Abstract
AbstractMachine learning-based modeling of reactor physics problems has attracted increasing interest in recent years. Despite some progress in one-dimensional problems, there is still a paucity of benchmark studies that are easy to solve using traditional numerical methods albeit still challenging using neural networks for a wide range of practical problems. We present two networks, namely the Generalized Inverse Power Method Neural Network (GIPMNN) and Physics-Constrained GIPMNN (PC-GIPIMNN) to solve K-eigenvalue problems in neutron diffusion theory. GIPMNN follows the main idea of the inverse power method and determines the lowest eigenvalue using an iterative method. The PC-GIPMNN additionally enforces conservative interface conditions for the neutron flux. Meanwhile, Deep Ritz Method (DRM) directly solves the smallest eigenvalue by minimizing the eigenvalue in Rayleigh quotient form. A comprehensive study was conducted using GIPMNN, PC-GIPMNN, and DRM to solve problems of complex spatial geometry with variant material domains from the field of nuclear reactor physics. The methods were compared with the standard finite element method. The applicability and accuracy of the methods are reported and indicate that PC-GIPMNN outperforms GIPMNN and DRM.
Publisher
Springer Science and Business Media LLC
Subject
Nuclear Energy and Engineering,Nuclear and High Energy Physics
Reference77 articles.
1. A. Hébert, Applied Reactor Physics, 3rd edn. (Presses internationales Polytechnique, 2020)
2. T.B. Fowler, D.R. Vondy, Nuclear reactor core analysis code: Citation. (Jan 1969) https://www.osti.gov/biblio/4772428
3. A. Hébert, Development of the nodal collocation method for solving the neutron diffusion equation. Ann. Nuclear Energy 14, 527–541 (1987). https://doi.org/10.1016/0306-4549(87)90074-0
4. L.A. Semenza, E.E. Lewis, E.C. Rossow, The application of the finite element method to the multigroup neutron diffusion equation. Nuclear Sci. Eng. 47, 302–310 (1972). https://doi.org/10.13182/NSE72-A22416
5. A. Hébert, Application of a dual variational formulation to finite element reactor calculations. Ann. Nuclear Energy 20, 823–845 (1993). https://doi.org/10.1016/0306-4549(93)90076-2
Cited by
1 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献