Neutron spectra unfolding in Bonner spheres spectrometry using neural networks

Abstract

The neural network method has been used for the unfolding of neutron spectra in neutron spectrometry by Bonner spheres. A back propagation algorithm was used for training of neural networks. 4 mm x 4 mm bare LiI (Eu) and in a polyethylene sphere set: 2, 3, 4, 5, 6, 7, 8, 10, 12, 18 inch diameter have been used for unfolding of neutron spectra. Neural networks were trained by 199 sets of neutron spectra, which were subdivided into 6, 8, 10, 12, 15 and 20 energy bins and for each of them an appropriate neural network was designed and trained. The validation was performed by the 21 sets of neutron spectra. A neural network with 10 energy bins which had a mean value of error of 6% for dose equivalent estimation of spectra in the validation set showed the best results. The obtained results show that neural networks can be applied as an effective method for unfolding neutron spectra especially when the main target is neutron dosimetry.

Robust Design of Artificial Neural Networks Methodology in Neutron Spectrometry

“…To unfold the neutron spectrum, Φ, several methods are used. [43,44,47] ANN technology is a useful alternative to solve this problem; [25][26][27][28][29][30][31] however, several drawbacks must be solved in order to simplify the use of these procedures.…”

“…Recently, the use of ANN technology has been applied with relative success in the research area of nuclear sciences, [3] mainly in the neutron spectrometry and dosimetry domains. [25][26][27][28][29][30][31] …”

Neural network unfolding of neutron spectrum measured by gold foil-based Bonner sphere

“…The prior spectrum, time-consuming procedure, the low-resolution spectrum are some drawbacks which these approaches offer [12]. Each of the mentioned difficulties has motivated the development of complementary procedures such as maximum entropy [13], Genetic Algorithms (GA) [14,15] and Artificial Neural Networks (ANN) [16][17][18]. The use of ANN to unfold neutron spectra from the count rates measured with BSS system has become in an alternative procedure [19,20], which has been applied with success, and some authors have expressed that this technology merit attention because of success obtained [21].…”

Neutron spectrometry using artificial neural networks

“…Each of them has difficulties that motivate the development of complementary procedures García-Domínguez et al, 1999). Recently, methods based upon maximum entropy (Reginatto et al, 2002), genetic algorithms (Freeman et al, 1999;Mukherjee, 2002) and artificial neural nets (Cordes et al, 1998;Fehrenbacher et al, 1999;Braga and Dias, 2002;Kardan et al, 2003Kardan et al, , 2004Palacios et al, 2004) have been utilized. Artificial neural networks (ANN) require the use of detectors whose response functions are independent.…”

“…A neural network is a set of input nodes that links directly to a series of output nodes or indirectly through one or more hidden layers (Kardan et al, 2003). The use of an artificial neural network requires the training of the network and the test of the trained network.…”