Monitoring nuclear reactor systems using neural networks and fuzzy logic
- Tennessee Univ., Knoxville, TN (United States)
A new approach is presented that demonstrates the potential of trained artificial neural networks (ANNs) as generators of membership functions for the purpose of monitoring nuclear reactor systems. ANN`s provide a complex-to-simple mapping of reactor parameters in a process analogous to that of measurement. Through such ``virtual measurements`` the value of parameters with operational significance, e.g., control-valve-disk-position, valve-line-up or performance can be determined. In the methodology presented the output of a virtual measuring device is a set of membership functions which independently represent different states of the system. Utilizing a fuzzy logic representation offers the advantage of describing the state of the system in a condensed form, developed through linguistic descriptions and convenient for application in monitoring, diagnostics and generally control algorithms. The developed methodology is applied to the problem of measuring the disk position of the secondary flow control valve of an experimental reactor using data obtained during a start-up. The enhanced noise tolerance of the methodology is clearly demonstrated as well as a method for selecting the actual output. The results suggest that it is possible to construct virtual measuring devices through artificial neural networks mapping dynamic time series to a set of membership functions and thus enhance the capability of monitoring systems. 8 refs., 11 figs., 1 tab.
- Research Organization:
- Oak Ridge National Lab., TN (United States)
- Sponsoring Organization:
- USDOE, Washington, DC (United States)
- DOE Contract Number:
- AC05-84OR21400; FG07-88ER12824
- OSTI ID:
- 10103005
- Report Number(s):
- CONF-920308-6; ON: DE92003406; TRN: 92:002385
- Resource Relation:
- Conference: American Nuclear Society (ANS) topical meeting on advances in reactor physics,Charleston, SC (United States),8-11 Mar 1992; Other Information: PBD: [1991]
- Country of Publication:
- United States
- Language:
- English
Similar Records
Virtual measurements using neural networks and fuzzy logic
Integration of neural networks with fuzzy reasoning for measuring operational parameters in a nuclear reactor