Application of a novel neural network for Identification of nonlinear Carbon/Carbon gaseous-state deposit process

摘要

A novel neural network model and algorithm for highly nonlinear C/C gaseous-state deposit process is presented, The network model consists of fuzzy classifier and some wavelet sub-networks which is called hybrid neural network. The input samples are trained by homologous wavelet network after classifying. The results of the identification of the C/C gaseous-state deposit process are desirable.