Application of Data Driven Technology in Wastewater Treatment Process

Aiming at the huge energy consumption of sewage treatment plants, a data-driven method for energy consumption prediction and optimization modeling of sewage treatment plant pumping stations is proposed. The adaptive neuro-fuzzy inference system (ANFIS) improved by the ant colony optimization algorithm (ACO) is used to model the relationship between the energy consumption of the pumping station and various influencing variables. The optimized ANFIS can accurately find the nonlinear relationship between the energy consumption of the pumping station and the internal variables. The genetic algorithm (GA) is used to optimize the established energy consumption model, and the energy consumption of the pump unit is minimized while the liquid level is stable. The verification results show that the ACO-ANFIS-GA algorithm proposed in this paper has a good application prospect in the field of energy management.