Details
| Original language | English |
|---|---|
| Pages (from-to) | 1293-1306 |
| Number of pages | 14 |
| Journal | Nuclear engineering and technology |
| Volume | 41 |
| Issue number | 10 |
| Publication status | Published - Dec 2009 |
| Externally published | Yes |
Abstract
In this paper, an infinite impulse response locally recurrent neural network (IIR-LRNN) is employed for modelling the dynamics of the Lead Bismuth Eutectic experimental Accelerator Driven System (LBE-XADS). The network is trained by recursive back-propagation (RBP) and its ability in estimating transients is tested under various conditions. The results demonstrate the robustness of the locally recurrent scheme in the reconstruction of complex nonlinear dynamic relationships.
Keywords
- Locally recurrent neural network, Nonlinear dynamics, Nuclear reactor, Transient extrapolation, Transient interpolation, Transient recovery
ASJC Scopus subject areas
- Energy(all)
- Nuclear Energy and Engineering
Cite this
- Standard
- Harvard
- Apa
- Vancouver
- BibTeX
- RIS
In: Nuclear engineering and technology, Vol. 41, No. 10, 12.2009, p. 1293-1306.
Research output: Contribution to journal › Article › Research › peer review
}
TY - JOUR
T1 - Modelling the dynamics of the lead bismuth eutectic experimental accelerator driven system byan infinite impulse response locally recurrent neural network
AU - Zio, Enrico
AU - Pedroni, Nicola
AU - Broggi, Matteo
AU - Golea, Lucia Roxana
N1 - Copyright: Copyright 2018 Elsevier B.V., All rights reserved.
PY - 2009/12
Y1 - 2009/12
N2 - In this paper, an infinite impulse response locally recurrent neural network (IIR-LRNN) is employed for modelling the dynamics of the Lead Bismuth Eutectic experimental Accelerator Driven System (LBE-XADS). The network is trained by recursive back-propagation (RBP) and its ability in estimating transients is tested under various conditions. The results demonstrate the robustness of the locally recurrent scheme in the reconstruction of complex nonlinear dynamic relationships.
AB - In this paper, an infinite impulse response locally recurrent neural network (IIR-LRNN) is employed for modelling the dynamics of the Lead Bismuth Eutectic experimental Accelerator Driven System (LBE-XADS). The network is trained by recursive back-propagation (RBP) and its ability in estimating transients is tested under various conditions. The results demonstrate the robustness of the locally recurrent scheme in the reconstruction of complex nonlinear dynamic relationships.
KW - Locally recurrent neural network
KW - Nonlinear dynamics
KW - Nuclear reactor
KW - Transient extrapolation
KW - Transient interpolation
KW - Transient recovery
UR - http://www.scopus.com/inward/record.url?scp=75149132848&partnerID=8YFLogxK
U2 - 10.5516/NET.2009.41.10.1293
DO - 10.5516/NET.2009.41.10.1293
M3 - Article
AN - SCOPUS:75149132848
VL - 41
SP - 1293
EP - 1306
JO - Nuclear engineering and technology
JF - Nuclear engineering and technology
SN - 1738-5733
IS - 10
ER -