Radiation Protection Dosimetry Advance Access originally published online on May 23, 2007
Radiation Protection Dosimetry 2007 126(1-4):408-412; doi:10.1093/rpd/ncm084
| ||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
Artificial neural networks technology for neutron spectrometry and dosimetry
1 Unidad Académica de Estudios Nucleares de la Universidad Autónoma de Zacatecas, Apdo. Postal 336, 98000 Zacatecas, Zac. México
2 Unidad Académica de Ingeniería Eléctrica de la Universidad Autónoma de Zacatecas, Apdo. Postal 336, 98000 Zacatecas, Zac. México
3 Departamento de Ingeniería Nuclear, Universidad Politécnica de Madrid, C. José Gutiérrez Abascal 2, E-28006 Madrid, Spain
4 Departamento de Física Teórica, Atómica, Molecular y Nuclear, Universidad de Valladolid, Valladolid, Spain
* Corresponding author: fermineutron{at}yahoo.com
Artificial Neural Network Technology has been applied to unfold neutron spectra and to calculate 13 dosimetric quantities using seven count rates from a Bonner Sphere Spectrometer with a 6LiI(Eu). Two different networks, one for spectrometry and another for dosimetry, were designed. To train and test both networks, 177 neutron spectra from the IAEA compilation were utilised. Spectra were re-binned into 31 energy groups, and the dosimetric quantities were calculated using the MCNP code and the fluence-to-dose conversion coefficients from ICRP 74. Neutron spectra and UTA4 response matrix were used to calculate the expected count rates in the Bonner spectrometer. Spectra and H*(10) of 239PuBe and 241AmBe were experimentally obtained and compared with those determined with the artificial neural networks.