基于ResNet-PINN求解中子方程算法研究  

Research on Algorithm of Solving Neutron Equation Based on ResNet-PINN

作　　者：牛艺晓 李佳芳 杨春 刘洋[3] 赖秋宇 符美蕊 蒋毅 Niu Yixiao;Li Jiafang;Yang Chun;Liu Yang;Lai Qiuyu;Fu Meirui;Jiang Yi(Key Laboratory of Land Resources Evaluation and Monitoring in Southwest China,Ministry of Education,Sichuan Normal University,Chengdu,610068,China;Chengdu State-owned Jinjiang Machine Factory,Chengdu,610043,China;School of Computer Science,Sichuan University,Chengdu,610065,China)

机构地区：[1]四川师范大学西南土地资源评价与监测教育部重点实验室,成都610068 [2]成都国营锦江机器厂,成都610043 [3]四川大学计算机学院,成都610065

出　　处：《核动力工程》2025年第2期76-80,共5页Nuclear Power Engineering

摘　　要：物理信息神经网络(PINN)作为一种结合物理知识的深度学习方法,其在求解问题的精度方面存在一定的局限性。为进一步提升PINN模型的求解精度,提出了一种基于残差网络(ResNet)结构改进的PINN模型(ResNet-PINN),详细阐述了ResNet-PINN基本原理和数值计算流程,并将其应用于核领域的中子扩散和输运方程的求解。实验验证表明,ResNet-PINN将堆芯中子扩散方程的求解精度提高了2~10倍,输运方程的求解精度提高了3~6倍,有效解决了PINN模型面临的求解精度局限性问题。As a deep learning method integrating physical knowledge,the Physics-Informed Neural Network(PINN)has certain limitations in terms of the accuracy of problem-solving.To further enhance the solution accuracy of the PINN model,an improved PINN model based on the Residual Network(ResNet)structure(ResNet-PINN)is proposed.The basic principle and numerical calculation process of ResNet-PINN are elaborated in detail,and it is applied to the solution of neutron diffusion and transport equations in the nuclear field.Experimental validation has shown that ResNet-PINN improves the solution accuracy of the reactor core neutron diffusion equation by a factor of 2 to 10 times,and enhances the solution accuracy of the transport equation by a factor of 3 to 6 times.,effectively solving the solution accuracy limitations faced by the PINN model.

关 键 词：物理信息神经网络(PINN) 残差网络(ResNet) 中子扩散方程 中子输运方程 

分 类 号：TL334[核科学技术—核技术及应用]