skip to main content

Title: Extending RISMC Capabilities for Real-Time Diagnostics and Prognostics

Quick and effective accident management is essential in any industry in order to limit and contain possible threats to both people and environment/assets. This is in particular relevant in the nuclear industry where accidents may have major impacts from an economic, health and societal point of view. As an example, the Fukushima Dai-ichi nuclear power plant accident highlighted the importance of the ability of plant operators and plant staff to react quickly and effectively in accident conditions. This particular event showed the importance of being able to: • Determine/estimate the actual status of the plant (i.e., diagnosis) when the monitoring system is corrupted or partially unavailable, and, • Forecast its future evolution (i.e., prognosis). In this paper we want to describe a research direction geared toward the development of a new set of advanced diagnosis and prognosis tools. We employ innovative data mining and machine learning techniques that are able to infer plant status and mimic the plant’s full temporal behavior in order to assist the reactor operators during an accident scenario.
Publication Date:
OSTI Identifier:
Report Number(s):
DOE Contract Number:
Resource Type:
Resource Relation:
Conference: ANS winter meeting,anheim (CA),11/09/2014,11/13/2014
Research Org:
Idaho National Laboratory (INL)
Sponsoring Org:
Country of Publication:
United States
97 MATHEMATICS AND COMPUTING; artificial intelligence; data mining; diagnosis; dynamic PRA; PRA; prognosis; reduced order model; surrogate; surrogate model; symbolic conversion