A nonlinear adaptive control approach for an activated sludge process using neural networks

The activated sludge process is an important treatment method of civil wastewater. Controlling of the activated sludge process is one of the most important and challenging tasks because of its strong nonlinearities and large uncertain dynamics. In this paper we present a nonlinear adaptive control approach to solve the dissolved oxygen concentration control problem for an uncertain wastewater treatment process. In the controller design, all uncertain dynamics of the wastewater treatment are approximated by using radial basis function (RBF) neural networks (NNs). The proposed adaptive NN control can guarantee semi-global uniform boundedness of all the closed-loop system signals as rigorously proved by Lyapunov synthesis. The control strategy is applied for an activated sludge process with the pre-denitrification technique to remove the nutrient nitrogen from the wastewater. The simulation studies are presented to demonstrate the effectiveness of the proposed nonlinear adaptive control approach.