A SIMULATION OF THE PENICILLIN G PRODUCTION BIOPROCESS APPLYING NEURAL NETWORKS

Brazilian Journal of Chemical Engineering. 1997;14(4) DOI 10.1590/S0104-66321997000400004

 

Journal Homepage

Journal Title: Brazilian Journal of Chemical Engineering

ISSN: 0104-6632 (Print); 1678-4383 (Online)

Publisher: Brazilian Society of Chemical Engineering

LCC Subject Category: Technology: Chemical technology: Chemical engineering

Country of publisher: Brazil

Language of fulltext: English

Full-text formats available: PDF, HTML, XML

 

AUTHORS

A.J.G. da Cruz
C.O. Hokka
R.C. Giordano

EDITORIAL INFORMATION

Peer review

Editorial Board

Instructions for authors

Time From Submission to Publication: 12 weeks

 

Abstract | Full Text

The production of penicillin G by Penicillium chrysogenum IFO 8644 was simulated employing a feedforward neural network with three layers. The neural network training procedure used an algorithm combining two procedures: random search and backpropagation. The results of this approach were very promising, and it was observed that the neural network was able to accurately describe the nonlinear behavior of the process. Besides, the results showed that this technique can be successfully applied to control process algorithms due to its long processing time and its flexibility in the incorporation of new data