Abstract: Operation of a sewage treatment plant is a complex task because it requires maintaining the parameters of its activities at the appropriate level in order to achieve the desired effect of reducing pollution and reduce the flow of sediment discharged from the biological reactor. The basis for predicting the amount of excess sludge and operational parameters WWTP can provide physical models describing the biochemical changes occurring in the reactor, in which the input parameters, ie. Indicators of effluent quality and quantity of wastewater are modeled in advance.
However, due to numerous interactions and uncertainty of the data in the physical models and forecast errors parameters of the inlet to the treatment plant Simulation results may be affected by significant errors. Therefore, to minimize the prediction error parameters of operation of the technological objects deliberate use of a black box model. In these models at the stage of learning is generated model structure underlying the projections analyzed the operating parameters of the plant.
This publication presents the possibility of the use of methods: support vector, k - nearest neighbour and trees reinforced to predict the amount of the resulting excess sludge during wastewater treatment in the WWTP located in Sitkowka - News with a capacity of 72,000 m(3)/d with a load of 275,000 PE. Due to the fact that did not have the quality parameters of wastewater at the inlet to the activated sludge chambers it was not possible to verify the empirical relationships commonly used in engineering practice to determine the size of the daily flow of excess sludge. Due to the significant differences in the amount of excess sludge generated in the period (t = 1 (sic) 7 days) the simulation of the amount of sludge into the time were performed. To assessment the compatibility of measurement results and simulations quantities of sludge the mean absolute error and relative error of prediction for the considered parameter of technology was used.
The analyzes carried out revealed that the amount of generated excess sludge can be predicted on the basis of parameters describing the quantity and quality of influent waste water (slurry concentration of total nitrogen and total phosphorus, BOD5) and the operating parameters of the biological reactor (recirculation rate, concentration and temperature of the sludge, the dosed amount of methanol and PIX). On the basis of computations, it can be concluded that the most accurate forecasting results amounts of sediment were obtained by using a reinforced trees (t = 2 to 5 days) and Support Vector Machines methods (t = 1, 6, 7 days). While the highest values of forecast errors sediments was obtained using a k - nearest neighbor (t = 2 to 5 days) and reinforced trees (t = 1, 6, 7 days).
B I B L I O G R A F I ASpis literatury
1. ATV – DVWK – A 131 P (2001). Wymiarowanie oczyszczalni ścieków z osadem czynnym. Warszawa: Wydawnictwo Seidel – Przywecki..
2. Bień, J., Neczaj, E., Worwąg, M, Grosser, A., Nowak, D., Milczarek, M., Janik, M. (2001). Kierunki zagospodarowania osadów w Polsce po roku 2013. Inżynieria i Ochrona Środowiska, Vol. 14, nr 4, 375-384.
3. Dellana, S., West, D. (2009). Predictive modeling for wastewater applica-tions: Linear and nonlinear approaches. Environmental Modelling and Software, Vol. 24, 96-106.
4. Friedman, J. (2002). Stochastic gradient boosting. Computational Statis-tics and Data Analysis, Vol. 38, No. 4, 367–378.
5. Friedman, J. (2001). Greedy function approximation: A gradient boosting machine. The Annals of Statistics, Vol. 29, No. 5,. 1189–1232.
6. Gawdzik, J., Długosz, J., Urbaniak, M. (2015). General Characteristics of The Quantity And Quality of Sewage Sludge From Selected Wastewater Treatment Plants in The Świętokrzyskie Province. Environment Protection Engineering, Vol. 41, No.2, pp. 107-117.
7. Heidrich, Z., Witkowski, A. (2005). Urządzenia do oczyszczania ścieków – projektowanie, przykłady obliczeń. Warszawa: Seidel – Przywecki.
8. Henze, M., Gujer, W., Mino, T., Loosdrecht, M. (2000). Activated Sludge Models. London: IWA Publishing.
9. Kalinowska-Przybyś, E. (2002). Uwaga na stopień recyrkulacji. Forum Eksploratora Nr 3(8) str.8-9.
10. Kiczko, A., Romanowicz, R., Osuch, M., Karamuz, E.(2013). Maximising the usefulness of flood risk assessment for the River Vistula in Warsaw. Natural Hazards and Earth System Sciences, Vol.13, .3443-3455.
11. Licznar, P., Szeląg, B., (2014): Analiza zmienności czasowej opadów atmosferycznych w Warszawie. Ochrona Środowiska Nr 3, 23-28.
12. Martin, C., Shaw, A.R., Phillips, H.M., Gilley, A. and Ayesa, E. (2010). Comparison of methods for dealing with uncertainty in wastewater modelling and design. In: Proc. WWTmod2010. Mont-Sainte-Anne, Québec, Canada, pp. 63-169.
13. Piotrowski, A., Napiorkowski, J., Rowiński, P. (2006). Flash-flood fore-casting by means of neural networks and nearest neighbour approach – a comparative study. Nonlinear Processes Geophysics, Vol. 13, 443–448.
14. Raha, D. (2007). Exploring Artificial Neural Networks (ANN) Modelling for a Biological Nutrient Removal (BNR) sewage treatment Plant (STP) to Forecast Effluent Suspended Solids. Indian Chemical Engineering, Vol. 49, No. 3,. 205 – 220.
15. Rydzyński, R. (2012). Dobre praktyki związane z gospodarką osadami ściekowymi. PURE. European Regional Development Fund and European Neighbourhood and Partnership Instrument.
16. Serón, N., Puig, S., Meijer, S., Balaguer, M., Colprim, J. (2011). Sludge production based on organic matter and nitrogen removal performances. Water Practice and Technology, Vol. 6, No. 2.
17. Studzinski, J., Bartkiewicz, L., Stachura, M. (2013). Development of math-ematical models for forecasting hydraulic loads of water and wastewater networks. EnviroInfo 2013: Environmental Informatics and Renewable En-ergies Copyright 2013 Shaker Verlag.
18. Tao, X., Chengwen, W. (2013). Estimating and modelling the sludge ex-cess discharge in wastewater treatment plants in China. Environmental Engineering and Management Journal, Vol.12, No. 7, 1509-1514
19. Vapnik, V. (1998). Statistical Learning Theory. John Wiley and Sons. New York, 1998.
20. Wei, X., Kusiak, A. (2015). Short-term prediction of influent flow in wastewater treatment plant. Stochastic Environmental Research and Risk Assessment. Vol. 29, No. 1, 241 – 249. 
Web of Science