System Structure Identification by Neural Networks: Application to the Thermal-Hydraulic Correlations in a Steam Generator

摘要

Niowadays, using artificial neural entworks (ANNs) to perform interesting input/output mappings in various industrial contexts has become alomst routine. Indeed, the nonlinear features of this algorithm allow one to deal with real complex sytems such as those encountered in the nuclear field. Here an ANN algorithmis applied to determine the relationsips that exist between some process variables pertaining to the operation of the steam generator of a pressurized water ractor. The exemplars requried for the ANN training are obtained from a suitable nonlinear, mathematical model, numerically integrated, whose solution yields pseudo-experimental data that simulate dta that would be collected in a real experiment.