Core reactivity estimation in space reactors using recurrent dynamic networks
- Departments of Nuclear Engineering, Texas A M University, College Station, Texas (USA)
- Department of Electrical and Computer Engineering, University of California at Irvine, Irvine, California (USA)
A recurrent Multi Layer Perceptron (MLP) network topology is used in the identification of nonlinear dynamic systems from only the input/output measurements. This effort is part of a research program devoted in developing real-time diagnostics and predictive control techniques for large-scale complex nonlinear dynamic systems. The identification is performed in the discrete time domain, with the learning algorithm being a modified form of the Back Propagation (BP) rule. The Recurrent Dynamic Network (RDN) developed is applied for the total core reactivity prediction of a spacecraft reactor from only neutronic power level measurements. Results indicate that the RDN can reproduce the nonlinear response of the reactor while keeping the number of nodes roughly equal to the relative order of the system. As accuracy requirements are increased, the number of required nodes also increases, however, the order of the RDN necessary to obtain such results is still in the same order of magnitude as the order of the matematical model of the system. There are a number of issues identified regarding the behavior of the RDN, which at this point are unresolved and require further research. Nevertheless, it is believed that use of the recurrent MLP structure with a variety of different learning algorithms may prove useful in utilizing artifical neural networks (ANNs) for recognition, classification and prediction of dynamic systems.
- DOE Contract Number:
- FG07-89ER12893
- OSTI ID:
- 5250642
- Report Number(s):
- CONF-910116-; CODEN: APCPC; TRN: 91-027457
- Journal Information:
- AIP Conference Proceedings (American Institute of Physics); (United States), Vol. 217:3; Conference: 8. symposium on space nuclear power systems, Albuquerque, NM (United States), 6-10 Jan 1991; ISSN 0094-243X
- Country of Publication:
- United States
- Language:
- English
Similar Records
Empirical model development and validation with dynamic learning in the recurrent multilayer perception
Empirical modeling of nuclear power plants using neural networks
Related Subjects
21 SPECIFIC NUCLEAR REACTORS AND ASSOCIATED PLANTS
SPACE POWER REACTORS
REACTOR MONITORING SYSTEMS
ARTIFICIAL INTELLIGENCE
NONLINEAR PROBLEMS
REACTOR CONTROL SYSTEMS
REACTOR CORES
SYSTEMS ANALYSIS
CONTROL SYSTEMS
MOBILE REACTORS
POWER REACTORS
REACTOR COMPONENTS
REACTORS
NESDPS Office of Nuclear Energy Space and Defense Power Systems
220400* - Nuclear Reactor Technology- Control Systems
220800 - Nuclear Reactor Technology- Propulsion Reactors