AI-based design of a nuclear reactor core

Abstract

The authors developed an artificial intelligence (AI)-based algorithm for the design and optimization of a nuclear reactor core based on a flexible geometry and demonstrated a 3× improvement in the selected performance metric: temperature peaking factor. The rapid development of advanced, and specifically, additive manufacturing (3-D printing) and its introduction into advanced nuclear core design through the Transformational Challenge Reactor program have presented the opportunity to explore the arbitrary geometry design of nuclear-heated structures. The primary challenge is that the arbitrary geometry design space is vast and requires the computational evaluation of many candidate designs, and the multiphysics simulation of nuclear systems is very time-intensive. Therefore, the authors developed a machine learning-based multiphysics emulator and evaluated thousands of candidate geometries on Summit, Oak Ridge National Laboratory’s leadership class supercomputer. The results presented in this work demonstrate temperature distribution smoothing in a nuclear reactor core through the manipulation of the geometry, which is traditionally achieved in light water reactors through variable assembly loading in the axial direction and fuel shuffling during refueling in the radial direction. The conclusions discuss the future implications for nuclear systems design with arbitrary geometry and the potential for AI-based autonomous design algorithms.

Artificial Intelligence for Multiphysics Nuclear Design Optimization with Additive Manufacturing

“…The second demonstration example is the optimization of the cooling channel designs for a cylindrical reactor [43,44]. The basis of this demonstration problem was to determine the optimal geometric shape in the axial dimension of the cooling channels of a simplified nuclear reactor design's full-core model.…”

Machine learning techniques for sequential learning engineering design optimisation

“…This trend has continued in recent years, seeing further industry application in fields such as chemical engineering [9] and railway engineering [10]. In a 2021 paper, Sobes et al [11] describe the machine learning (ML)-based design optimisation of a nuclear (fission) reactor core using HPC multiphysics simulation, demonstrating Bayesian optimisation of a continuously variable parameterised geometry. Though the focus was on nuclear fission, the methodology described is highly applicable to fusion design problems.…”

Large-Scale Additive Manufacturing of Silicon Carbide with Process Monitoring

“…• Demonstrating an agile design process to leverage AM and rapidly converge on an optimized, advanced nuclear microreactor design [9][10][11][12][13][14][15] • Advancing new reactor materials such as an yttrium hydride moderator [16][17][18][19][20][21][22], AM 316 stainless steel (316SS) [23], AM silicon carbide (SiC) [24,25], and the novel integration of uranium nitride tristructural-isotropic fuel [26] densely packed in an AM SiC matrix [27] • Developing the digital platform necessary to certify and qualify AM materials for nuclear applications [28][29][30] • Integrating and embedding spatially distributed sensors within AM materials for nuclear applications [31][32][33][34] • Progressing toward semi-autonomous reactor operation [35,36] • Evaluating and understanding radiation effects on AM SiC [37,38], 316SS [39], and integral TCR fuel compacts [27,40] In fiscal year (FY) 2021, the TCR program priorities shifted away from a nuclear reactor demonstration, but the focus on advancing ceramic AM for nuclear applications and qualifying AM components remained. Eventually, the TCR program was merged into the AMMT program and focused on the broader adoption of AM for nuclear applications compliant with American Society of Mechanical Engineers (ASME) Nuclear Quality Assurance (NQA-1) standards.…”