Optimization of the circulating cooling water mass flow in indirect dry cooling system of thermal power unit using artificial neural network based on genetic algorithm

Abstract

The power consumption of circulating pumps can be effectively reduced by optimizing the circulating cooling water mass flow rate in indirect dry cooling system of a thermal power unit. The coupling algorithm of the artificial neural network optimized by genetic algorithm and the heat transfer model of the condenser and the air-cooled heat exchanger was established to obtain the air mass flow rate into the natural draft dry cooling tower (NDDCT). Assuming that the steam turbine back pressure is constant, the optimal mass flow rate of the circulating cooling water corresponding to the ambient temperature and the ambient temperature range in which the mass flow rate can be adjusted were obtained when the output power load was constant by using the heat transfer model of the condenser and the air-cooled heat exchanger. Calculation results show that the optimal mass flow rate of the circulating cooling water corresponding to ambient temperature gradually increased with the increase in the output power load and the decrease in the minimum inlet temperature of circulating cooling water in the NDDCT. Moreover, the ambient temperature range in which the mass flow rate of the circulating cooling water can be adjusted gradually decreased. Meanwhile, the ambient temperature range gradually decreased with the increase in the minimum outlet temperature of the circulating cooling water in the NDDCT, but the optimal mass flow rate corresponding to the ambient temperature remained unchanged. Taking the operating state of the unit on a certain day as an example, at least 16,515 kWh circulating pump power consumption can be saved by adjusting the circulating cooling water mass flow rate to the optimum value.