On-line estimation of biomass concentration using a neural network and information about metabolic state

Abstract

This paper deals with the design of a neural network-based biomass concentration estimation system. This system is enhanced by the incorporation of information about the actual metabolism of the microorganism cultivated, which is taken from an on-line knowledge-based system. Two different design approaches have been investigated using the fed-batch cultivation of baker's yeast as the model process. In the first, metabolic state (MS) data were passed as additional input to the neural network; in the second, these data were used to select a neural network suitable for the specific MS. Two neural network types--feed-forward (Levenberg-Marquardt) and cascade correlation--were applied to this system and tested, and the performances of these neural networks were compared.

Online nonlinear sequential Bayesian estimation of a biological wastewater treatment process

“…Table 1 presents descriptions of model parameters with the values used in this study. For biological wastewater treatment processes, some of the process states of interest are often not directly measurable [8,9] or their determination through analytical methods is not suited to online monitoring; in such cases they can be obtained through a recursive estimation algorithm using the measurable process variables. It is well known that the growth rate of biomass is slow compared to the variation of the substrate.…”

“…However, some state variables in wastewater treatment processes cannot be directly measured online (e.g. biomass and substrate concentration) due to a lack of reliable and inexpensive online measurement systems [8,9]. Hence, many studies have focused on developing a recursive online estimation algorithm to reconstruct the unmeasurable states from available measurements (e.g.…”

Control of continuous fed-batch fermentation process using neural network based model predictive controller

“…Since the control variables involved specific values, besides measuring CER and OUR, biomass concentration also needs to be measured. This can be achieved by sensors [33] and various estimation methods such as neural network based methods developed earlier [34][35][36]. Unlike ethanol concentration and RQ, Q c -Q o are unique for the state of the full utilization of the respiratory capacity of cells through pathway R1.…”

On-line estimation of biomass and intracellular protein for recombinant Escherichia coli cultivated in batch and fed-batch modes

“…Biomass is a critical parameter in the fermentation process, and it is difficult to be measured (Madrid and Felice, 2005;Vanek et al, 2004;Vicente et al, 1998;Wang et al, 1998). It is important because it is a key variable in the optimization of a specific process, or to reach a maximum efficiency to obtain a certain product, i.e., an antibiotic and recombinant protein.…”