Convolutional Neural Network–Aided Temperature Field Reconstruction: An Innovative Method for Advanced Reactor Monitoring. (4th May 2023)

• Record Type: Journal Article
• Authors: Leite, Victor C.; Merzari, Elia; Ponciroli, Roberto; Ibarra, Lander
• Is Part Of: Nuclear technology. Volume 209:Number 5(2023)
• Page Start: 645
• Page End: 666
• Publication Date: 2023-05-04
• Subjects: Molten Salt Fast Reactor -- machine learning -- monitoring system; Nuclear engineering -- Periodicals; Nuclear engineering; Nuclear Physics; Periodicals; Periodicals; 621.48
• DOI: 10.1080/00295450.2022.2151822
• Languages: English
• ISSNs: 1943-7471

Abstract

Abstract: In this study, the capabilities of a physics-informed convolutional neural network (CNN) for reconstructing the temperature field from a limited set of measurements taken at the boundaries of internal flows are demonstrated. Such an approach enables the development of less invasive monitoring methods for real-time plant diagnostics. As a test case, a Molten Salt Fast Reactor (MSFR) design was selected. This circulating fuel reactor has received interest from both scientific and industrial communities due to its intrinsic safety and sustainability. Molten salt flows in such reactors, however, can present highly localized temperature peaks that can induce significant thermal stresses onto the vessel walls. At these local maxima, the salt temperature may exceed a thousand kelvins, which makes a direct measurement challenging or even unfeasible. The proposed CNN algorithm allows one to detect indirectly such discontinuities through an accurate, albeit indirect, temperature measurement method during reactor operation. The datasets employed to train and test the machine learning models in the present work were generated with Nek5000, a computational fluid dynamics (CFD) code developed at Argonne National Laboratory. The CNN algorithm is trained with CFD results that span a set of MSFR operational power and flow ranges. To demonstrate the efficacy of the algorithm, predictions are made for test cases contained within the training range but for which the CFD data were not used when training. Results demonstrate that the proposed technique properly characterizes temperature peaks and distributions within the domain for a broad range of scenarios.