Performance optimization of the air-cooling system in a coal-fired power unit based on intelligent algorithms

Abstract

Air-cooled condensing technology is considered a preferred technology for thermal power generation due to the advantages of water savings. The performance of air-cooled condenser (ACC) is mainly influenced by external weather conditions and unit operation. In this paper, an artificial intelligence algorithm model is developed to predict and optimize the performance of the air-cooled condenser in advance based on long-term operational data of coal-fired power plants. A back propagation neural network algorithm is used to establish a net power output-back pressure model, and the optimal back pressure search is completed based on the established model. Finally, the average power savings of a single sample over a 30-second period was used as an indicator to evaluate the energy saving effect of optimized back pressure. The artificial intelligence analysis method not only enables the use of a large amount of operational data, but also allows effective prediction, analysis, and optimization of the performance of the air-cooled condenser, ultimately improving the overall performance of this equipment. The results indicate that: (1) when the back pressure of the unit reaches 9.25 kPa, the net power output of the unit is the highest, thus achieving the optimal back pressure; (2) by calculating the average energy savings, it can be concluded that, for a single sample over a 30-second period, the average power savings of the unit are above 7.0 kWh during the medium load period, and 5.0 kWh during the low and high load periods. Therefore, the proposed optimization method is beneficial for energy saving of the air-cooled condenser.