STATIC AND DYNAMIC NEURAL-NETWORK MODELS FOR ESTIMATING BIOMASS CONCENTRATION DURING THERMOPHILIC, LACTIC-ACID BACTERIA BATCH CULTURES

Neural networks were used to elaborate static and dynamic models for t he on-line estimation of biomass concentration during batch cultures o f Streptococcus salivarius ssp. therrmophilus 404 and Lactobacillus de lbrueckii ssp. bulgaricus 398 conducted at controlled pH and temperatu re. Four static models with different structures and input variables w ere tested. The model relating the increase of lactic acid concentrati on and the working conditions (pH and temperature) to the increase of biomass was the most appropriate. Nevertheless, all the static models could furnish biased estimations when initial values of biomass were e rroneous or when lactic acid measurements were perturbed or noisy. To overcome these drawbacks, recurrent neural networks were used to model the dynamic behaviour of fermentations. These dynamic models, when ac ting as estimators, performed just as well as the static models but of fered more stable responses, due to an implicit corrective action aris ing from the training methodology and the associated method for biomas s estimation.