Skip to Main Content
The paper reviews the concept of fuzzy system interpretability and concludes that known interpretability constraints work mostly for the internal consistency of the system, thus are insufficient that we could really benefit from interpretability in practice. In particular, reliability of system rules is an often overlooked property. The latter is a phenomenon of external consistency and thus is largely a responsibility of the optimization algorithm that is used to finalize the system. The modeling algorithm that is suggested in current paper has special regard for model reliability. We then proceed with a methodology for extracting a process controller from the identified process model. Controller design is guided by a automatic linguistic inversion technique. The approach is successfully tested on a fed-batch fermentation benchmark.