Systems, and methods for diagnosing an additive manufacturing device using a physics assisted machine learning model

1. A system for diagnosing an additive manufacturing device, the system comprising:

a first module configured to:

obtain one or more parameters for a digital twin of a component of the additive manufacturing device based on raw data from the component of the additive manufacturing device; and

generate physics features for the digital twin of the component of the additive manufacturing device based on the one or more parameters and one or more transfer functions;

a second module configured to obtain one or more classifiers for classifying the component as a first condition or a second condition based on physics features; and

a third module configured to:

determine a health of the component based on the generated physics features of the first module and the one or more classifiers.

2. The system of claim 1 , wherein the one or more parameters are raw data for the component of the additive manufacturing device.

3. The system of claim 1 , wherein the component is a cathode, and the raw data includes a grid voltage and a beam current for the cathode.

4. The system of claim 1 , wherein the component is a cathode, and the physics features include at least one of a cathode temperature, a cathode brightness, and vacuum environment.

5. The system of claim 1 , wherein the one or more transfer functions is updated based on parameters related to wear and tear of the component of the additive manufacturing device.

6. The system of claim 1 , wherein the second module is configured to update the one or more classifiers based on parameters related to wear and tear of the component of the additive manufacturing device.

7. The system of claim 1 , wherein the one or more classifiers include threshold values determined based on machine learning or statistical models on evaluation of builds and parameters for the builds.

8. The system of claim 1 , further comprising a fourth module configured to determine a cause for a failure of the component based on a comparison of the generated physics features of the first module and the one or more classifiers.

9. A method for diagnosing an additive manufacturing device, the method comprising:

obtaining one or more parameters for a digital twin of a component of the additive manufacturing device based on raw data from the component of the additive manufacturing device;

generating physics features for the component of the additive manufacturing device based on the one or more parameters and one or more transfer functions;

obtaining one or more classifiers for classifying the component as a first condition or a second condition based on physics features; and

determining a health of the component based on the generated physics features for the component of the additive manufacturing device and the one or more classifiers.

10. The method of claim 9 , wherein the one or more parameters are raw data for the component of the additive manufacturing device.

11. The method of claim 9 , wherein the component is a cathode, and the raw data includes a grid voltage and a beam current for the cathode.

12. The method of claim 9 , wherein the component is a cathode, and the physics features include at least one of a cathode temperature, a cathode brightness, and vacuum environment.

13. The method of claim 9 , further comprising updating the one or more transfer functions based on parameters related to wear and tear of the component of the additive manufacturing device.

14. The method of claim 9 , further comprising updating the one or more classifiers based on parameters related to wear and tear of the component of the additive manufacturing device.

15. The method of claim 9 , wherein the one or more classifiers include threshold values determined based on machine learning or statistical models on evaluation of builds and parameters for the builds.

16. The method of claim 9 , further comprising determining a cause for a failure of the component based on a comparison of the generated physics features and the one or more classifiers.

17. A non-transitory machine readable media includes computer executable instructions, when executed by one or more processors, configured to:

obtain one or more parameters for a digital twin of a component of an additive manufacturing device based on raw data from the component of the additive manufacturing device;

generate physics features for the component of the additive manufacturing device based on the one or more parameters and one or more transfer functions;

obtain one or more classifiers for classifying the component as a first condition or a second condition based on physics features; and

determine a health of the component based on the generated physics features for the component of the additive manufacturing device and the one or more classifiers.

18. The non-transitory machine readable media of claim 17 , wherein the one or more parameters are raw data for the component of the additive manufacturing device.

19. The non-transitory machine readable media of claim 17 , wherein the component is a cathode, and the raw data includes a grid voltage and a beam current for the cathode.

20. The non-transitory machine readable media of claim 17 , wherein the computer executable instructions, when executed by one or more processors, are configured to update the one or more transfer functions based on parameters related to wear and tear of the component of the additive manufacturing device.