Artificial Neural Network (ANN) Approach to Modelling of Selected Nitrogen Forms Removal from Oily Wastewater in Anaerobic and Aerobic GSBR Process Phases

Abstract

Paper presents artificial neural network models (ANN) approximating concentration of selected nitrogen forms in wastewater after sequence batch reactor operating with aerobic granular activated sludge (GSBR) in the anaerobic and aerobic phases. Aim of the study was to determine parameters conditioning effectiveness of selected nitrogen forms removal in GSBR reactor process phases. Models of artificial neural networks were developed separately for N-NH4, N-NO3 and total nitrogen concentration in particular process phases of GSBR reactor. In total, 6 ANN models were presented in this paper. ANN models were made as multilayer perceptron (MLP), which were learned using the Broyden-Fletcher-Goldfarb-Shanno algorithm. Developed ANN models indicated variables the most influencing of particular nitrogen forms in aerobic and anaerobic phase of GSBR reactor. Concentration of estimated nitrogen form at the beginning of anaerobic or aerobic phase, depending on ANN model, in all ANN models influenced approximated value. Obtained determination coefficients varied from 0.996 to 0.999 and were depending on estimated nitrogen form and GSBR process phase. Hence, developed ANN models can be used in further studies on modeling of nitrogen forms in anaerobic and aerobic phase of GSBR reactors.

Biosorption Capacity of Activated Sludge Sand Bed for Removal of Copper from Treated Wastewater

“…Dechlorination of the water was crucial to maintain the parameters of the effluent flowing into the bed. This avoided the conversion of model wastewater constituents from dissolved to suspended form [Ofman and Struk-Sokolowska, 2019]. This regularity was of particular importance in the case of Cu ions, as this approach ensured that the predominant process in the removal of Cu ions was that of sorption on the biological membrane formed on the filter bed.…”

Integrated sequential fuzzy logic search models for simulating wastewater treatment plants missing influent parameters

“…Ansari et al (2018) predicted influent flow rate in WWTPs using autoregressive integrated moving average (ARIMA), nonlinear autoregressive network (NAR) and SVM regression time series algorithms. Ofman and Struk‐Sokołowska (2019) used multilayer perceptron (MLP) to model the concentration of nitrogen forms after anaerobic and aerobic stages of a granular sequencing batch reactor (GSBR) reactor.…”

“…In Mojiri et al (2020) study, the performance of anammox–biochar in a synthetic wastewater treatment was optimized using ANN modelling. Ofman and Struk‐Sokołowska (2019) developed MLP‐ANN models for N‐NH 4 , N‐NO 3 and total nitrogen concentration in particular process phases of aerobic granular activated sludge reactor.…”

Distribution of Heavy Metal Fractions in Sewage Sludge from a Selected Municipal Sewage Treatment Plant

“…Clearly presented statistical data indicate that since 2004 an increasing amount of sludge has been used as a fertiliser for agricultural crops. However, it should be noted that sewage sludge contains heavy metals (Bauman-Kaszubska & Sikorski 2011), as well as other toxic compounds (Ofman & Skoczko 2018, Ofman & Struk-Sokołowska 2019, Struk-Sokołowska et al 2020. The amount of organic and inorganic pollutants in sewage sludge depends on the chemical characteristics of the wastewater flowing into the facility (WIOŚ 2018).…”