A Soft-sensing Method Based on BP Neural Network for Improving Dissolved Oxygen Measurement

At present, there lack of fast and stable methods for detecting some key parameters in wastewater treatment such as dissolved oxygen (DO), chemical oxygen demand (COD) and biological oxygen demand (BOD). In this paper, a soft-sensing method based on artificial neural networks is proposed in order to resolve this problem. A BP neural network is proposed and trained using the testing data from a practical treatment process. The simulation results show that the soft-sensing system for DO concentration measurement based on the BP neural network can give an accurate estimate of DO concentration real-time. Thus, the system can be implemented for real-time control of wastewater treatment