Moose Stochastic Tools: A Module for Performing Parallel, Memory-Efficient in Situ Stochastic Simulations

Prince, Zachary M.; Slaughter, Andrew E.; German, Péter; Halvic, Ian; Jiang, Wen; Spencer, Benjamin W.; Dhulipala, Somayajulu L. N.; Gaston, Derek

doi:10.2139/ssrn.4049487

Search citation statements

Order By: Relevance

Paper Sections

Select...

Software Architecture1

Ivb Surrogate Model1

Citation Types

Supporting

Mentioning

Contrasting

Year Published

2023

Publication Types

Select...

Preprint1

Other1

Relationship

Self Cite0

Independent2

Authors

Journals

Cited by 2 publications

(2 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…1, can be divided into core capabilities, located in the framework, and physics-specific capabilities, which have been placed in physics modules. The Libtorch-based ML functionalities have been divided between the framework and the MOOSE stochastic tools module (MOOSE-STM) [11], which incorporates algorithms necessary for efficient stochastic analysis, surrogate generation, and data analysis. Even though the syntax of Libtorch is directly available in MOOSE and MOOSE-based applications, several wrapper classes have been created to simplify the utilization, creation, and training of NN models in MOOSE.…”

Section: Software Architecturementioning

confidence: 99%

Enabling Scientific Machine Learning in MOOSE Using Libtorch

German

Yushu

2023

Preprint

View full text Add to dashboard Cite

Section: Software Architecturementioning

confidence: 99%

Enabling Scientific Machine Learning in MOOSE Using Libtorch

German

Yushu

2023

Preprint

View full text Add to dashboard Cite

“…A surrogate model was developed using the stochastic tools module of the Moose framework with polynomial regression [21]. The generated data with Serpent was used to train the regression model and generate the coefficients of the polynomial terms.…”

Section: Ivb Surrogate Modelmentioning

confidence: 99%

A Predictive Transient Model of the TREAT-SIRIUS Experiments

Jaradat,

Schunert,

Gleicher

et al. 2023

Nuclear and Emerging Technologies for Space (NETS 2023)

View full text Add to dashboard Cite

To support experiments modeling and transient analysis of the NASA-sponsored SIRIUS experiments in the Transient Reactor Test Facility (TREAT), an innovative predictive transient model has been developed to simulate various transient experiments. The developed model is based on a new approach that utilizes steady-state Monte Carlo calculations along with a surrogate model based on polynomial regression to determine the core reactivity. The reactivity is supplied to a point kinetics model that determines the reactor power, and it is coupled to an adiabatic feedback model to determine the fuel average temperature. In this work, the newly developed model is introduced along with validation test results considering SIRIUS-1 experiments at different power levels. The initial test results show a very good agreement with experimental data at different power levels, which indicates that the model can be used to predict the power of future transient tests.

show abstract

Moose Stochastic Tools: A Module for Performing Parallel, Memory-Efficient in Situ Stochastic Simulations

Cited by 2 publications

References 6 publications

Enabling Scientific Machine Learning in MOOSE Using Libtorch

Enabling Scientific Machine Learning in MOOSE Using Libtorch

A Predictive Transient Model of the TREAT-SIRIUS Experiments

Contact Info

Product

Resources

About