Self-organizing structured modelling of a biotechnological fed-batch fermentation by means of genetic programming

摘要: The article describes an approach for the self organizing generation of models complex and unknown processes by means genetic programming its application in a biotechnological fed batch production. described combines novel results computer science-genetic programming-with well known proven techniques control system theory-block diagrams Z transformation. synthesis these approaches is powerful tool data driven modelling that offers large number possibilities to integrate existing knowledge e.g. on submodels or expected elements. received use this provide transparent insight into structure process basis long term prediction behaviour therefore determination optimal setpoint profiles. That may overcome specific difficulties are bound adaptive learning-in sense neural networks-methods.