Influence of information noise on inference procedures of fuzzy expert systems for fermentation control and management

A possibility for enrichment of the methodology of expert system development based on a simulation of the probabilistic component of information vagueness is proposed. Using this concept, Gaussian noise with different sizes of dispersion was applied to the experimental values of the main physiological state variables in phenylalanine fermentation by genetically manipulated Echerichia coli. These variables were introduced at the input of the recognition block of the expert system, imitating noisy experimental data. It is shown that implementation of this approach can reveal some important characteristics of expert systems and can be useful for their improvement.This study was carried out within the framework of Bulgaria-UNDP Joint Project DP/BUL/007/86.The authors express their gratitude to Mr. Ricaredo Matanguihan for his assistance during the numerical examination of the fuzzy expert system for the control and management of phenylalanine fermentation.