Performance analysis and control of wastewater treatment plant using Adaptive Neuro-Fuzzy Inference System (ANFIS) and Multi-Linear Regression (MLR) techniques

Obasi Peter Okeke, Ismail I Aminu, Abdulazeez Rotimi, Bara'u Gafai Najashi, M.M Jibril, Awaisu Shafiu Ibrahim, Abba Bashir, Salim Idris Malami, Habibu M.A, Mohammed Mukhtar Magaji
2022 GSC Advanced Engineering and Technology  
In order to provide an effective tool for the simulation of wastewater treatment plant performance and control, a reliable model is essential. In the present study, two different artificial intelligence (AI) models; Adaptive Neuro-Fuzzy inference system (ANFIS), and a classical multi-linear regression analysis (MLR) were applied for predicting the performance of Abuja wastewater treatment plant (AWWTP), in terms of Conductivity, pH, Iron content, BOD, COD, TSS and TDS. The daily data were
more » ... ed from Abuja Wastewater treatment plant, for this purpose, single and ensemble models were employed to compare and improve the prediction performance of the plant. The obtained result of single models proved that, MLR model provides an effective analysis in comparison to the other single model. The result showed that, conductivity influences the performance and efficiency of the water treatment plant by an increased efficiency performance of AI modelling up to 99.6% testing phase and 6.8% Error value of same phase. This shows that MLR model was more robust and reliable method for predicting the Abuja WWTP performance.
doi:10.30574/gscaet.2022.4.2.0033 fatcat:zyptovmo5ncfjjfds3k2mwwniq