ABSTRACT
The paper considers Adaptive Learning Networks (ALN) as a tool to solve the problems of modeling, prediction, diagnostics and pattern recognition in complex systems. This method is similar to the neural network technique. The main difference is the self-organization of network structure on the basis of generation and estimation of various nodes, connections and weights. A set of functions presented in the paper shows that ALNs are easily realized in APL2. User-defined operators are used as a very convenient tool for ALN programming. The paper discusses the application of implemented software to the problem of Burnout Heat Flux Prediction in nuclear reactors. It is shown that ALN technique allows the prediction of burnout heat flux with approximately three times better accuracy than other commonly used methods.
- AGI71.A.G.Ivakhnenko. Polynomial theory of complex systems. IEEE Transactions on Systems, Man and Cybernetics, SMC- 1 (4), October 1971.Google Scholar
- Alf90.M. Alfonseca. Neural networks in APL. A CM SIGAPL Quote Quad, 20(4), July 1990. Google ScholarDigital Library
- Bar71.R.L. Barron. Adaptive transformation networks for modelling, prediction and control. In Joint National Conference of Major Systems Proceedings, IEEE/ORSA, October 1971.Google Scholar
- BJ89.H.A. Broaclbent and J.Lucas. A neural networks model of serial learning. A CM SIGAPL Quote Qua& 19(4), August 1989. Google ScholarDigital Library
- Dor83.V.E. Doroshuk. Heat Transfer Burnout with Water Boiling in Ducts. Energoatomizdat, Moscow, 1983.Google Scholar
- Uhr91.R.E. Uhrig. Application of neural networks to the operation of nuclear power plants. In A Symposium on Nuclear Reactor Surveillance and Diagnostics Proceedings, May 1991.Google Scholar
Index Terms
- Adaptive learning networks in APL2
Recommendations
Adaptive learning networks in APL2
The paper considers Adaptive Learning Networks (ALN) as a tool to solve the problems of modeling, prediction, diagnostics and pattern recognition in complex systems. This method is similar to the neural network technique. The main difference is the self-...
Comments