Abstract To give better reactor physics results, the detailed 3-D diffusion module has been implemented in HTGR engineering simulator system (ESS), which needs more efficient cross-section calculations to meet real-time requirement of ESS. To calculated the HTGR’s cross-sections, more reactor variables are needed with larger scope and more complex non-linear relationships, which makes the polynomial method used well in LWR simulators hard to meet full range accuracy. In this paper, a new cross-section calculation method based on machine learning is proposed. The proposed method uses deep neuron network to consider the complex non-linear relationships between reactor variables and uses tree regression to achieve accurate cross-sections in full range, which are trained from the scattered database generated by V.S.O.P.. With the numerical tests, the proposed cross-section calculation method is proved to achieve much more accurate cross-section results than present polynomial method and also fast enough to be used in the HTGR ESS.

中文翻译：

---

基于机器学习方法的高温气冷堆工程模拟器系统截面计算新方法

摘要 为了获得更好的反应堆物理结果，高温气冷堆工程模拟器系统（ESS）中实现了详细的3-D扩散模块，需要更有效的截面计算来满足ESS的实时要求。为了计算HTGR的横截面，需要更多的反应堆变量，范围更大，非线性关系更复杂，这使得在LWR模拟器中很好地使用的多项式方法难以满足全范围精度。本文提出了一种新的基于机器学习的截面计算方法。所提出的方法使用深度神经元网络来考虑反应器变量之间复杂的非线性关系，并使用树回归实现全范围的精确横截面，这些横截面是从 VSOP 生成的分散数据库中训练出来的。通过数值测试，