【摘要】 以南方某机场航站楼冷源系统为研究对象，采用深度神经网络建立了两种不同类型冷水机组的运行能效模型，并将冷却水出水温度模型与冷水机组能效模型进行耦合，以冷源系统能耗最低为目标，采用布谷鸟搜索算法优化了冷源系统的运行参数、冷水机组与冷却塔的组合方式。研究结果表明：采用深度神经网络建立的冷水机组模型具有较高的精度和泛化能力，与原运行方式对比，采用布谷鸟搜索算法优化的方法在夏季典型日最高节能19.6%,具有较高的节能效果。更多还原

【Abstract】 Based on a cooling system for a terminal building in a southern airport, two types of chiller efficiency models were established using deep neural networks, and the model of cooling water outlet temperature was coupled with deep neural networks. With the aim of minimizing the energy consumption of the cooling system, the cuckoo search algorithm was adopted to optimize the operating parameters of the cooling system and the combination of chiller and cooling towers. The results show that the chiller model with deep neural networks has high accuracy and generalization ability. Compared with the original operation mode, the cuckoo search algorithm can achieve up to 19.6% energy saving on a typical day in summer, demonstrating a good energy-saving efficiency.更多还原