Aeration Control and Parameter Soft Estimation for a Wastewater Treatment Plant Using a Neurogenetic Design

Abstract

Biochemical oxygen demand and chemical oxygen demand are the most important parameters for wastewater management and planning, which represents the oxygen consumption from degradation of organic material. Insufficient levels of dissolved oxygen prevent the successful degradation of organic matter present, whereas too high levels cause a waste of energy and hence decreased efficiency. Therefore, the need for controlling dissolved oxygen through adequate aeration and sludge pumping operations is of great importance. This paper proposes the use of artificial neural networks applied both to the prediction of both oxygen demand parameters starting from secondary variable measurements and to the control of dissolved oxygen in aeration tanks for a nonlinear wastewater treatment model benchmark. Genetic algorithms are used for the automatically choice of the optimum control law based on the neural network model of the plant. The results show how this combined scheme can be effectively employed in aeration control.