Multi model Fusion Modeling Algorithms for Fermentation Process

A new algorithm,which is based on multi model fusion technique to construct the model of fermentation process,is proposed.The algorithm can simultaneously use on line and off line parameters to construct models.Firstly,multi model fusion modeling algorithms are designed,the modeling method of two sub models based on adaptive fuzzy neural networks and fuzzy inference are described.Secondly,for three nonlinear testing functions,GMDH PTSV,Fourier neural network and multi model fusion modeling algorithms,are used to construct models respectively.Finally,results of the multi model fusion modeling algorithms for penicillin fermentation process are given.