inis 20(24): e3

Research Article

Synapse. A Neutron Spectrum Unfolding Code Based on Generalized Regression Artificial Neural Networks

Download46 downloads
  • @ARTICLE{10.4108/eai.21-10-2020.166667,
        author={Ma. del Rosario Martinez-Blanco and Arturo Serrano-Mu\`{o}oz and Hector Rene Vega-Carrillo and Marco Aurelio de Sousa-Lacerda and Roberto Mendez-Villafa\`{o}e and Eduardo Gallego and Antonio del Rio de Santiago and Luis Octavio Solis-Sanchez and Jose Manuel Ortiz-Rodriguez},
        title={Synapse. A Neutron Spectrum Unfolding Code Based on Generalized Regression Artificial Neural Networks},
        journal={EAI Endorsed Transactions on Industrial Networks and Intelligent Systems},
        volume={7},
        number={24},
        publisher={EAI},
        journal_a={INIS},
        year={2020},
        month={10},
        keywords={Neutron spectrometry and dosimetry, Artificial intelligence, Generalized regression artificial neural networks, unfolding code, programming},
        doi={10.4108/eai.21-10-2020.166667}
    }
    
  • Ma. del Rosario Martinez-Blanco
    Arturo Serrano-Muñoz
    Hector Rene Vega-Carrillo
    Marco Aurelio de Sousa-Lacerda
    Roberto Mendez-Villafañe
    Eduardo Gallego
    Antonio del Rio de Santiago
    Luis Octavio Solis-Sanchez
    Jose Manuel Ortiz-Rodriguez
    Year: 2020
    Synapse. A Neutron Spectrum Unfolding Code Based on Generalized Regression Artificial Neural Networks
    INIS
    EAI
    DOI: 10.4108/eai.21-10-2020.166667
Ma. del Rosario Martinez-Blanco1, Arturo Serrano-Muñoz1, Hector Rene Vega-Carrillo2, Marco Aurelio de Sousa-Lacerda3, Roberto Mendez-Villafañe4, Eduardo Gallego5, Antonio del Rio de Santiago1, Luis Octavio Solis-Sanchez1, Jose Manuel Ortiz-Rodriguez1,*
  • 1: Laboratorio de Innovación y Desarrollo Tecnológico en Inteligencia Artificial. Unidad Académica de Ingeniería Eléctrica. Universidad Autónoma de Zacatecas. Av. Ramón López Velarde, 801, Zacatecas, México. C.P. 98000
  • 2: Unidad Académica de Estudios Nucleares, Universidad Autónoma de Zacatecas. C. Ciprés, 10, Col. Centro, C.P.98000, Zacatecas, Zacatecas, México
  • 3: Centro de Investigación de Tecnología Nuclear de la Comisión Nacional de Energía Nuclear (CDTN-CNEN), Av. Presidente Antonio Carlos, 6627, Belo Horizonte, Brazil
  • 4: Laboratorio de Patrones Neutrónicos del Departamento de Metrología de Radiaciones Ionizantes del Centro de Investigaciones Energéticas, Medioambientales y Tecnológicas (CIEMAT), Avda. Complutense, 22, 28040, Madrid, España
  • 5: Departamento de Ingeniería Energética de la Universidad Politécnica de Madrid, ETSI Industriales, C. José Gutiérrez Abascal, 2, 28006, Madrid, España
*Contact email: Morvymm@yahoo.com.mx

Abstract

In its broadest sense, the term artificial intelligence indicates the ability of an artifact to perform the same types of functions that characterize human thought. The goal of AI is to use algorithms, heuristics and methodologies based on the ways in which the human brain solves problems. Artificial neural networks recreate the structure of the human brain imitating the learning process. The Artificial neural networks theory has provided an alternative to classical computing for those problems in which traditional methods have delivered results that are not very convincing or not very convenient such as in the case of the neutron spectrometry and dosimetry problem for radiation protection purposes, using the Bonner spheres spectrometer as measurement system, mainly because many problems are encountered when trying to determine the neutron energy spectrum of a measured data. The most delicate part of the spectrometry based on this system is the unfolding process, for which several neutron spectrum unfolding codes have being developed. However, these codes require an initial guess spectrum in order to initiate the unfolding process. Their poor availability and their not easy management for the end user are other associated problems. Artificial Intelligence technology, is an alternative technique that is gaining popularity among researchers in neutron spectrometry research area, since it offers better results compared with the traditional solution methods. In this work, "Synapse", a neutron spectrum unfolding code based on Generalized Regression Artificial Neural Networks technology is presented. The Synapse code is capable to unfold the neutron spectrum and to calculate 15 dosimetric quantities using the count rates, coming from a BSS as the only entrance information. The results obtained show that the Synapse code, based on GRANN technology, is a promising and innovative technological alternative for solving the neutron spectrometry and dosimetry problems.