This work presents an application of a recursive estimator of states and pa
rameters in a fed-batch penicillin production process based on the use of t
he extended Kalman filter. The estimated state variables were the cell, sub
strate, product and dissolved oxygen concentrations, the fermenter Volume a
nd the oxygen transfer coefficient. A simplified model of this process was
used for the filter, and the actual Values for product amount and concentra
tion of dissolved oxygen with independent random Gaussian white noise were
obtained using a deterministic and nonstructured mathematical model. The in
fluence of the filter parameters, initial deviations and presence of noise
on the observed variables was analyzed. In addition, estimator performance
was verified when the parameters and the structure of the process model wer
e changed. The extended Kalman filter implemented was found to be suitable
to predict the states of the system and the model parameters. Therefore, it
can be used for optimization and control purposes in a fermentative proces
s which requires some state variables that are measured with a long delay t
ime or unmeasured parameters.