Notice: Undefined index: linkPowrot in C:\wwwroot\wwwroot\publikacje\publikacje.php on line 1275
[43700] Artykuł: Ocena wpływu zmiennych wejściowych oraz struktury modelu sztucznej sieci neuronowej na prognozowanie dopływu ścieków komunalnych do oczyszczalni(Impact Assessment of Input Variables and model structure on Forecasting Wastewater Inflow into sewage Treatment Plants)Czasopismo: Ochrona Środowiska Tom: 38, Zeszyt: 2, Strony: 29-36 ISSN: 1230-6169 Wydawca: POLISH SANITARY ENGINEERS ASSOC, UL MARSZ J PILSUDSKIEGO 74, WROCLAW, 2 SKR POCZT 980 50-900, POLAND Opublikowano: Czerwiec 2016 Autorzy / Redaktorzy / Twórcy Grupa MNiSW: Publikacja w czasopismach wymienionych w wykazie ministra MNiSzW (część A) Punkty MNiSW: 15 Klasyfikacja Web of Science: Article ![]() Słowa kluczowe: sieci neuronowe  modelowanie dopływu ścieków  regresja logistyczna  oczyszczalnia ścieków  Keywords: Sewage treatment plant  wastewater inflow  modeling  forecasting  ANN  correlation coefficient  |
Due to a stochastic nature of sewage inflow into a treatment plant the inflow amount and its quality are highly variable which has a significant impact on the plant technological objects operation. Hence, sewage inflow forecasting would be desirable as it allows for mitigating the impact of abnormal events that might lead to major plant installation disruption. This paper presents the results of a raw sewage inflow modeling using Artificial Neural Networks (ANNs). Results of the three-year measurements of precipitation rates and sewage treatment plant inflow in Rzeszow and Kielce were used in the analyses. To assess the impact of exogenous variables on the model quality the logistic regression method was applied. The variables considered were the precipitation rate and daily sewage inflow, which were appropriately delayed in relation to the forecasted inflow values. Impact of the model structure parameters on accuracy of the mathematical model forecasts was also investigated.