arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2503.19620cs.LGphysics.comp-ph
收藏

通过上下文学习和迭代LLM提示进行核工程设计问题的优化

Optimization through In-Context Learning and Iterative LLM Prompting for Nuclear Engineering Design Problems

Blue Wave AI Labs(蓝波人工智能实验室);Purdue University(普渡大学)

M. Rizki Oktavian, Anirudh Tunga, Amandeep Bakshi, Michael J. Mueterthies, J. Thomas Gruenwald, Jonathan Nistor

AI总结:

本研究提出利用大型语言模型通过迭代提示进行优化,应用于核工程中的沸水反应堆燃料栅格设计,无需调参,且能超越传统元启发式方法。

摘要:

核工程设计的优化,例如核燃料组件配置,涉及管理反应性控制和功率分布等相互竞争的目标。本研究探讨了使用“通过提示进行优化”(Optimization by Prompting)这一利用大型语言模型(LLMs)的迭代方法来解决这些挑战。该方法实现简单,无需超参数调整或复杂的数学公式。优化问题可以用简单英语描述,仅需一个评估器和一个解析脚本即可执行。LLMs的上下文学习能力使其能够理解问题的细微差别,因此它们有潜力超越传统的元启发式优化方法。本研究展示了将LLMs作为优化器应用于沸水反应堆(BWR)燃料栅格设计的实例,证明了商业LLMs相比传统方法能够获得更优的优化结果。

英文摘要:

The optimization of nuclear engineering designs, such as nuclear fuel assembly configurations, involves managing competing objectives like reactivity control and power distribution. This study explores the use of Optimization by Prompting, an iterative approach utilizing large language models (LLMs), to address these challenges. The method is straightforward to implement, requiring no hyperparameter tuning or complex mathematical formulations. Optimization problems can be described in plain English, with only an evaluator and a parsing script needed for execution. The in-context learning capabilities of LLMs enable them to understand problem nuances, therefore, they have the potential to surpass traditional metaheuristic optimization methods. This study demonstrates the application of LLMs as optimizers to Boiling Water Reactor (BWR) fuel lattice design, showing the capability of commercial LLMs to achieve superior optimization results compared to traditional methods.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑