Reliability estimation of an advanced nuclear fuel using coupled active learning, multifidelity modeling, and subset simulation. (October 2022)

• Record Type: Journal Article
• Authors: Dhulipala, Somayajulu L.N.; Shields, Michael D.; Chakroborty, Promit; Jiang, Wen; Spencer, Benjamin W.; Hales, Jason D.; Labouré, Vincent M.; Prince, Zachary M.; Bolisetti, Chandrakanth; Che, Yifeng
• Is Part Of: Reliability engineering & system safety. Volume 226(2022)
• Publication Date: 2022-10
• Subjects: Active learning -- Nuclear fuel -- Reliability -- Monte Carlo -- Variance reduction -- TRISO fuel -- Deep neural networks -- Gaussian process; Reliability (Engineering) -- Periodicals; System safety -- Periodicals; Industrial safety -- Periodicals; Fiabilité -- Périodiques; Sécurité des systèmes -- Périodiques; Sécurité du travail -- Périodiques; 620.00452
• DOI: 10.1016/j.ress.2022.108693
• Languages: English
• ISSNs: 0951-8320

Abstract

Abstract: Tristructural isotropic (TRISO)-coated particle fuel is a robust nuclear fuel and determining its reliability is critical for the success of advanced nuclear technologies. However, TRISO failure probabilities are small and the associated computational models are expensive. We used coupled active learning, multifidelity modeling, and subset simulation to estimate the failure probabilities of TRISO fuels using several 1D and 2D models. With multifidelity modeling, we replaced expensive high-fidelity (HF) model evaluations with information fusion from two low-fidelity (LF) models. For the 1D TRISO models, we considered three multifidelity modeling strategies: only Kriging, Kriging LF prediction plus Kriging correction, and deep neural network (DNN) LF prediction plus Kriging correction. While the results across these multifidelity modeling strategies compared satisfactorily, strategies employing information fusion from two LF models called the HF model least often. Next, for the 2D TRISO model, we considered two multifidelity modeling strategies: DNN LF prediction plus Kriging correction (data-driven) and 1D TRISO LF prediction plus Kriging correction (physics-based). The physics-based strategy, as expected, consistently required the fewest calls to the HF model. However, the data-driven strategy had a lower overall simulation time since the DNN predictions are instantaneous, and the 1D TRISO model requires a non-negligible simulation time. Highlights: TRISO, a robust nuclear fuel, is associated with small failure probabilities. Active learning with multifidelity modeling to efficiently estimate TRISO failure. Multifidelity information fusion from two low-fidelity models most efficient. Physics-based multifidelity strategy reduces calls to high-fidelity model. Data-driven multifidelity strategy has less overall simulation time.