Building automation system uses several networks of sensors for continuous monitoring of building control systems for energy-efficient operation. Physical sensors are costly and need frequent calibration. The accurate measurement of supply air temperature from the air handling units (AHUs) has an important effect on the control of cooling coil, supply air temperature and supply airflow rate delivered to rooms. In the case when such a sensor gives erroneous measurements, a virtual sensor can replace temporarily the faulty sensor, and it can also be used for automated fault detection of HVAC systems. This article proposes two different gray-box (models A and B) for predicting the supply air temperature of air handling units that were developed and tested using the measurements from two buildings. The models require the measurement of three variables (mixed air temperature, cooling coil valve signal, and chilled water inlet temperature). The results of both models are discussed and compared. A sliding window approach for cross-validation of the models was also carried out. The developed gray-box models A and B could be integrated into BAS for virtual measurement, virtual calibration, and fault detection in HVAC systems.

楼宇自动化系统使用多个传感器网络来连续监控楼宇控制系统，以实现节能运行。物理传感器价格昂贵，需要经常校准。准确测量空气处理单元（AHU）的送风温度对控制冷却盘管，送风温度和送入房间的送风量具有重要影响。在这种传感器进行错误测量的情况下，虚拟传感器可以暂时替换故障传感器，也可以用于HVAC系统的自动故障检测。本文提出了两种不同的灰箱（模型A和B），用于预测使用两个建筑物的测量值开发和测试的空气处理单元的送风温度。这些模型需要测量三个变量（混合空气温度，冷却盘管阀信号和冷冻水入口温度）。讨论并比较了两个模型的结果。还执行了用于模型交叉验证的滑动窗口方法。可以将开发的灰盒模型A和B集成到BAS中，以在HVAC系统中进行虚拟测量，虚拟校准和故障检测。