Evaluation of Nitrate Removal Effect in Groundwater Using Artificial Neural Networks

摘要

Groundwater contamination by nitrate is a globally growing problem. Biological denitrification is a simple and cost effective method. However, this process is non-linear, complex and multivariable. In order to solve this problem, activated sludge process was introduced to remove nitrate in groundwater with the aid of artificial neural networks (ANN) to evaluate the nitrate removal effect. The parameters such as COD NO3-N NO2-N MLSS DO etc. were used for input nodes and the COD NO3-N NO2-N were selected for output nodes. Experimental ANN training results showed that the ANN was able to predict the output water quality parameters very well. Most of relative error of NO3-N and COD were in the range of ±10% and ±5% respectively. The ANN model of nitrate removal in ground water prediction results produced good agreement with the experimental data.