An application of neural networks and artificial intelligence for in-core fuel management
- Univ. of Tennessee, Knoxville (United States)
This paper reports the feasibility of using expert systems in combination with neural networks and neutronics calculations to improve the efficiency for obtaining optimal candidate reload core designs. The general objectives of this research are as follows: (1) generate a suitable data base and ancillary software for training neural networks that duplicate neutronics calculations. (2) develop a graphical interface with neutronics software and neural networks for manual shuffling of reload cores. (3) construct an expert system for shuffling reload cores with specified rules. (4) develp neural networks that capture the nonlinear behavior of fuel depletion. (5) integrate the neural networks and neutronics software with an expert system to specify reload cores that obtain appropriate figure of merit.
- OSTI ID:
- 6661238
- Report Number(s):
- CONF-921102-; CODEN: TANSAO
- Journal Information:
- Transactions of the American Nuclear Society; (United States), Vol. 66; Conference: Joint American Nuclear Society (ANS)/European Nuclear Society (ENS) international meeting on fifty years of controlled nuclear chain reaction: past, present, and future, Chicago, IL (United States), 15-20 Nov 1992; ISSN 0003-018X
- Country of Publication:
- United States
- Language:
- English
Similar Records
Hybrid Intelligent Perception System: Intelligent perception through combining Artificial Neural Networks and an Expert System
Evaluating the performance of two neutron spectrum unfolding codes based on iterative procedures and artificial neural networks
Related Subjects
99 GENERAL AND MISCELLANEOUS//MATHEMATICS, COMPUTING, AND INFORMATION SCIENCE
FUEL MANAGEMENT
ARTIFICIAL INTELLIGENCE
OPTIMIZATION
EXPERT SYSTEMS
KNOWLEDGE BASE
NEURAL NETWORKS
REACTOR CORES
REACTOR COMPONENTS
220300* - Nuclear Reactor Technology- Fuel Elements
990200 - Mathematics & Computers