Adaptive critic control for wastewater treatment systems based on multi-objective particle swarm optimization

Considering the quality preservation and consumption reduction in wastewater treatment systems, the operation process is regarded as a multi-objective optimization control problem. An adaptive critic control scheme is developed based on multi-objective particle swarm optimization. First, the data information of inlet and outlet components is analyzed with the data-driven framework. The model of the optimization target is constructed, which reflects the effluent quality and energy consumption. Then, the MOPSO algorithm is used to solve the multi-objective optimization problem. A decision method is designed to select the preferred solution, which can be defined as the optimal set concentration of the dissolved oxygen and the nitrate nitrogen. Next, in order to realize the bottom tracking control of the optimal set-point, an adaptive dynamic programming based auxiliary controller is used to replenish the strategy of the proportional-integral-differential algorithm. Finally, the established algorithm is verified on the simulation platform of the wastewater treatment. The results show that the proposed algorithm can effectively improve the operational performance of the wastewater treatment process.