Back propagation neural network analysis for the detection of explosives based on tagged neutron

A system for detecting explosives in walls based on the tagged neutron method was established. An associated particle neutron generator ING-27 developed by the All-Russian Research Institute of Automatics (VNIIA) is used as the neutron source, two yttrium lutetium silicate (LYSO) detectors are used for the γ detector, and a silicon detector is used as the α detector. The α-γ coincidence spectra of 300 g ammonium nitrate and TNT samples placed behind 10 cm concrete wall were measured. A neural network algorithm was applied to analyze the data. Through fine selection of time windows of α-γ coincidence spectra, the counts of full-energy peak of N, C and O elements and their proportions are selected as the input eigenvectors. The neural network is trained by the experimental data obtained by this system. Through training, eight groups of test data consisting of 32 γ-ray spectra were identified, and a 98.7% of correct detection rate was achieved.