Dynamic optimization of wastewater treatment process based on novel multi-objective ant lion optimization and deep learning algorithm

Abstract

In this paper, a novel dynamic optimization control based on multi-objective ant lion optimization (DMOALO) and deep learning algorithm is proposed, which could optimize energy consumption (EC) and effluent quality (EQ) simultaneously in the wastewater treatment processes. In order to overcome the difficulty that there is no clear function relationship between the dynamic parameters and the performance indicators, a novel deep belief network (DBN) model for predicting EC and EQ as objective function is proposed. Then, this objective function with constraints is solved by DMOALO method, and the optimal solution would be selected by the intelligent decision system. Finally, Proportional Integral (PI) controllers would be used to track and control these optimal dynamic parameters. DBN-DMOALO-PI optimization control strategy is evaluated in benchmark simulation model 1(BSM1), the simulation results demonstrated this novel optimization control strategy could reduce the EC significantly while meeting the standards of effluent quality parameters. EC is decreased by 3.31% compared with PI optimization control strategy. Therefore, this novel method may reduce the cost of wastewater treatment process effectively, and realize the carbon neutrality in wastewater treatment process.