HYBRID FUZZY NEURAL-NETWORK FOR DIAGNOSIS - APPLICATION TO THE ANAEROBIC TREATMENT OF WINE DISTILLERY WASTE-WATER IN A FLUIDIZED-BED REACTOR

In this paper, we present a hybrid approach that uses both fuzzy logic and artificial neural networks for online detection and analysis of p roblems occurring in a 120 liter anaerobic digestion fluidized bed rea ctor for the treatment of wine distillery wastewater. The raw data ava ilable on the process (i.e., pH, temperature, recirculation flow rate, input flow rate and gas flow rate) are preprocessed using fuzzy logic to build a vector of features (i.e., a pattern vector). This feature vector is classified into a prespecified category (i.e., a class) whic h is a state of the system, according to discrimination fuzzy rules. A n artificial neural network is then used to classify the process state s and to identify the faulty or dangerous ones. This approach was deve loped to handle in real time problems such as, for example, foam formi ng, sudden changes in the effluent to be treated (due to a change in c oncentration), pipe clogging (due to struvite formation) or bed temper ature regulation (due to improper setting of the control parameters). (C) 1997 IAWQ. Published by Elsevier Science Ltd.