Creating a comfortable and healthy indoor environment is very important for indoor occupants. It is difficult to obtain complete information about the indoor airflow field from experimental measurements only, but traditional computational fluid dynamics methods require a lot of time and complex boundary conditions. With the advent of data-driven methods, the cost of the reconstruction of indoor airflow fields has been greatly reduced. Therefore, a two-dimensional airflow field with only a limited amount of experimental measurement data is reconstructed using a physics-informed neural network (PINN), and the constructed PINN model increases the physical interpretability of the neural network through the Navier–Stokes equations. Subsequently, the influence of the number and spatial location of the experimental measurement points on the accuracy of the PINN model for the reconstruction of the indoor airflow field is discussed, and the influence of different spatial locations of the measurement points on the PINN model for the reconstruction of the indoor airflow field is analyzed in more detail by orthogonal experiments with non-global information and orthogonal experiments with global information. The results show that the indoor airflow field can be reconstructed accurately by using only a limited amount of measurement points to participate in the training of the PINN model, and the measurement points that can reflect the vortex information in the airflow field are more favorable for the reconstruction of the airflow field. Moreover, only orthogonal experiments with global information can effectively infer the optimal spatial location for sampling measurement points in the airflow field.

This study aims to investigate the operation performance of a new terminal form of radiant air-conditioning system called the air carrying energy radiant air-conditioning system (ACERS). Three summer operation conditions, namely steady condition (without opening door and window), open-door condition and open-window condition, are researched in a residential apartment using experimental, computational fluid dynamics (CFD) simulation and thermodynamic methods. The concept of dynamic synergistic operation of mechanical ventilation driven by the air-conditioning system and natural ventilation driven by the open door or window is proposed. A thermodynamic model formulated by the dynamic enthalpy equation, dynamic temperature equation and dynamic moisture equation is developed to analyze the heat and mass transfer process of the test room under the synergistic operation of mixing ventilation. Moreover, the CFD simulation results are used to analyze the synergistic operation and thermodynamic energy transfer of the test room under the mixing ventilation of ACERS and open door/window. It is indicated that ACERS is an important technology with a low temperature gradient of less than 0.1 °C between the head (1.5 m) and ankle level (0.1 m) and low velocity of approximately 0.1 m/s in the occupied zone under the steady condition. The thickness of the boundary zone under the orifice plate of ACERS under the steady, open-door and open-window conditions is 12, 6, and 8 cm, respectively, which can effectively prevent condensation. This study proves that ACERS is a promising technology for air conditioning in residential buildings in regions with hot and humid summers.

Due to the data deficiency in developing countries like China, the calculation of the building production phase only considers a few major materials. To solve this problem, three indexes are put forward, which are cost-based energy, cost-based exergy and cost-based carbon, and a new concept, the equivalent coefficient of thermodynamic cost, is presented based on social economic indicator, energy intensity. Then a thermodynamic method is built up to estimate the energy, exergy consumption and CO₂ emission of building materials in production phase. Compared to the conventional calculation, this thermodynamic method takes full account of every material in the BOQ (bill of quantity), and the data used in the method, energy intensity, can be found in government publications. The production phase of the case building is analyzed using this method, and results show that the production phase accounts for 12.34% of the life cycle energy consumption, also contributes 15.48% towards the life cycle CO₂ emissions. The embodied energy of the case building is about 4.995 GJ/m² which matches the results from other LCA research, thus verifies the validity of the proposed calculation. This method is practical and significant in improving sustainable building assessment tools and enacting energy policies in building sector.