Enhance modelling predicting for removal efficacy of primary and biological treatment in wastewater treatment plants by using an adaptive neuro-fuzzy inference system.

An adaptive network-based fuzzy inference system (ANFIS) was used to develop models for the prediction of removal efficiency of biological oxygen demand (BOD), total nitrogen (TN), total phosphorus (TP), and total suspended solids(TSS) in a wastewater treatment plant. In a primary and biological wastewater treatment facility, ANFIS' hybrid learning algorithm was utilized to model the nonlinear interactions between influent pollutant variables and effluent variables. ANFIS is very beneficial for highly nonlinear processes, such as WWTP. By examining linear correlation matrices among input and output variables, input variables for BOD, TN, TP, and TSS models were hydraulic retention time(HRT), temperature(T), and dissolved oxygen(DO). The results show that the created system is capable of providing appropriate predicting and control outcomes. ANFIS was able to achieve minimum mean square errors of 0.1673, 0.0266, 0.0318, and 0.0523 for BOD, TN, TP, and TSS, respectively. BOD, TN, TP, and TSS all have very high correlation coefficients. The prediction performance of ANFIS in the wastewater treatment plant was satisfactory.