Simulation of T-S Fuzzy Neural Network to UASB Reactor Shocked by Toxic Loading

Abstract

The neural network was conducted based on the Takagi-Sugeno fuzzy systems. Predictions of the biogas production rate, volatile fatty acid and CH4 for the UASB reactor were made using fuzzy neural network based on database collected from the anaerobic system shocked by the Chloroform and 2, 4-dinitrophenol loading. The correlation coefficients of observed and simulated values were above 0.940 for the training set, and above 0.860 for testing set. The results showed that fuzzy neural network can perfectly predict the performance of UASB shocked by the toxic loading, and has greatly adaptability to the variations of the anaerobic treatment system .