Publikacje

Abstract:

Forecasting the amount and quality of wastewater flowing into a treatment plant sufficiently in advance, enables effective control of numerous treatment process parameters. Therefore, mathematical (physical deterministic and time series statistical) models forecasting both the amount and quality of wastewater inflow into a sewage treatment plant are under development. In this paper, a possibility of simpler time series models application to forecasting values of selected indicators (biochemical oxygen demand (BOD5), total suspended solids (TSS), total nitrogen (TN), total phosphorus (TP) and ammonium (NH4+)) of sewage quality in the inflow into a treatment plant was investigated. The research was based solely on sewage flow rate data and - for the purpose of comparison - the actual measured indicator values. For this purpose, MARS type blackbox and random forest (RF) methods were used. Also, a possibility of combining the RF method with a classification model (RF+SOM) was investigated. Boosted trees (BT) and principal component analysis (PCA) methods were applied for identification of data that determine variability of the selected sewage quality indicators. The models were developed on the basis of continuous daily measurements performed in the period of 2013-2015 in the municipal sewage treatment plant in Rzeszow.

POWRÓT

Strona główna > Publikacje

Zastosowanie metod czarnej skrzynki do prognozowania wartości wybranych wskaźników jakości ścieków dopływających do oczyszczalni komunalnej