Approaches to the modelling of biochemical processes

The paper reports on the development of numerical models for the OTC (oxytetracycline) fermentation process. It also introduces the concept of neural networks and illustrates how these systems can be used to `learn´ the inter-relationships of a fermentation process. The OTC process is outlined and its control problems are highlighted. The development of an AR model for the OTC process is reported. The neural networks and results of a simple network used to model the relationships of some of the variables involved in the OTC process are presented