skip to main content
OSTI.GOV title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: Time Dependent Data Mining in RAVEN

Abstract

RAVEN is a generic software framework to perform parametric and probabilistic analysis based on the response of complex system codes. The goal of this type of analyses is to understand the response of such systems in particular with respect their probabilistic behavior, to understand their predictability and drivers or lack of thereof. Data mining capabilities are the cornerstones to perform such deep learning of system responses. For this reason static data mining capabilities were added last fiscal year (FY 15). In real applications, when dealing with complex multi-scale, multi-physics systems it seems natural that, during transients, the relevance of the different scales, and physics, would evolve over time. For these reasons the data mining capabilities have been extended allowing their application over time. In this writing it is reported a description of the new RAVEN capabilities implemented with several simple analytical tests to explain their application and highlight the proper implementation. The report concludes with the application of those newly implemented capabilities to the analysis of a simulation performed with the Bison code.

Authors:
 [1];  [1];  [1];  [1];  [1];  [1];  [1];  [1]
  1. Idaho National Lab. (INL), Idaho Falls, ID (United States)
Publication Date:
Research Org.:
Idaho National Lab. (INL), Idaho Falls, ID (United States)
Sponsoring Org.:
USDOE Office of Nuclear Energy (NE)
OSTI Identifier:
1364494
Report Number(s):
INL/EXT-16-39860
TRN: US1703353
DOE Contract Number:
AC07-05ID14517
Resource Type:
Technical Report
Country of Publication:
United States
Language:
English
Subject:
97 MATHEMATICS AND COMPUTING; PROBABILISTIC ESTIMATION; TIME DEPENDENCE; COMPUTER CODES; SIMULATION; datamining; RAVEN; time dependent datamining

Citation Formats

Cogliati, Joshua Joseph, Chen, Jun, Patel, Japan Ketan, Mandelli, Diego, Maljovec, Daniel Patrick, Alfonsi, Andrea, Talbot, Paul William, and Rabiti, Cristian. Time Dependent Data Mining in RAVEN. United States: N. p., 2016. Web. doi:10.2172/1364494.
Cogliati, Joshua Joseph, Chen, Jun, Patel, Japan Ketan, Mandelli, Diego, Maljovec, Daniel Patrick, Alfonsi, Andrea, Talbot, Paul William, & Rabiti, Cristian. Time Dependent Data Mining in RAVEN. United States. doi:10.2172/1364494.
Cogliati, Joshua Joseph, Chen, Jun, Patel, Japan Ketan, Mandelli, Diego, Maljovec, Daniel Patrick, Alfonsi, Andrea, Talbot, Paul William, and Rabiti, Cristian. 2016. "Time Dependent Data Mining in RAVEN". United States. doi:10.2172/1364494. https://www.osti.gov/servlets/purl/1364494.
@article{osti_1364494,
title = {Time Dependent Data Mining in RAVEN},
author = {Cogliati, Joshua Joseph and Chen, Jun and Patel, Japan Ketan and Mandelli, Diego and Maljovec, Daniel Patrick and Alfonsi, Andrea and Talbot, Paul William and Rabiti, Cristian},
abstractNote = {RAVEN is a generic software framework to perform parametric and probabilistic analysis based on the response of complex system codes. The goal of this type of analyses is to understand the response of such systems in particular with respect their probabilistic behavior, to understand their predictability and drivers or lack of thereof. Data mining capabilities are the cornerstones to perform such deep learning of system responses. For this reason static data mining capabilities were added last fiscal year (FY 15). In real applications, when dealing with complex multi-scale, multi-physics systems it seems natural that, during transients, the relevance of the different scales, and physics, would evolve over time. For these reasons the data mining capabilities have been extended allowing their application over time. In this writing it is reported a description of the new RAVEN capabilities implemented with several simple analytical tests to explain their application and highlight the proper implementation. The report concludes with the application of those newly implemented capabilities to the analysis of a simulation performed with the Bison code.},
doi = {10.2172/1364494},
journal = {},
number = ,
volume = ,
place = {United States},
year = 2016,
month = 9
}

Technical Report:

Save / Share: