# AUTOMATIC LIMIT SURFACE SEARCH FOR PWR TRANSIENTS BY RELAP5-3D/RAVEN CODES

## Abstract

Deterministic safety analysis of nuclear power plants can be improved by applying modern algorithms and codes exploiting machine learning and parallel computing. In this paper we show the application of some of these advanced methodologies for the determination of limit surfaces. A limit surface is an n-dimensional surface describing the plant status, e.g. identifying, as function of selected plant parameters, the boundaries between failed and safe conditions for the core fuel. Using the RELAP5-3D system thermal-hydraulic code coupled to the RAVEN statistical-analysis code, we show how to apply machine-learning algorithms (near-neighbor, support-vector machine, etc.) for determining relevant limit surfaces for PWR station-blackout and loss of offsite power. As a first step, a set of training simulations is run to sample the nuclear power plant responses. Those calculations are used to train a Reduced-Order-Model (ROM), which RAVEN then uses for determining an approximated limit surface. Verification of the guessed limit surface is then automatically performed and calculation is terminated depending by the chosen convergence criteria. The combination of High Performance Computing (HPC) and ROMs allow a remarkable reduction of the time required for the surface determination. RAVEN performs also the automatic data collection of the output of the numerous runs, thusmore »

- Authors:

- Idaho National Laboratory

- Publication Date:

- Research Org.:
- Idaho National Lab. (INL), Idaho Falls, ID (United States)

- Sponsoring Org.:
- USDOE Office of Nuclear Energy (NE)

- OSTI Identifier:
- 1478778

- Report Number(s):
- INL/CON-18-45361-Rev000

- DOE Contract Number:
- AC07-05ID14517

- Resource Type:
- Conference

- Resource Relation:
- Conference: ANS Best Estimate Plus Uncertainty International Conference (BEPU 2018), Lucca, Italy, 05/13/2018 - 05/19/2018

- Country of Publication:
- United States

- Language:
- English

- Subject:
- 22 - GENERAL STUDIES OF NUCLEAR REACTORS; Limit Surface; RELAP5-3D; RAVEN

### Citation Formats

```
Parisi, C., Alfonsi, A., Mandelli, D., and Rabiti, C.
```*AUTOMATIC LIMIT SURFACE SEARCH FOR PWR TRANSIENTS BY RELAP5-3D/RAVEN CODES*. United States: N. p., 2018.
Web.

```
Parisi, C., Alfonsi, A., Mandelli, D., & Rabiti, C.
```*AUTOMATIC LIMIT SURFACE SEARCH FOR PWR TRANSIENTS BY RELAP5-3D/RAVEN CODES*. United States.

```
Parisi, C., Alfonsi, A., Mandelli, D., and Rabiti, C. Tue .
"AUTOMATIC LIMIT SURFACE SEARCH FOR PWR TRANSIENTS BY RELAP5-3D/RAVEN CODES". United States. https://www.osti.gov/servlets/purl/1478778.
```

```
@article{osti_1478778,
```

title = {AUTOMATIC LIMIT SURFACE SEARCH FOR PWR TRANSIENTS BY RELAP5-3D/RAVEN CODES},

author = {Parisi, C. and Alfonsi, A. and Mandelli, D. and Rabiti, C.},

abstractNote = {Deterministic safety analysis of nuclear power plants can be improved by applying modern algorithms and codes exploiting machine learning and parallel computing. In this paper we show the application of some of these advanced methodologies for the determination of limit surfaces. A limit surface is an n-dimensional surface describing the plant status, e.g. identifying, as function of selected plant parameters, the boundaries between failed and safe conditions for the core fuel. Using the RELAP5-3D system thermal-hydraulic code coupled to the RAVEN statistical-analysis code, we show how to apply machine-learning algorithms (near-neighbor, support-vector machine, etc.) for determining relevant limit surfaces for PWR station-blackout and loss of offsite power. As a first step, a set of training simulations is run to sample the nuclear power plant responses. Those calculations are used to train a Reduced-Order-Model (ROM), which RAVEN then uses for determining an approximated limit surface. Verification of the guessed limit surface is then automatically performed and calculation is terminated depending by the chosen convergence criteria. The combination of High Performance Computing (HPC) and ROMs allow a remarkable reduction of the time required for the surface determination. RAVEN performs also the automatic data collection of the output of the numerous runs, thus easing the workload of the safety analyst. Finally, using RAVEN “Ensamble Forward” sampling technique, we show how to inform the limit surface calculations with some of the code and input uncertainties.},

doi = {},

journal = {},

number = ,

volume = ,

place = {United States},

year = {2018},

month = {5}

}