用Transformer模型预测中子输运计算负载，省去耗时的小规模模拟。
Neurons for Neutrons: A Transformer Model for Computation Load Estimation on Domain-Decomposed Neutron Transport Problems
- 设计3D输入嵌入与专用表示，适配域分解的中子输运问题。
- 在小型模块堆仿真上达到98.2%预测准确率，可跳过小规模模拟。
- 对不同燃料组件和参数变化具有鲁棒性，适合核工程研究者使用。
域分解技术用于降低大型中子输运问题的内存开销。目前，最优处理器分配通常通过小规模仿真确定，但这一过程耗时且需随输入改变重复进行。本文提出一种具有独特3D输入嵌入的Transformer模型，其输入表示专为域分解的中子输运问题设计，可预测小规模仿真生成的子域计算负载。实验表明，该模型在小型模块堆（SMR）仿真数据上训练后，预测准确率达98.2%，可完全跳过小规模模拟步骤。同时，还评估了模型在不同燃料组件、几何结构及仿真参数变化下的鲁棒性。
原文摘要 · Abstract (English)
Domain decomposition is a technique used to reduce memory overhead on large neutron transport problems. Currently, the optimal load-balanced processor allocation for these domains is typically determined through small-scale simulations of the problem, which can be time-consuming for researchers and must be repeated anytime a problem input is changed. We propose a Transformer model with a unique 3D input embedding, and input representations designed for domain-decomposed neutron transport problems, which can predict the subdomain computation loads generated by small-scale simulations. We demonstrate that such a model trained on domain-decomposed Small Modular Reactor (SMR) simulations achieves 98.2% accuracy while being able to skip the small-scale simulation step entirely. Tests of the model's robustness on variant fuel assemblies, other problem geometries, and changes in simulation parameters are also discussed.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。