Signal Path Oriented Approach for Generation of Dynamic Process Models
Peter Marenbach, Kurt Dirk Bettenhausen, Stephan Freyer · The MIT Press eBooks · 1996
The article at hand discusses a tool for automatic generation of structured models for complex dynamic processes by means of genetic programming. In contrast to other techniques which use genetic programming to find an appropriate arithmetic expression in order to describe the input-output behaviour of a process, this tool is based on a block oriented approach with a transparent description of signal paths. A short survey on other techniques for computer based system identification is given and the basic concept of SMOG (Structured MOdel Generator) is described. Furthermore latest extensions of the system are presented in detail, including automatically defined sub-models and qualitative fitness criteria. 1 Introduction Within the field of automatic control theory the term model stands for the description of a technical system or process which can be used as a starting point for tasks like diagnosis, simulation or control. Since a model is developed with respect to such a given task,...