Knowledge acquisition and knowledge based control in bioprocess engineering

Knowledge acquisition is still a major bottle-neck with respect to efficien t computer control design of knowledge based systems in bioprocess engineer ing. In this paper an approach towards the automatic generation of fuzzy ru les is presented and applied to data of an industrial antibiotic fermentati on. Fuzzy rules generated describe the relationship between the kinetics of the preculture and the antibiotic yield of the main culture. The terms use d in these rules were derived by clustering employing the fuzzy-C-means met hod. In order to rate and select rules and finally to optimize parameters o f membership functions of fuzzy variables different criteria are discussed in relation to the aim of the knowledge based control. Results are presente d with respect to process monitoring. Genetic algorithms proved suitable fo r optimization procedures due to the existence of multiple local optima. (C ) 1998 Elsevier Science B.V. All rights reserved.