关键词:

软测量, 辅助变量选择, 加权, RBF神经网络, 菌体浓度, 发酵

Abstract:

Combined with the practical situation of Nosiheptide fermentation process, a weighted radial basis function neural network (WRBFNN) based biomass soft sensor modeling method is presentedBased on the unstructured model of Nosiheptide fermentation process, the secondary variables were selected according to the implicit function existence theorem, which made the selection theoretically strictAccording to the characteristics that biomass could vary in a wide range, the error function of the traditional RBFNN was improvedEach batch sample was selfadaptively weighted according to their predicting ability to the predicted object, and then WRBFNN was used to develop the biomass soft sensor modelThe testing results showed the effectiveness of the presented approach.

Key words:

软测量, 辅助变量选择, 加权, RBF神经网络, 菌体浓度, 发酵