Determination of Gamma point source efficiency based on a back-propagation neural network

• Published in: Nuclear science and techniques Vol. 29; no. 5; pp. 81 - 89
• Main Authors: Zheng, Hong-Long, Tuo, Xian-Guo, Peng, Shu-Ming, Shi, Rui, Li, Huai-Liang, Lu, Jing, Li, Jin-Fu
• Format: Journal Article
• Language: English
• Published: Singapore Springer Singapore 01.05.2018; Institute of Nuclear Physics and Chemistry, China Academy of Engineering Physics, Mianyang 621900, China; Fundamental Science on Nuclear Wastes and Environmental Safety Laboratory, Southwest University of Science and Technology, Mianyang 621010, China%Institute of Nuclear Physics and Chemistry, China Academy of Engineering Physics, Mianyang 621900, China%Fundamental Science on Nuclear Wastes and Environmental Safety Laboratory, Southwest University of Science and Technology, Mianyang 621010, China; College of Chemistry and Environmental Engineering,Sichuan University of Science and Engineering,Zigong 643000, China%College of Chemistry and Environmental Engineering,Sichuan University of Science and Engineering,Zigong 643000, China
• Subjects: Energy; Hadrons; Heavy Ions; Nuclear Energy; Nuclear Physics; Gamma point source; BP neural network; Efficiency; HPGe detector
• ISSN: 1001-8042; 2210-3147
• DOI: 10.1007/s41365-018-0410-4

Efficiency is an important factor in quantitative and qualitative analysis of radionuclides, and the gamma point source efficiency is related to the radial angle, detection distance, and gamma-ray energy. In this work, on the basis of a back-propagation (BP) neural network model, a method to determine the gamma point source efficiency is developed and validated. The efficiency of the point sources 137 Cs and 60 Co at discrete radial angles, detection distances, and gamma-ray energies is measured, and the BP neural network prediction model is constructed using MATLAB. The gamma point source efficiencies at different radial angles, detection distances, and gamma-ray energies are predicted quickly and accurately using this nonlinear prediction model. The results show that the maximum error between the predicted and experimental values is 3.732% at 661.661 keV, 11 π /24, and 35 cm, and those under other conditions are less than 3%. The gamma point source efficiencies obtained using the BP neural network model are in good agreement with experimental data.