AI-Enabled QFT-Based Adaptive Control of Artificial Wetlands for Sustainable Wastewater Treatment in Future Cities

In this research, dissolved oxygen (DO) and ammonium ion (AMI) are regulated to treat urban wastewater. Instead of the conventional wastewater treatment process (WTP), an artificial intelligence (AI) based horizontal subsurface-flow type of artificial wetland (HSAW) is used. The HSAW is a more sustainable and economic solution than the conventional WTP. However, the modeling and control of an HSAW are challenging tasks. A recurrent artificial neural network is used to derive a dynamic adaptive model of the HSAW under consideration. To regulate the water quality influencing variables, a multi-variable quantitative feedback theory-based adaptive controller is employed. The results reveal that the proposed controller regulates DO and AMI levels according to the desired criteria. Additionally, a comparative analysis is provided, showing that the proposed control scheme outperforms a number of other reported controllers.