arXiv：cs.LG· Will Savage, Logan Burnett, Dean Price·· 4 小时前AI 评分34
基于梯度的核临界实验优化：用神经网络替代特征值灵敏度
Gradient-based optimization of nuclear criticality experiments using neural surrogate eigenvalue sensitivities
AI 导读
研究团队训练物理信息深度神经网络预测栅格型临界实验几何的中子灵敏度，并利用其可微性对材料组合进行梯度优化，以最大化与目标技术的相关系数 c_k。该方法应用于 HALEU 燃料的 TN-Americas TN-LC 运输容器验证，三种关注配置分别取得 0.97757、0.81324 和 0.93276 的 c_k 分数。
正文
Abstract:The validation of advanced nuclear reactor designs and fuel concepts will require the design of new critical experiments with high neutronic similarity to the target technology. Neutronic similarity can be quantified by the correlation coefficient $c_k$, which captures the shared bias in $k_\text{eff}$ induced by uncertainties in nuclear data. Generally, a $c_k\geq0.9$ is needed for an experiment to be sufficiently similar to a target technology. In this work, a physics-informed deep neural network is trained to predict the neutronic sensitivity of grid-based critical experiment geometries. The differentiability of the neural network is used to enable gradient-based design optimization of new experiment geometries to maximize $c_k$ with the sensitivity profile of a target technology. This approach allows for optimization over the combinatorial design space of potential material combinations within the grid, moving beyond traditional parametric optimization approaches. The method is applied to the validation of the TN-Americas TN-LC transportation cask with HALEU fuel, for which existing critical experiment coverage is limited. This application is shown to produce experiment geometries achieving $c_k$ scores of 0.97757, 0.81324, and 0.93276 for three configurations of interest.
| Subjects: | Machine Learning (cs.LG) |
| Cite as: | arXiv:2606.04033 [cs.LG] |
| (or arXiv:2606.04033v2 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2606.04033 arXiv-issued DOI via DataCite |
Submission history
From: Dean Price [view email]
[v1]
Mon, 1 Jun 2026 21:19:18 UTC (3,057 KB)
[v2]
Wed, 7 Oct 2026 17:17:59 UTC (3,154 KB)
来源：arXiv：cs.LG · arxiv.org