Design of AI neural network based controller for controlling dissolved oxygen concentration in a sequencing batch reactor

Abstract

The design and development of the neural network based controller performance for the activated sludge process in sequencing batch reactor (SBR) is presented. In this paper, here we give a comparative study of various neural network based controllers such as the direct inverse control, internal model control and hybrid neural network control strategies to maintain the dissolved oxygen level of an activated sludge system by manipulating the air flow rate. The neural network inverse model based controller with the model-based scheme represents the controller, which relies solely upon the simple neural network inverse model. In the internal model control, both the forward and inverse model is used directly as elements within the feedback loop. The hybrid neural network control consists of a basic neural network (NN) controller in parallel with a proportional integral (PI) controller. Various simulation test involving multiple set point changes, disturbances rejection and noise effects were performed to review the performances of these various controllers. From the results it can be seen that hybrid controller gives best results in tracking set point changes value the disturbances and noise effects.