predetermined time interval; and
applying the trained machine-learning model on a sequence of images of the orifice of the 3D printer nozzle to identify the occluded regions.