Combined application of Monte Carlo method and neural networks to simulate qualitative prompt gamma neutron activation analysis

Abstract

Prompt gamma spectrum produced by thermal neutron absorption and fast neutron inelastic scattering is simulated using Monte Carlo code MCNP4C. The simulated spectrum is analyzed with artificial neural network techniques. The neural network in our study is trained based on back-propagation algorithm with 138 gamma ray spectra. Elements existing in the 20 different substances are specified. The ANN could identify elements correctly in 96% of input cases.