Soft sensor of biomass in nosiheptide fermentation process based on secondary variable weighted modeling method

Abstract

Biomass is hard to be measured on line in Nosiheptide fermentation process, which brings difficulties to control and optimization of this process. To solve this problem, soft sensor technique is applied to implement the on-line estimation of biomass, and a secondary variable weighted modeling method is proposed. Based on the unstructured model for Nosiheptide fermentation process, the secondary variables are selected according to the implicit function existence theorem. Then, each secondary variable is self-adaptively weighted according to its different effect on biomass, and a soft sensor model of biomass is developed by using the secondary variable weighted modeling method. The testing results show the effectiveness of the proposed method. © 2012 Springer-Verlag Berlin Heidelberg.