Method and system for competence monitoring and contiguous learning for control

1. A competence modelling and control system comprising:

a competence module to receive data from at least one data source;

a memory for storing program instructions;

a competence processor, coupled to the memory, and in communication with the competence module, and operative to execute program instructions to:

receive an objective;

select a machine learning model associated with the objective;

receive data from the at least one data source;

generate at least one next input based on the received data, wherein the at least one next input is distinct from the received data;

determine whether the at least one next input is in a competent region of training data of the machine learning model or is in an incompetent region of the machine learning model, wherein the competent region is a region in which the machine learning model is competent to make predictions;

when the at least one next input is inside the competent region, generate an output of the machine learning model;

determine an estimate of uncertainty for the generated output of the machine learning model;

when the uncertainty is below an uncertainty threshold, determine the machine learning model is competent and when the uncertainty is above the uncertainty threshold, determine the machine learning model is incompetent; and

operate the physical asset based on the state of the machine learning model, where the state is one of competent and incompetent.

2. The system of claim 1 , further comprising program instructions to:

trigger at least one of a baseline control and a learning module when the at least one next input is in the incompetent region.

3. The system of claim 1 , further comprising program instructions to:

determine a second next input of the at least one next inputs when it is determined the received at least one next input is in the incompetent region.

4. The system of claim 2 , further comprising program instructions to:

determine whether a learning trigger of the learning module has been met, wherein the learning trigger is a pre-set threshold number of instances the input is in the incompetent region within a pre-set amount of time.

5. The system of claim 4 , further comprising program instructions to:

initiate at least one learning mechanism of the learning module.

6. The system of claim 5 , wherein the learning mechanism is one of a learning by experimenting on the physical asset, learning from second assets via transfer learning, learning by simulation, or learning from at least one expert.

7. The system of claim 5 , wherein the system includes at least two learning mechanisms, and further comprises program instructions to:

select one of the at least two learning mechanisms based on a learning mode decision rule.

8. The system of claim 6 , further comprising program instructions to:

collect second data based on the initiated learning mechanism.

9. The system of claim 8 , further comprising program instructions to:

update the machine learning model based on the collected second data.

10. The system of claim 1 , wherein the at least one data source is a physical asset.

11. A method comprising:

receiving an objective;

selecting a machine learning model associated with the objective;

receiving data from at least one data source;

generating at least one next input based on the received data, wherein the at least one next input is distinct from the received data;

determining whether the at least one next input is in a competent region of training data of the machine learning model or is in an incompetent region of the machine learning model, wherein the competent region is a region in which the machine learning model is competent to make predictions;

when the at least one next input is inside the competent region, generating an output of the machine learning model;

determining an estimate of uncertainty for the generated output of the machine learning model;

when the uncertainty is below an uncertainty threshold, determining the machine learning model is competent and when the uncertainty is above the uncertainty threshold, determining the machine learning model is incompetent; and

operating the physical asset based on the state of the machine learning model, where the state is one of competent and incompetent.

12. The method of claim 11 , further comprising:

triggering at least one of a baseline control and a learning module when the at least one next input is in the incompetent region.

13. The method of claim 11 , further comprising:

determining a second next input of the at least one next inputs when it is determined the at least one next input is in the incompetent region.

14. The method of claim 12 , further comprising:

determining whether a learning trigger of the learning module has been met, wherein the learning trigger is a pre-set threshold number of instances the input is in the incompetent region within a pre-set amount of time.

15. The method of claim 14 , further comprising:

initiating at least one learning mechanism of the learning module.

16. The method of claim 15 , further comprising:

collecting second data based on the initiated learning mechanism.

17. The method of claim 16 , further comprising:

updating the machine learning model based on the collected second data.

18. A non-transitory computer-readable medium storing instructions that, when executed by a computer processor, cause the computer processor to perform a method comprising:

receiving an objective;

selecting a machine learning model associated with the objective;

receiving data from at least one data source;

generating at least one next control input based on the received data, wherein the at least one next input is distinct from the received data;

determining whether the at least one next control input is in a competent region of training data of the machine learning model or an incompetent region of the machine learning model, wherein the competent region is a region in which the machine learning model is competent to make predictions;

when the at least one next input is inside the competent region, generating an output of the machine learning model;

determining an estimate uncertainty for the generated output of the machine learning model;

when the uncertainty is below an uncertainty threshold, determining the machine learning model is competent and when the uncertainty is above the uncertainty threshold, determining the machine learning model is incompetent; and

operating the physical asset based on the state of the machine learning model, where the state is one of competent and incompetent.

19. The medium of claim 18 , further comprising instructions that cause the computer processor to:

trigger at least one of a baseline control and a learning module when the at least one next control input is in the incompetent region.

20. The medium of claim 18 , further comprising instructions that cause the computer processor to:

determine a second next input of the at least one next inputs when it is determined at least one next input is in the incompetent region.