Abstract
Physical models of chemical processes are often difficult to derive. Hybrid fuzzy-first principles models can be a good alternative. These models consist of a framework of dynamic mass and energy balances, supplemented by fuzzy submodels descibing mass transformation and transfer rates in case a sound physical description is not possible. This paper presents an approach to constructing these models, which uses Kalman filtering for parameter estimation and a large scale optimisation algorithm for hybrid model optimisation. In addition, three classes of identification algorithms for fuzzy models are compared: fuzzy clustering, genetic algorithms and neuro-fuzzy mehtods. The comparison is illustrated for a penicillin fed batch reactor test case. Fuzzy clustering proved to be the most suitable technique, with genetic algorithms being a good alternative.
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
