Soft-sensing method for wastewater treatment based on BP neural network

At present, wastewater treatment quality parameters cannot be detected on-line. In this paper, the soft-sensing method based on artificial neural networks is proposed in order to resolve this problem. The wastewater treatment technique is analyzed systematically. ORP, DO, PH and MLSS which can be detected on-line are taken as the secondary variables. BOD, COD, N and P which cannot be detected on-line are taken as the primary variables. The BP neural network for soft-sensing is proposed and trained using the testing data of the practical treatment process. The simulation results show that the soft-sensing system of wastewater treatment based on the BP neural network can correctly estimate the quality parameters in real time. Thus, the system can be accommodated to the changes of the environment and implement the real time control of wastewater treatment.