Development and assessment of a nearly autonomous management and control system for advanced reactors. (January 2021)

• Record Type: Journal Article
• Authors: Lin, Linyu; Athe, Paridhi; Rouxelin, Pascal; Avramova, Maria; Gupta, Abhinav; Youngblood, Robert; Lane, Jeffrey; Dinh, Nam
• Is Part Of: Annals of nuclear energy. Volume 150(2021)
• Publication Date: 2021-01
• Subjects: AI Artificial Intelligence -- DT Digital Twin -- DTE Digital Twin Environment -- DTP Digital Twin Prototype -- DTI Digital Twin Instance -- DT-D Digital Twin for Diagnosis -- DT-P Digital Twin for Prognosis -- DT-SA Digital Twin for Strategy Assessment -- DT-SI Digital Twin for Strategy Inventory -- EBR-II Experimental Breeder Reactor II -- FCL Fuel Centerline Temperature -- FDD Fault Detection and Diagnosis -- FHF Function-based Hierarchical Framework -- FN False Negative -- FNN Feed Forward Network -- FNR False Negative Rate -- FP False Positive -- FPR False Positive Rate -- HPP High-Pressure Plenum -- IHX Intermediate Heat Exchanger -- LOFA Loss of Flow Accident -- LPP Low-Pressure Plenum -- NAMAC Nearly Autonomous Management and Control -- NPP Nuclear Power plant -- PFCL Peak Fuel Centerline Temperature -- PSP Primary Sodium Pump -- PRA Probabilistic Risk Assessment -- QoI Quantity of Interest -- RMSE Root Mean Square error -- SCS Supervisory Control System -- SSF Safety Significant Factor -- TN True Negative -- TNR True Negative Rate -- TP True Positive -- TPR True Positive Rate -- UP Upper Plenum; Autonomous control -- Digital twin -- Diagnosis -- Prognosis; Nuclear energy -- Periodicals; Nuclear engineering -- Periodicals; 621.4805
• DOI: 10.1016/j.anucene.2020.107861
• Languages: English
• ISSNs: 0306-4549

Abstract

Abstract: This paper develops a Nearly Autonomous Management and Control (NAMAC) system for advanced reactors. The development process of NAMAC is characterized by a three layer-layer architecture: knowledge base, the Digital Twin (DT) developmental layer, and the NAMAC operational layer. The DT is described as a knowledge acquisition system from the knowledge base for intended uses in the NAMAC system. A set of DTs with different functions is developed with acceptable performance and assembled according to the NAMAC operational workflow to furnish recommendations to operators. To demonstrate the capability of the NAMAC system, a case study is designed, where a baseline NAMAC is implemented for operating a simulator of the Experimental Breeder Reactor II during a single loss of flow accident. When NAMAC is operated in the training domain, it can provide reasonable recommendations that prevent the peak fuel centerline temperature from exceeding a safety criterion.