Abstract
In the context of water scarcity and tightening environmental requirements, improving the energy efficiency of biological wastewater treatment processes has become particularly important. The aeration tank is one of the most energy-intensive and dynamically complex components units, strongly affected by the variability in influent flow and composition. Conventional PID control, do not provide predictive disturbance compensation and often result in excessive aeration and increased energy consumption. The study proposes an intelligent control approach based on a digital twin, neural network-based influent flow forecasting, and model predictive control (MPC). The digital twin represents a dynamic model of the biological process incorporating key state variables, including substrate, activated sludge, and dissolved oxygen concentrations. A neural network model is used to predict the diurnal variability coefficient of influent flow based on long-term statistical observations. The predicted values are incorporated into the MPC algorithm as measured disturbances, enabling anticipatory aeration system. Simulation results show stabilisation of dissolved oxygen under variable inflow conditions and reduces energy consumption by preventing over-aeration. The proposed architecture is suitable for implementation within existing industrial PLC-SCADA systems in advisory MPC mode and improves energy efficiency, robustness, and environmental performance.