The method of pattern recognition onset of nuclear boiling on based the bayes classifier

摘要

The principal idea of the work consists in that noise signals at the outlet of main nudear power plant technological parameter gauges (neutron flux, dynamic pressure etc.) contain important information on technical state of the equipment. As a result efficient algorithms of random process Identification that after respective spectral transformation are considered as multidimensional random vectors were developed. Automated classification of these vector in the developed algorithms in realized on the base of probability function, especially of Bayes classifier. Application of classifier is based on construction of multidimensional distribution of probabilities in feature space of corresponding dimension, with the help of which random vectors-realizations of corresponding images that are subjected to automated classification are described.