What question did this study set out to answer?

To model the activated sludge process for predicting and optimizing effluent water quality parameters.

February 26, 2026Open Access

Modelling and optimisation of activated sludge process using artificial neural networks and genetic algorithms

SSSaurabh SahadevGovernment Medical College GMGopal MadhuCochin University of Science and Technology RTRoy ThomasCochin University of Science and Technology

Key Points

To model the activated sludge process for predicting and optimizing effluent water quality parameters.
Utilized multi-layer perceptron neural networks for modelling effluent parameters
Employed multi-objective genetic algorithm to optimize influent parameters
Evaluated model using correlation coefficient and mean square error
Conducted analysis using MATLAB R2019a
Achieved an overall correlation coefficient of 0.9207 for effluent predictions
Mean square error for predictions was 0.0091
Identified optimal influent pH between 6-8, SS between 68-380, BOD between 155-692, and O&G between 8-45

Abstract

Mathematical modelling of activated sludge process (ASP) is done using multi-layer perceptron neural networks (MLP-ANN) to predict effluent water quality parameters and multi objective genetic algorithm (MOGA) is employed to optimise influent water quality parameters so that the concentration of contaminants in the effluent stream is minimized. The study area selected was in a central district of southern state of India. The effluent parameters to be investigated are pH, suspended solids (SS) and biochemical oxygen demand (BOD) and the influent parameters to be optimised are pH, suspended solids (SS), biochemical oxygen demand (BOD) and oil and grease (OG₈₍₅} lies between 8-45 when the objective functions were minimised simultaneously.

AIに質問

Bookmark

View Full Paper