使用卷积神经网络分辨核子有效质量劈裂  

Using Convolutional Neural Networks to Distinguish Nucleon Effective Mass Splitting

作　　者：李理 张英逊[1,2] 杨钧评 崔莹 陈响 王馨钰 赵凯 Li Li;Zhang Yingxun;Yang Junping;Cui Ying;Chen Xiang;Wang Xinyu;Zhao Kai(Department of Nuclear Physics,China Institute of Atomic Energy,Beijing,102413,China;Guangxi Key Laboratory of Nuclear Physics and Technology,Guangxi Normal University,Guilin,Guangxi,541004,China)

机构地区：[1]中国原子能科学研究院核物理研究所,北京102413 [2]广西师范大学广西核物理与核技术重点实验室,广西桂林541004

出　　处：《核动力工程》2025年第2期68-75,共8页Nuclear Power Engineering

基　　金：国家自然科学基金(12275359、12375129、11875323、11961141003);国家重点研发计划(2023YFA1606402);中国原子能科学研究院稳定支持基础科研计划(YZ222407001301、YZ232604001601);中核集团公司领创计划(LC192209000701、LC202309000201);抗辐照应用技术创新中心创新基金(KFZC2023021201)。

摘　　要：为精确分辨核物质中质子与中子有效质量劈裂,本研究提出一种使用双通道输入的卷积神经网络(CNN)确定核子有效质量劈裂的新方法。该方法的主要思想是利用CNN学习理论模型计算质子、中子产额的纵、横动量分布。研究采用的理论模型为改进的量子分子动力学模型(ImQMD),有效相互作用参数为SkM^(*)与SLy4两套参数,分别对应于中子有效质量大于质子有效质量和中子有效质量小于质子有效质量。通过对大量模型数据的学习,建立了利用CNN分辨核子有效质量劈裂的方法。对3套丰中子弹靶系统^(48)Ca+^(208)Pb、^(48)Ca+^(124)Sn和^(124)Sn+^(124)Sn的分析表明,3套系统均在束流能量为50 MeV/u时分辨精度最高,均超过99.5%。在束流能量为270 MeV/u时,3套系统的分辨精度仍均高于93%。通过遮挡法对质子、中子产额的纵、横动量分布图像重要性区域进行了考查,给出了3套系统在50 MeV/u时的重要性图分析,指出二维动量图像中,低横动量区域对于有效质量劈裂的分辨有更大的重要性。In order to accurately distinguish the effective mass splitting of protons and neutrons in nuclear matter,a dual-channel-input convolutional neural network(CNN)is proposed for determining the effective mass splitting of nucleons.The main idea of this method is to use CNN learning theoretical model to calculate the longitudinal and transverse momentum distributions of proton and neutron yields.The theoretical model used in this study is an improved quantum molecular dynamics model(ImQMD),and the effective interaction parameters are SkM^(*)and SLy4,which correspond to the effective mass of neutrons being larger than the effective mass of protons and the effective mass of neutrons being smaller than the effective mass of protons respectively.Through the learning of a large number of model data,a method to distinguish the effective mass splitting of nucleons by CNN is established.The analysis of the three sets of neutronrich target systems—^(48)Ca+^(208)Pb,^(48)Ca+^(124)Sn,and ^(124)Sn+^(124)Sn—shows that all three systems achieve the highest resolution accuracy at a beam energy of 50 MeV/u,exceeding 99.5%.At a beam energy of 270 MeV/u,the resolution accuracy of all three systems remains above 93%.Using the blocking method,the importance regions of the longitudinal and transverse momentum distribution of proton and neutron yields were investigated.An analysis of the importance maps for the three systems at 50 MeV/u was provided,indicating that the two-dimensional energy spectra of nucleons in the low transverse momentum region are more sensitive to the effective mass splitting of nucleons.

关 键 词：核子有效质量劈裂 卷积神经网络(CNN) 丰中子系统 机器学习 重要性图 

分 类 号：TL334[核科学技术—核技术及应用]