Self Learning Fuzzy Logic Control of Dissolved Oxygen Concentration in a Fermentation Process

摘要

Biotechnological processes are notoriously difficult to control using conventional methods owing to their time-variant and non-linear characteristics. An alternative control method is to utilise artificial intelligence such as fuzzy logic. A problem wiht the development of fuzzy logic ocntrollers is rule-base genertion. A Self-Learning Fuzzy Logic Control(SLFLC) methodology offers a ossible alternative solution. A study is presented illustrating the performance of a SLFLC by demonstrating its ability to generate a rule-set based on a predetermined criteria. The SLFLC described has been successfully applied to simulations of a Bakers Yeast fedbatch fermentation. Results demonstrate ho the learning mechanism produces a rule-set which controls the dissolved oxygen concentration throughout the fermentation process duration.