Artificial neural network approximations of linear fractional neutron models

被引：17

作者：

Vyawahare, Vishwesh A. ^{[1
]}

Espinosa-Paredes, Gilberto ^{[2
]}

Datkhile, Gaurav ^{[1
]}

Kadam, Pratik ^{[1
]}

机构：

[1] Ramrao Adik Inst Technol, Dept Elect Engn, Nerul 400706, Navi Mumbai, India

[2] Univ Autonoma Metropolitana Iztapalapa, Area Ingn Recursos Energet, Av San Rafael Atlixco 186, Mexico City 09340, DF, Mexico

来源：

ANNALS OF NUCLEAR ENERGY | 2018年 / 113卷

关键词：

Subdiffusive transport; FNPK models; Artificial neural networks; Fractional Reduced Order Model (F-ROM); NUCLEAR-REACTOR; ANOMALOUS DIFFUSION; DYNAMICS; STABILITY; SYSTEM;

D O I：

10.1016/j.anucene.2017.11.005

中图分类号：

TL [原子能技术]; O571 [原子核物理学];

学科分类号：

0827 ; 082701 ;

摘要：

In this paper the artificial neural network (ANN) approximation for fractional neutron point kinetics (FNPK) model and fractional reduced-order model (F-ROM) is presented. The input-output data of the step response generated using the closed-loop stable fractional-order models was used for the training the ANN models. The ANN topology with various layers and different number of neutrons was tried to obtain the best approximation for the fractional-order model. The results confirm that the designed ANNs provide a good approximation to linear FNPK and F-ROM models. It was also observed that the convergence and learning of ANN is greatly affected by the type of model (FNPK or F-ROM), value of anomalous diffusion coefficient (fractional-order derivative) and the relaxation time. (C) 2017 Elsevier Ltd. All rights reserved.

引用

页码：75 / 88

页数：14

共 46 条

[1] Modeling nuclear reactor core dynamics with recurrent neural networks [J].

Adali, T ;

Bakal, B ;

Sonmez, MK ;

Fakory, R ;

Tsaoi, CO .

NEUROCOMPUTING, 1997, 15 (3-4) :363-381

[2] PWR system simulation and parameter estimation with neural networks [J].

Akkurt, H ;

Çolak, Ü .

ANNALS OF NUCLEAR ENERGY, 2002, 29 (17) :2087-2103

[3]

[Anonymous], 1999, FRACTIONAL DIFFERENT

[4]

[Anonymous], P 18 INTERNATIONALCO

[5]

Assaleh K., 2007, INT S SIGNAL PROCESS, P1

[6]

AXTELL M, 1990, PROC NAECON IEEE NAT, P563, DOI 10.1109/NAECON.1990.112826

[7] Simulating the dynamics of the neutron flux in a nuclear reactor by locally recurrent neural networks [J].

Cadini, F. ;

Zio, E. ;

Pedroni, N. .

ANNALS OF NUCLEAR ENERGY, 2007, 34 (06) :483-495

[8]

CARLSON GE, 1964, IEEE T CIRCUITS SYST, VCT11, P210

[9] On the feedback stability of linear FNPK equations [J].

Cazares-Ramirez, R. -I. ;

Vyawahare, Vishwesh. A. ;

Espinosa-Paredes, G. ;

Nataraj, P. S. V. .

PROGRESS IN NUCLEAR ENERGY, 2017, 98 :45-58

[10] FRACTAL SYSTEM AS REPRESENTED BY SINGULARITY FUNCTION [J].

CHAREF, A ;

SUN, HH ;

TSAO, YY ;

ONARAL, B .

IEEE TRANSACTIONS ON AUTOMATIC CONTROL, 1992, 37 (09) :1465-1470

← 1 2 3 4 5 →