Rapid digital nuclear reactor design using machine learning

1. A method of designing nuclear reactors, comprising:

identifying a plurality of design variables for a nuclear reactor;

identifying a multiplicity of metric variables for the nuclear reactor, including a first plurality of metric variables to measure thermal-hydraulic properties, a second plurality of metric variables to measure neutronics properties, and a third plurality of metric variables to measure stress properties;

receiving user input to specify a respective range of values for each of the plurality of design variables, thereby forming an initial trust region;

receiving user input to specify a respective threshold value for each of the multiplicity of metric variables;

constructing a Latin hypercube comprising N samples of values for design parameters within the initial trust region that minimizes the multivariate correlation between the plurality of design variables, wherein N is an integer greater than 1;

for each of the N samples in the Latin hypercube:

executing a thermal-hydraulics analysis process to compute the first plurality of metric variables that measure thermal-hydraulic properties;

executing a neutronics analysis process to compute the second plurality of metric variables corresponding to the neutronics properties;

executing a stress analysis process to compute the third plurality of metric variables corresponding to the stress properties; and

applying a cost function to compute a respective aggregate residual of the multiplicity of metric variables compared to the threshold values for the multiplicity of metric variables;

training a machine learning model according to the N samples and the corresponding computed aggregate residuals;

shrinking the initial trust region, centered at a sample of the N samples having a smallest residual, wherein the respective range for each design variable of the plurality of design variables is shrunk according to correlation between the respective design variable and estimated residuals using the machine learning model;

repeating for a plurality of iterations the constructing of the Latin hypercube, the executing of the thermal-hydraulic analysis process, the executing of the neutronics analysis process, the executing of the stress analysis process, the computing of the first, second and third pluralities of metric variables, and the training until a sample of the N samples having a smallest residual is unchanged for a predetermined number of iterations;

using the machine learning model from a final iteration to assess relative importance of each design variable of the plurality of design variables; and

providing the assessment visually in a report.

2. The method of claim 1 , wherein the machine learning model is a random forest of decision trees or a neural network for Bayesian optimization.

3. The method of claim 1 , wherein the machine learning model uses one or more evolutionary methods, and wherein the one or more evolutionary methods are selected from the group consisting of a genetic algorithm, a coupled simulated anneal algorithm, and a differential evolutionary algorithm.

4. The method of claim 1 , wherein executing the thermal-hydraulics analysis process, executing the neutronics analysis process, and executing the stress analysis process are performed concurrently.

5. The method of claim 1 , wherein executing the thermal-hydraulics analysis process, executing the neutronics analysis process, and executing the stress analysis process are performed serially.

6. The method of claim 1 , wherein the thermal-hydraulics analysis process, the neutronics analysis process, and the stress analysis process are each performed at respective distinct computing subsystems.

7. The method of claim 1 , further comprising during one of the plurality of iterations:

determining that the sample of the N samples having the smallest residual has a value for a first design variable on a boundary of the trust region; and

in response to the determination, expanding the trust region to include a range for the first design variable that was not previously in the trust region.

8. The method of claim 1 , wherein one of the second plurality of metric variables is an effective neutron multiplication factor (K eff ).

9. The method of claim 1 , wherein shrinking the trust region uses a learning rate multiplier specified by user input.

10. The method of claim 1 , wherein an initial Latin hypercube is centered at average values for the user-specified ranges of the plurality of design variables.

11. The method of claim 1 , wherein the plurality of design variables includes a first design variable that has discrete categorical values, the method further comprising:

encoding each discrete categorical value as a numeric value in a continuous range to form a first replacement design variable; and

substituting the first replacement design variable for the first design variable.

12. The method of claim 11 , further comprising, during each of the plurality of iterations:

for the sample of the N samples having the smallest residual, estimating probabilities that switching to different categorical values would produce a smaller residual according to the cost function; and

for an immediately subsequent iteration, using sampling rates for the Latin hypercube that are proportional to the estimated probabilities.

13. The method of claim 11 , wherein the first design variable is fluid type or material type.

14. The method of claim 13 , wherein the discrete categorical values for fluid type or material type are selected from a database of materials including single phase gases, liquids, and solids.

15. A computing system, comprising:

one or more computers, each having one or more processors and memory, wherein the memory stores one or more programs configured for execution by the one or more processors, the one or more programs comprising instructions for:

identifying a plurality of design variables for a nuclear reactor;

identifying a multiplicity of metric variables for the nuclear reactor, including a first plurality of metric variables to measure thermal-hydraulic properties, a second plurality of metric variables to measure neutronics properties, and a third plurality of metric variables to measure stress properties;

receiving user input to specify a respective range of values for each of the plurality of design variables, thereby forming an initial trust region;

receiving user input to specify a respective threshold value for each of the multiplicity of metric variables;

constructing a Latin hypercube comprising N samples of values for design parameters within the initial trust region that minimizes the multivariate correlation between the plurality of design variables, wherein N is an integer greater than 1;

for each of the N samples in the Latin hypercube:

executing a thermal-hydraulics analysis process to compute the first plurality of metric variables that measure thermal-hydraulic properties;

executing a neutronics analysis process to compute the second plurality of metric variables corresponding to the neutronics properties;

executing a stress analysis process to compute the third plurality of metric variables corresponding to the stress properties; and

applying a cost function to compute a respective aggregate residual of the multiplicity of metric variables compared to the threshold values for the multiplicity of metric variables;

training a machine learning model according to the N samples and the corresponding computed aggregate residuals;

shrinking the initial trust region, centered at a sample of the N samples having a smallest residual, wherein the respective range for each design variable of the plurality of design variables is shrunk according to correlation between the respective design variable and estimated residuals using the machine learning model;

repeating for a plurality of iterations the constructing of the Latin hypercube, the executing of the thermal-hydraulic analysis process, the executing of the neutronics analysis process, the executing of the stress analysis process, the computing of the first, second and third pluralities of metric variables, and the training until a sample of the N samples having a smallest residual is unchanged for a predetermined number of iterations;

using the machine learning model from a final iteration to assess relative importance of each design variable of the plurality of design variables; and

providing the assessment visually in a report.

16. The computing system of claim 15 , wherein the machine learning model is a random forest of decision trees or a neural network for Bayesian optimization.

17. The computing system of claim 15 , wherein the machine learning model uses one or more evolutionary methods, and wherein the one or more evolutionary methods are selected from the group consisting of a genetic algorithm, a coupled simulated anneal algorithm, and a differential evolutionary algorithm.

18. The computing system of claim 15 , wherein one of the second plurality of metric variables is an effective neutron multiplication factor (K eff ).

19. The computing system of claim 15 , wherein the plurality of design variables includes a first design variable that has discrete categorical values, the method further comprising:

encoding each distinct discrete categorical value as a numeric value in a continuous range to form a first replacement design variable; and

substituting the first replacement design variable for the first design variable.

20. The computing system of claim 19 , further comprising, during each of the plurality of iterations:

for the sample of the N samples having the smallest residual, estimating probabilities that switching to different categorical values would produce a smaller residual according to the cost function; and

for an immediately subsequent iteration, using sampling rates for the Latin hypercube that are proportional to the estimated probabilities.