Wyniki wyszukiwania - BazTech

Ograniczanie wyników

2 Civil and Environmental Engineering Reports

2 Płonka Lesław

Znaleziono wyników: 2

Liczba wyników na stronie

Wyniki wyszukiwania

Sortuj według:

Ogranicz wyniki do:

Short-Term Forecast of Oxygen Concentration in Nitrification Chamber Using Artificial Neural Network

Płonka Lesław

Civil and Environmental Engineering Reports

2022

Vol. 32, no. 4

428--439

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.

Artificial Neural Network as a Virtual Sensor of Nitrate Nitrogen (V) Concentration in an Activated Sludge Reactor

Płonka Lesław

Civil and Environmental Engineering Reports

2020

Vol. 30, no. 4

188--200

The paper discusses the use of an artificial neural network to control the operation of wastewater treatment plants with activated sludge. The task of the neural network in this case is to calculate (predict) the readings of the probe measuring the concentration of nitrate nitrogen (V) in one of the biological reactor tanks. Neural networks are known for their ability to universal approximation of virtually any relationship, including the function of many variables, but the process of "training" the network requires the presentation of many sets of input data and corresponding expected results. This is a difficulty in the case of wastewater treatment plants, because some key process parameters are usually not measured online (samples are taken and measurements are taken in the laboratory), and even if they are, the time intervals are large. Bearing in mind the aforementioned difficulty, this work uses a set of input data consisting only of information that can be measured with measuring probes. As a result of the conducted experiments a high compliance of the probe's prediction with the expected values was obtained. The paper also presents data preparation and the network "training" process.