期刊论文

Activity Inversion of Radioactive Source Term Based on Convolutional Neural Network

中文

原子核物理评论

1007-4627

2023

40

3

401-409

10.11804/NuclPhysRev.40.2022104

本校为第一机构

放射性源项往往分布于探测目标内部,难以直接定位和测量。为监测废物处理和核设施退役过程中放射性源项的剂量水平,本工作提出了一种基于卷积神经网络(CNN)的源项活度反演方法,建立了辐射场通量与源项活度的相关性。该方法对废物钢...展开更多 放射性源项往往分布于探测目标内部,难以直接定位和测量。为监测废物处理和核设施退役过程中放射性源项的剂量水平,本工作提出了一种基于卷积神经网络(CNN)的源项活度反演方法,建立了辐射场通量与源项活度的相关性。该方法对废物钢桶、内置过滤器滤芯的混凝土桶、内置空气过滤器的废物方箱及退役反应堆一回路管道建立源项计算模型,并基于CNN对样本进行学...

The radioactive source terms are often distributed inside the detection target,which are difficult to be located and measured directly.In order to monitor the dose level of radioactive source terms during the waste treatment and nuclear facilities decommissioning,in thi...MORE The radioactive source terms are often distributed inside the detection target,which are difficult to be located and measured directly.In order to monitor the dose level of radioactive source terms during the waste treatment and nuclear facilities decommissioning,in this research we propose an activity inversion method o...