Comparison of theoretical and machine learning models to estimate gamma ray source positions using plastic scintillating optical fiber detector

Nuclear Engineering and Technology

Cheol Ho Pyeon¹  Seunghyeon Kim²  Siwon Song²  Taeseob Lim²  Bongsoo Lee²  Jin Ho Kim²  Jinhong Kim²  Jae Hyung Park² 

[1] Research Center for Safe Nuclear System, Institute for Integrated Radiation and Nuclear Science, Kyoto University, Asashiro-nishi, Kumatori-cho, Sennan-gun, Osaka, 590-0494, Japan;School of Energy Systems Engineering, Chung-Ang University, Seoul, 06974, South Korea;

关键词: Plastic scintillating optical fiber;    Gamma ray detection;    Position estimation;    Machine learning;    Nonlinear regression;   

DOI  :  

来源: DOAJ

【 摘 要 】

In this study, one-dimensional gamma ray source positions are estimated using a plastic scintillating optical fiber, two photon counters and via data processing with a machine learning algorithm. A nonlinear regression algorithm is used to construct a machine learning model for the position estimation of radioactive sources. The position estimation results of radioactive sources using machine learning are compared with the theoretical position estimation results based on the same measured data. Various tests at the source positions are conducted to determine the improvement in the accuracy of source position estimation. In addition, an evaluation is performed to compare the change in accuracy when varying the number of training datasets. The proposed one-dimensional gamma ray source position estimation system with plastic scintillating fiber using machine learning algorithm can be used as radioactive leakage scanners at disposal sites.

【 授权许可】

Unknown