Dynamic, risk informed decision support systems and methods
| DWPI Title: Method for generating risk-informed diagnosis, involves executing control action by user within decision guideline, where probabilistic risk assessment methods is selected from group consisting of discrete dynamic event tree |
| Abstract: The present disclosure is directed to a decision support system or tool based on a Bayesian Network (BN) framework. The diagnostic support tool is created by using advanced Probabilistic Risk Assessment (PRA) method(s) to construct Bayesian Networks (BNs) that form a Bayesian Decision Support Process (BDSP) to provide science-based decision support for understanding and managing events in complex systems. In an embodiment, the PRA method(s) may include Discrete Dynamic Event Trees (DDETs) and simulations. |
| Use: Method for generating risk-informed diagnosis and response planning support. |
| Advantage: The bayesian network can serve as a diagnosis support tool that can process real time plant data upon the onset of off-normal conditions, analyze that data in the context of the previously processed discrete dynamic event tree plant simulations, and facilitate the operators' diagnosis of the off-normal conditions by prioritizing the plant conditions that can most likely be of relevance and importance to the mitigation of the off-normal conditions. |
| Novelty: The method involves outputting results from a probabilistic assessment into a Bayesian network decision support system being executed on the computer system. generating on the computer system a probabilistic map of relationships between the variety of scenarios and observed parameters for the system. The user uses the probabilistic map to provide real-time decision support for a system condition diagnosis and a response plan for the system condition, where the real-time decision support includes the decision guidelines. A control action is executed by the user within one of the decision guidelines. The probabilistic risk assessment methods are selected from a group consisting of a discrete dynamic event tree and a computer model of a progression simulation. |
| Filed: 3/26/2015 |
| Application Number: US14669107A |
| Tech ID: SD 12729.1 |
| This invention was made with Government support under Contract No. DE-NA0003525 awarded by the United States Department of Energy/National Nuclear Security Administration. The Government has certain rights in the invention. |
| Data from Derwent World Patents Index, provided by Clarivate All rights reserved. Republication or redistribution of Clarivate content, including by framing or similar means, is prohibited without the prior written consent of Clarivate. Clarivate and its logo, as well as all other trademarks used herein are trademarks of their respective owners and used under license. |