Back propagation neural network analysis for the detection of explosives based on tagged neutron
- PDF / 942,610 Bytes
- 8 Pages / 595.276 x 790.866 pts Page_size
- 44 Downloads / 200 Views
Back propagation neural network analysis for the detection of explosives based on tagged neutron Ke Gong1 · Shu‑Jun Xiao1 · Shi‑Wei Jing1,2,3 · Yu‑Lai Zheng2 Received: 11 April 2020 © Akadémiai Kiadó, Budapest, Hungary 2020
Abstract 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. Keywords Tagged neutron method · Characteristic γ-ray · BP neural network · Explosive detection · Strong interference
Introduction The destructive and lethal power of terrorist bomb attacks can cause enormous casualties and property losses. Realtime and rapid detection of explosives has become an issue of great concern in the field of global counter-terrorism [1, 2]. Explosives can be detected in various ways, which can be achieved by testing the geometrical shape, vapor emissions and element composition of the sample. Scanning based on X-ray or γ-ray can only provide information about the shape, location, and density of the object being measured, which has severe limitations. Neutrons have high penetration for most materials and can be used for nondestructive testing. The atomic density or relative content of C, O, and N can be measured to determine whether the detected substance * Shi‑Wei Jing [email protected] 1
College of Physics, Northeast Normal University, No. 5268, People Street, Nanguan, Changchun 130024, Jilin, People’s Republic of China
2
China Institute of Atomic Energy, Beijing 121000, People’s Republic of China
3
Key Laboratory of Sichuan Higher Education—Criminal Science and Technology Laboratory, Sichuan Police College, Luzhou, Sichuan, People’s Republic of China
is an explosive [3]. Explosives can be detected by thermal neutron analysis, fast neutron analysis, pulsed fast thermal neutron method, and tagged neutron method (TNM). The coincidence spectra of α particles and γ-rays detected by the tagged neutron method based on the D-T reaction has the advantages of anti-interference and spatial partition detection compared with other neutron analysis techniques commonly used. It can effectively reduce the strong γ background, which comes from the detection process and the surrounding environment of the object bei
Data Loading...
