A back propagation neural network model for accurately predicting the removal efficiency of ammonia nitrogen in wastewater treatment plants using different biological processes. (15th August 2022)

• Record Type: Journal Article
• Authors: Zhang, Shu-Zhe; Chen, Shuo; Jiang, Hong
• Is Part Of: Water research. Volume 222(2022)
• Publication Date: 2022-08-15
• Subjects: Back propagation artificial neural network -- Principal component analysis -- Treatment process -- Ammonia nitrogen -- Prediction; Water -- Pollution -- Research -- Periodicals; 363.7394
• DOI: 10.1016/j.watres.2022.118908
• Languages: English
• ISSNs: 0043-1354

Abstract

Highlights: A new back propagation artificial neural network model (BPANN) was developed. The BPANN is capable to predict the denitrification of wastewater treatment plants. Principal component analysis process can highly increase the model accuracy. The BPANN model can be effectively used for different biological treatment processes. Training ratios for different biological treatment processes are obtained. Abstract: Accurately predicting the water quality of treated water from a water treatment plant (WWTP) based on the obtained operating database is of great significance. However, it is difficult for common mechanistic models to work well. In this study, a back propagation artificial neural network (BPANN) model with high accuracy was developed to predict the denitrification efficiency based on a 1-year operating database. Standardized principal component analysis (PCA) methods were used to address the data, and the PCA processed data exhibited the best accuracy. In three WWTPs adopting the anaerobic/anoxic/oxic (A 2 O) process, the ammonia nitrogen removal efficiency of WWTPs was successfully predicted by using five variables: inlet flow rate, pH value, original ammonia nitrogen concentration, Chemical oxygen demand (COD) concentration, and total phosphorus concentration. Importantly, the obtained BPANN model can be effectively used for other widely used treatment processes, such as oxidation ditch (OD), sequencing batch reactor activated sludge process (SBR), membrane bioreactor (MBR), and cyclic activated sludge technology (CAST), by simply optimizing the training data ratios between 50/50 and 90/10. This is the first trial to set up a universal model for predicting the denitrification efficiency of WWTPs adopting common biological processes. The model could be used to choose the optimum treatment process in the new WWTP design or take action in advance to avoid the risk of excessive emissions when the already built WWTPs are subjected to sudden shocks. Graphical abstract: A back propagation artificial neural network (BPANN) model with high accuracy was developed to predict the denitrification efficiency, and the BPANN model can be used for different biological treatment processes by optimizing the training ratio. Image, graphical abstract