基于贝叶斯优化的压水堆堆芯换料优化方法研究  

Research on PWR Core Refueling Optimization Method Based on Bayesian Optimization

作　　者：周原成 李云召[1] 吴宏春[1] Zhou Yuancheng;Li Yunzhao;Wu Hongchun(School of Energy and Power Engineering,Xi’an Jiaotong University,Xi’an,710000,China)

机构地区：[1]西安交通大学能源与动力工程学院,西安710000

出　　处：《核动力工程》2025年第2期202-208,共7页Nuclear Power Engineering

基　　金：国家自然科学基金(12375175)。

摘　　要：压水堆堆芯换料优化是核电站安全高效经济运行的关键环节,属于有约束的非线性非凸整数组合优化问题。传统方法计算效率低,容易陷入局部最优解。本文提出了一种基于变分自动编码器、深度度量学习和贝叶斯优化的换料优化方法。该方法利用变分自动编码器将离散的堆芯布置方案映射到连续的隐变量空间;再通过深度度量学习构建结构化的隐空间,使堆芯物理特性相近的样本在隐空间中距离也相近;然后利用多目标贝叶斯优化方法在隐空间中高效地搜索最优解,并通过解码器将最优隐变量解码成对应的堆芯布置方案。基于某M310堆芯首循环初装料数据进行的实验验证表明,该方法能够有效提高换料优化效率和求解质量,获得优于传统方法的布置方案。Refueling optimization for pressurized water reactor(PWR)cores is crucial for the safe,efficient,and cost-effective operation of nuclear power plants,which is a constrained,nonlinear,non-convex integer combinatorial optimization challenge.Traditional methods often struggle with low computational efficiency and the risk of getting trapped in local optima.This paper presents a refueling optimization approach based on variational autoencoders,deep metric learning,and Bayesian optimization.The method leverages variational autoencoders to map discrete core layout configurations into a continuous latent space.Deep metric learning is then used to construct the latent space such that samples with similar core physical characteristics are positioned closer together.A multi-objective Bayesian optimization is subsequently applied to efficiently search for optimal solutions in this latent space,and a decoder transforms the optimal latent variables back into corresponding core layouts.Experimental validation using the first-cycle initial loading data of an M310 core demonstrates that this method significantly improves refueling optimization efficiency and solution quality,producing better configurations than traditional methods.

关 键 词：堆芯换料优化 贝叶斯优化 变分自动编码器 深度度量学习 NECP-Bamboo 

分 类 号：TL32[核科学技术—核技术及应用]