Dynamic Process Modeling using Fuzzy Submodels
| Authors: | Betlem Ben, University of Twente, Netherlands
van Lith Pascal, University of Twente, Netherlands
Roffel Brian, University of Twente, Netherlands |
|---|
| Topic: | 3.2 Cognition and Control ( AI, Fuzzy, Neuro, Evolut.Comp.) |
|---|
| Session: | Intelligent Modelling and Identification II |
|---|
| Keywords: | dynamic modelling, fuzzy modelling, distributed-parameter systems, lumped-parameter systems, polymer reactor, pulp digester, batch distillation column |
|---|
Abstract
This article discusses a new modular design approach for hybrid models consisting of a dynamic framework augmented with static fuzzy sub-models. As the framework is physically based, the models have a dynamic behaviour that corresponds well with the original process. Their fit to process data assures good steady state behaviour and corrects the dynamic behaviour for assumptions and simplifications. The hybrid model design is illustrated for three dynamically different processes: an ideally mixed, a distributed and a chained process.
