The cooling performance of an indirect aircooled system heavily depends on the environmental wind speed and temperature. Manual adjustment of shutters by operators significantly impacts the safety, stability, and cost-effectiveness of unit operations. In this paper, a large number of sensors are used to monitor environmental information, and the BP neural network algorithm improved by quantum genetic algorithm is introduced based on the ICS platform to predict the circulating water temperature at the outlet of the cooling tower. According to the historical data and environmental variables, the optimal values of the outlet water temperature is accurately predicted, which as the main parameter to adjust PID for the shutter opening adjustment, so as to automatically control the lowest stable value of the outlet water temperature and obtain the optimal back pressure value. The operation data of the case unit shows that the system can automatically control the parameters of the cooling tower to the optimal level, reduce the labor intensity of the operators, reduce the energy consumption of the unit, and improve the economy and operation stability of the unit.