SHORT-TERM FORECAST OF OXYGEN CONCENTRATION IN NITRIFICATION CHAMBER USING ARTIFICIAL NEURAL NETWORK

Due to the difficulties in implementing other methods of removing organic compounds and nitrogen from wastewater, municipal wastewater treatment plants use classical processes (nitrification and denitrification) that require large energy expenditure on aeration. The problem of high energy consumption concerns every treatment plant using aerobic activated sludge, hence the constant attempts to introduce possibly intelligent aeration control techniques. In this study, a short-term (hourly) forecast of oxygen concentration in the aeration chamber was calculated under the conditions of changing values of wastewater flow and pollutant concentrations as well as active aeration control according to an unchanging algorithm. Artificial neural networks were used to calculate the forecast. It is shown that an accurate prediction can be obtained by using different sets of input data but depending on what data we choose, the neural network required to obtain a good result has a more or less complex structure. The resulting prediction can be applied as part of a system for detecting abnormal situations and for preventing excessive energy consumption through unnecessary over-oxygenation of activated sludge.