Predictive control of wastewater works by neural networks

The efficiency of wastewater treatment plants can be improved substantially by methods of Computational Intelligence (CI), especially Fuzzy-Control and Neuronal Networks, which are used for controlling and optimising of the purification process. Areas of application are the control of sludge water dosage, of phosphate elimination by optimal precipitant dosage as well as an optimal aeration in the nitrification zone. Municipal wastewater treatment plants with 60.000 and 12.600 inhabitant equivalents have been equipped with the controllers and they are in operation since more than 3 years. Results of operation of the plants are presented in comparison to previously used classical control: Performance increased significantly and the outflow values could be kept securely below the governmental requirements without increase of the energy consumption. Peak loads in the inflow were eliminated in the plant and did not increase outflow-concentrations. Results of operation from more than three years clearly show that the CI-controller is a cost-efficient Method for a sustainable rise of performance in municipal wastewater treatment plants.