Recurrent neural network model of a fed-batch Saccharomyces cerevisiae fermentation process

Barrera-Cortés, Josefina; Baruch, Ieroham S.

doi:10.1109/ijcnn.2000.860835

Cited by 3 publications

(1 citation statement)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…as the input variables while building up the time-delay ANN. Barrera-Cortes and Baruch [7] input yeast biomass, substrate concentration, ethanol concentration and fermentation volume to the 4-8-4 recurrent neural network, the network showing a good convergence with an acceptable final mean-square error of 1.5%-2.2%. However, by now most of the work on ANNs for the yeast fermentation has concerned with the laboratory-scale.…”

Section: Introductionmentioning

confidence: 96%

Artificial Neural Network Based Software Sensor for Yeast Biomass Concentration during Industrial Production

2006

2006 International Conference on Computational Intelligence and Security

View full text Add to dashboard Cite

The artificial neural network is a potential 'sensor' in the complex bioprocess. The recurrent neural network (RNN) was employed as the software sensor to measure the biomass concentration during the baker's yeast industrial production, owing to its good ability in dealing with non-linear and time-varying process. Based on the data sets provided by the plant, input variables were selected as air flow rate (G), ethanol concentration (Eth), volume of the contents in the reactor (Vol), temperature (T), pH and their time-delay values as well as the predicted values ofyeast biomass concentration at delayed time. The topology of the RNN was optimized to be 11-16-1. The RNN showed good generalization abilityfor the testing samples. The robustness of the RAN was evaluated by adding deliberately inflicted noises to the G and Eth. The RNN showed higher robustness to the noise from Eth than thatfrom G.

show abstract

Section: Introductionmentioning

confidence: 96%