Author(s)

N Atanasova & B Kompare

Abstract

Simulation of wastewater treatment plants (WWTP) is a difficult task, due to the complex and mostly dynamic behaviour of the WWTP system. Regression trees are presented as a useful simulation/modelling tool for making predictions on WWTP operation given measured data at the input. A crucial step in the construction of such models is data preparation. Two data sets measured on two different WWTP are used in this paper. Both databases are composed of data that are usually measured on a WWTP and characterise the WWTP operation. The main difference between them is in data presentation. In the first data set (WWTP1) data are presented as a one-day situation of the plant operation, i.e. daily averaged values of the measured data (attributes) are given. Second data set (WWTP2) is composed of actual values of the attributes measured in one hour intervals. Regression tree models that predict outflow attributes according to inflow attributes are constructed for both data sets and compared in their performance. Assumption that data presentation and further preparation have a big influence on the results was confined. Program package WEKA, which includes most of popular machine learning algorithms, was used for constructing the models. 1 Introduction Wastewater treatment plants (WWTP) are dynamic and complex systems, which include numerous complex biological processes that are sometimes difficult to control and consequently to ensure a good quality outflow from the WWTP. Therefore, modelling is becoming a very helpful and commonly used tool for simulation and control of the WWTP operation. Usually, mathematical models are used for modelling of WWTP. These mathematical models are constructed from basic physical, chemical and biological principles. According to the fact that we are dealing with dynamic and complex process the equations in these

Keywords