Temperature precision control is one of the most critical issues in metrology laboratories, and this issue has become increasingly stringent in modern society. Radiant air conditioning system, which minimizes vibration through radiant heat transfer instead of conventional convection, has gained attention but is more sensitive to temperature fluctuations from the cooling source. Considering that phase change materials (PCMs) have the advantage of suppressing water temperature fluctuations, comparative simulations are carried out to analyze the suppressing effectiveness by adding two typical PCMs (paraffin and dimethyl sulfoxide) in water tanks and radiant panels separately. Results indicate that adding paraffin to water tanks has a better effect than dimethyl sulfoxide while it is inverse for radiant panels. Then, the adding volume ratios (paraffin for the water tank is 0.2; dimethyl sulfoxide for radiant panels is 0.1) are provided, when surface temperature fluctuations of radiant panels are suppressed within ±0.1 K. Finally, the relationship between the latent heat/thermal conductivity of PCM versus suppressing effect is investigated to provide a reference for the design of radiant air conditioning systems in metrology laboratories.

Fault detection and diagnosis are essential to the air conditioning system of the data center for elevating reliability and reducing energy consumption. This study proposed a convolutional neural network (CNN) based data-driven fault detection and diagnosis model considering temporal dependency for composite air conditioning system that is capable of cooling the high heat flux in data centers. The input of fault detection and diagnosis model was an unsteady dataset generated by the experimentally validated transient mathematical model. The dataset concerned three typical faults, including refrigerant leakage, evaporator fan breakdown, and condenser fouling. Then, the CNN model was trained to construct a map between the input and system operating conditions. Further, the performance of the CNN model was validated by comparing it with the support vector machine and the neural network. Finally, the score-weighted class mapping activation method was utilized to interpret model diagnosis mechanisms and to identify key input features in various operating modes. The results demonstrated in the pump-driven heat pipe mode, the accuracy of the CNN model was 99.14%, increasing by around 8.5% compared with the other two methods. In the vapor compression mode, the accuracy of the CNN model achieved 99.9% and declined the miss rate of refrigerant leakage by at least 61% comparatively. The score-weighted class mapping activation results indicated the ambient temperature and the actuator-related parameters, such as compressor frequency in vapor compression mode and condenser fan frequency in pump-driven heat pipe mode, were essential features in system fault detection and diagnosis.