A fuzzy neural network model for the estimation of the feeding rate to an anaerobic waste water treatment process
Jae-Soo Kim, R. Kozma, Nikola Kirilov Kasabov, B Gols, M. Geerink, Taco Cohen · Otago University Research Archive (University of Otago) · 1998
: Biological processes are among the most challenging to predict and control. It has been recognised that the development of an intelligent system for the recognition, prediction and control of process states in a complex, nonlinear biological process control is difficult. Such unpredictable system behaviour requires an advanced, intelligent control system which learns from observations of the process dynamics and takes appropriate control action to avoid collapse of the biological culture. In the present study, a hybrid system called fuzzy neural network is considered, where the role of the fuzzy neural network is to estimate the correct feed demand as a function of the process responses. The feed material is an organic and/or inorganic mixture of chemical compounds for the bacteria to grow on. Small amounts of the feed sources must be added and the response of the bacteria must be measured. This is no easy task because the process sensors used are non-specific and their response woul...