Dissolved Oxygen Control in Activated Sludge Process Using a Neural Network-Based Adaptive PID Algorithm

The concentration of dissolved oxygen (DO) in the aeration tank(s) of an activated sludge system is one of the most important process control parameters. The DO concentration in the aeration tank(s) is maintained at a desired level by using a Proportional-Integral-Derivative (PID) controller. Since the traditional PID parameter adjustment is not adaptive, the unknown disturbances make it difficult to adjust the DO concentration rapidly and precisely to maintain at a desired level. A Radial Basis Function (RBF) neural network (NN)-based adaptive PID (RBFNNPID) algorithm is proposed and simulated in this paper for better control of DO in an activated sludge process-based wastewater treatment. The powerful learning and adaptive ability of the RBF neural network makes the adaptive adjustment of the PID parameters to be realized. Hence, when the wastewater quality and quantity fluctuate, adjustments to some parameters online can be made by RBFNNPID algorithm to improve the performance of the controller. The RBFNNPID algorithm is based on the gradient descent method. Simulation results comparing the performance of traditional PID and RBFNNPID in maintaining the DO concentration show that the RBFNNPID control algorithm can achieve better control performances. The RBFNNPID control algorithm has good tracking, anti-disturbance and strong robustness performances.