Deep learning based dynamic COD prediction model for urban sewage
Due to the comprehensive sources of urban sewage, the contents of pollutants in urban sewage are quite complex and fluctuate frequently. Unstable status for both sewage inflow and COD makes it difficult to precisely control the process parameters in wastewater treatment plants (WWTPs). To reach the effluent quality standard, the WWTPs increase the aeration rate and chemical inputs, resulting in the great waste of resources and energy, rising production costs, and secondary pollution. Reputed for decreasing unnecessary energy and chemical input, a dynamic COD prediction model of urban sewage based on the hybrid CNN-LSTM deep learning algorithm is proposed to support the further development of the feed-forward control system. The prediction results reveal that the hybrid CNN-LSTM prediction model has higher accuracy and better prediction performance than the stand-alone CNN or LSTM model. The error analysis indicates that the prediction performance can satisfy industrial requirement and can be adopted in urban WWTPs.