TY - JOUR
T1 - Identification of a fed-batch fermentation process
T2 - Comparison of computational and laboratory experiments
AU - Cabrera, A.
AU - Poznyak, A.
AU - Poznyak, T.
AU - Aranda, J.
PY - 2002/1
Y1 - 2002/1
N2 - To identify a Saccharomyces cerevisiae fed-batch fermentation process, it is suggested that a differential (dynamic in continuous time) neural network (DNN) be implemented. A priori information on the dynamic equations and their parameters is not required to realize this approach. Based on real data, obtained from laboratory experiments, this DNN of a simple structure (six neurons) is shown to have a high capability of identifying this process (to reproduce the input-output relation) after several working hours of learning.
AB - To identify a Saccharomyces cerevisiae fed-batch fermentation process, it is suggested that a differential (dynamic in continuous time) neural network (DNN) be implemented. A priori information on the dynamic equations and their parameters is not required to realize this approach. Based on real data, obtained from laboratory experiments, this DNN of a simple structure (six neurons) is shown to have a high capability of identifying this process (to reproduce the input-output relation) after several working hours of learning.
KW - Differential neural networks
KW - Fed-batch fermentation
KW - Identification
UR - http://www.scopus.com/inward/record.url?scp=0035708836&partnerID=8YFLogxK
U2 - 10.1007/s00449-001-0273-6
DO - 10.1007/s00449-001-0273-6
M3 - Artículo
SN - 1615-7591
VL - 24
SP - 319
EP - 327
JO - Bioprocess and Biosystems Engineering
JF - Bioprocess and Biosystems Engineering
IS - 5
ER -