Digital-twin-based improvements to diagnosis, prognosis, strategy assessment, and discrepancy checking in a nearly autonomous management and control system. (February 2022)

• 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 166(2022)
• Publication Date: 2022-02
• Subjects: ANN Artificial neural network -- AOR allowable operating region -- BEP best efficiency point -- DT digital twin -- DT-D diagnosis digital twin -- DT-P prognosis digital twin -- EBR-II Experimental Breeder Reactor II -- FNN feedforward neural network -- GSIM GOTHIC simulator -- K-L Kullback-Leibler -- PFCL peak fuel centerline temperature -- POR Preferred Operating Region -- I&C instrumentation and control -- LOF loss of flow -- MSE mean squared error -- NAMAC Nearly Autonomous Management and Control -- PSP primary sodium pump -- RMSE root mean square error -- RNN recurrent neural network -- SCRAM From the NRC Web site: "the sudden shutting down of a nuclear reactor usually by rapid insertion of control rods." (The etymology of the term is unclear.) -- SMBO sequential model-based optimization -- SSF safety-significant factor; autonomous control -- digital twin -- diagnosis -- prognosis; Nuclear energy -- Periodicals; Nuclear engineering -- Periodicals; 621.4805
• DOI: 10.1016/j.anucene.2021.108715
• Languages: English
• ISSNs: 0306-4549

Abstract

Highlights: The development and assessment of digital twins of different functions. The development and assessment of a NAMAC system. The demonstration of NAMAC and discrepancy checker on a EBR-II simulator. Abstract: The Nearly Autonomous Management and Control System (NAMAC) is a comprehensive control system that assists plant operations by furnishing control recommendations to operators in a broad class of situations. This study refines a NAMAC system for making reasonable recommendations during complex loss-of-flow scenarios with a validated Experimental Breeder Reactor II simulator, digital twins improved by machine-learning algorithms, a multi-attribute decision-making scheme, and a discrepancy checker for identifying unexpected recommendation effects. We assess the performance of each NAMAC component, while we demonstrate and evaluated the capability of NAMAC in a class of loss-of-flow scenarios.