Systems, methods, and media for artificial intelligence feedback control in additive manufacturing

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 a first image of a printed layer of the object; and

at least one hardware processor configured to:

receive the first image from the image sensor;

obtain one or more desired mechanical properties for the object;

generate a second image of the printed layer based on the first image;

identify an anomaly in the printed layer from the second image using a first artificial intelligence algorithm that is configured to detect anomalies in printed layers;

determine a correlation between the identified anomaly and one of an infill density and an infill pattern used to print the printed layer using a second artificial intelligence algorithm that is configured to determine correlations between identified anomalies and the one of the infill density and the infill pattern;

adjust a value for the one of the infill density and the infill pattern to be used by the print head to print a subsequent layer of the object; and

cause the print head to print the subsequent layer of the object using the value for the one of the infill density and the infill pattern to substantially achieve the one or more desired mechanical properties.

2. The additive manufacturing system of claim 1 , wherein the second image of the printed layer is generated using one of a shape-from-focus algorithm, a shape-from-shading focus algorithm, a photometric stereo algorithm, and a Fourier ptychography modulation algorithm.

3. The additive manufacturing system of claim 1 , wherein at least one of the first artificial intelligence algorithm and the second artificial intelligence algorithm includes at least one of machine learning, hidden Markov models, recurrent neural networks, convolutional neural networks, Bayesian symbolic methods, support vector machines, and general adversarial network.

4. The additive manufacturing system of claim 1 , wherein identifying the anomaly is performed by comparing the second image with at least one of: generated numerical control code for the printed layer, one or more prior layers of the printed object, or a production design for the printed object.

5. The additive manufacturing system of claim 1 , wherein the at least one hardware processor is further configured to:

identify a print parameter that affects at least one of a mechanical property, an optical property, and an electrical property of the object;

measure the at least one of the mechanical property, the optical property, and the electrical property after the object is printed;

determine at least one of an anomaly rate and an anomaly pattern of the object; and

determine how the at least one the anomaly rate and the anomaly pattern and the print parameter impact the at least one of the mechanical property, the optical property, and the electrical property of the object.

6. The additive manufacturing system of claim 5 , wherein identifying a print parameter uses an artificial intelligence algorithm.

7. The additive manufacturing system of claim 5 , wherein determining how the at least one the anomaly rate and the anomaly pattern and the print parameter impact the at least one of the mechanical property, the optical property, and the electrical property uses an artificial intelligence algorithm.

8. A method for additive manufacturing, comprising:

receiving a first image produced by an image sensor configured to capture an image of a printed layer of an object printed in a layer by layer manner;

obtaining one or more desired mechanical properties for the object;

generating a second image of the printed layer using a hardware processor;

identifying an anomaly in the printed layer from the second image using a first artificial intelligence algorithm that is configured to detect anomalies in printed layers;

determining a correlation between the identified anomaly and one of an infill density and an infill pattern used to print the printed layer using a second artificial intelligence algorithm that is configured to determine correlations between identified anomalies and the one of the infill density and the infill pattern;

adjusting a value for the one of the infill density and the infill pattern to be used by a print head to print a subsequent layer of the object; and

causing the print head to print the subsequent layer of the object using the value for the one of the infill density and the infill pattern to substantially achieve the one or more desired mechanical properties.

9. The method of claim 8 , wherein the second image of the printed layer is generated using one of a shape-from-focus algorithm, a shape-from-shading focus algorithm, a photometric stereo algorithm, and a Fourier ptychography modulation algorithm.

10. The method of claim 8 , wherein at least one of the first artificial intelligence algorithm and the second artificial intelligence algorithm includes at least one of machine learning, hidden Markov models, recurrent neural networks, convolutional neural networks, Bayesian symbolic methods, support vector machines, and general adversarial network.

11. The method of claim 8 , wherein identifying the anomaly is performed by comparing the second image with at least one of: generated numerical control code for the printed layer, one or more prior layers of the printed object, and a production design for the printed object.

12. The method of claim 8 , further comprising:

identifying a print parameter that affects at least one of a mechanical property, an optical property, and an electrical property of the object;

measuring the at least one of the mechanical property, the optical property, and the electrical property after the object is printed;

determining at least one of an anomaly rate and an anomaly pattern of the object; and

determining how the at least one the anomaly rate and the anomaly pattern and the print parameter impact the at least one of the mechanical property, the optical property, and the electrical property of the object.

13. The method of claim 12 , wherein identifying a print parameter uses an artificial intelligence algorithm.

14. The method of claim 12 , wherein determining how the at least one of the anomaly rate and the anomaly pattern and the print parameter impact the at least one of the mechanical property, the optical property, and the electrical property of the object uses an artificial intelligence algorithm.

15. A non-transitory computer-readable medium containing computer-executable instructions that, when executed by a processor, cause the processor to perform a method for additive manufacturing comprising:

receiving a first image produced by an image sensor configured to capture an image of a printed layer of an object printed in a layer by layer manner;

obtaining one or more desired mechanical properties for the object;

generating a second image of the printed layer;

identifying an anomaly in the printed layer from the second image using a first artificial intelligence algorithm that is configured to detect anomalies in printed layers;

determining a correlation between the identified anomaly and one of an infill density and an infill pattern used to print the printed layer using a second artificial intelligence algorithm that is configured to determine correlations between identified anomalies and the one of the infill density and the infill pattern;

adjusting for the one of the infill density and the infill pattern to be used by a print head to print a subsequent layer of the object; and

causing the print head to print the subsequent layer of the object using a value for the one of the infill density and the infill pattern to substantially achieve the one or more desired mechanical properties.

16. The non-transitory computer-readable medium of claim 15 , wherein the second image of the printed layer is generated using one of a shape-from-focus algorithm, a shape-from-shading focus algorithm, a photometric stereo algorithm, and a Fourier ptychography modulation algorithm.

17. The non-transitory computer-readable medium of claim 15 , wherein at least one of the first artificial intelligence algorithm and the second artificial intelligence algorithm includes at least one of machine learning, hidden Markov models, recurrent neural networks, convolutional neural networks, Bayesian symbolic methods, support vector machines, and general adversarial network.

18. The non-transitory computer-readable medium of claim 15 , wherein identifying the anomaly is performed by comparing the second image with at least one of: generated numerical control code for the printed layer, one or more prior layers of the printed object, and a production design for the printed object.

19. The non-transitory computer-readable medium of claim 15 , wherein the method further comprises:

identifying a print parameter that affects at least one of a mechanical property, an optical property, and an electrical property of the object;

measuring the at least one of the mechanical property, the optical property, and the electrical property after the object is printed;

determining at least one of an anomaly rate and an anomaly pattern of the object; and

determining how the at least one the anomaly rate and the anomaly pattern and the print parameter impact the at least one of the mechanical property, the optical property, and the electrical property of the object.

20. The non-transitory computer-readable medium of claim 19 , wherein identifying a print parameter uses an artificial intelligence algorithm.

21. The non-transitory computer-readable medium of claim 19 , wherein determining how the at least one of the anomaly rate and the anomaly pattern and the print parameter impact the at least one of the mechanical property, the optical property, and the electrical property of the object uses an artificial intelligence algorithm.