Wastewater DO Concentration Control through NH4 Prediction Based on Evolutionary Radial Basis Function Neural Network

Evolutionary Neural network has been used in many industries control problems. This paper analyzes Dissolved Oxygen (DO) model and set-point control, then using Evolutionary Radial Basis Function (RBF) Neural Network to present a new idea and model for DO concentration control. The idea is to control DO set-point through ammonium concentration prediction based on Evolutionary RBF Neural Network. Compared to the idea of DO set-point control from on-line measurements of the ammonium concentration, new idea is better in response to actual situation. According to analyzing and Evolutionary RBF Neural Network theory, an Evolutionary RBF Neural Network is designed. Real wastewater plant data is used to the model simulation. Simulation shows that the idea and model is a good way to the DO concentration control.