The energy consumption of heating, ventilation, and air conditioning (HVAC) systems holds a significant position in building energy usage, accounting for about 65% of the total energy consumption. Moreover, with the advancement of building automation, the energy consumption of ventilation systems continues to grow. This study focuses on improving the performance of spherical tuyeres in HVAC systems. It primarily utilizes neural networks and multi-island genetic algorithms (MIGA) for multi-parameter optimization. By employing methods such as structural parameterization, accurate and fast computational fluid dynamics (CFD) simulations, a minimized sample space, and a rational optimization strategy, the time cycle of the optimization process is shortened. Additionally, a new comprehensive evaluation index is proposed in this research to describe the performance of spherical tuyeres, which can be used to more accurately assess spherical tuyeres with different structures. The results show that by establishing a neural network prediction model and combining it with the multi-island genetic algorithm, a novel spherical tuyere design was successfully achieved. The optimized novel spherical tuyeres achieved a 27.05% reduction in the spherical tuyeres effective index (STEI) compared to the traditional spherical tuyeres. Moreover, the resistance decreased by 15.68%, and the jet length increased by 7.57%. The experimental results demonstrate that our proposed optimization method exhibits high accuracy, good generalization capability, and excellent agreement at different Reynolds numbers.

Calculating the resistance of ventilation air-conditioning ducts under nonfully developed flow is a crucial problem that must be addressed. Based on the characteristics of the resistance in ventilation air-conditioning ducts, the truncation method—a computational method that is appropriate for nonfully developed flow boundary conditions—was proposed in this study. The resistance distributions in the upstream and downstream ducts from typical local components, including reducers, bends and tee ducts, were investigated. Using the resistance values of the local components under fully developed flow, the resistances that did not belong to nonfully developed flow were truncated and removed. Finally, the calculation steps of the proposed method were discussed, an engineering case study was presented, and the accuracy of the developed model was analyzed. The results showed that for the local components in the system (reducers, bends and tee ducts), their proportions of the total resistance exhibited similar trends under different width-to-height ratios. The resistance of these local components included upstream resistance, downstream resistance and their own resistance. The upstream resistance accounted for 2%-6% of the total resistance, whereas the downstream resistance of the reducers, bends and tee ducts accounted for 40%-60% of the total resistance. A functional relationship was established between the local resistance and cutoff distance of the reducers, bends and tee ducts. Hence, the truncation method can calculate the local resistance from the cutoff distance. Moreover, in the presented engineering case study, the error between the actual measured resistance values and those simulated with the truncation method was only 4.28%, which was far less than that of the results simulated with the traditional calculation methods (53.64%).

To achieve sufficient air conditioning of large buildings, reasonable air distribution in indoor spaces is an effective method for creating stratified air conditioning. Therefore, optimizing the air distribution in large buildings is extremely significant. In this paper, we expound on a new method for air distribution design and optimization based on target value evaluation and summarize the relevant design processes based on an orthogonal test and by decoupling the effects of the size of the tuyère, airflow temperature, air-supply angle and velocity on air distribution. Then, we present a design case. To optimize the distribution of a lateral air supply in winter, the deflection angle, velocity and temperature of the air supply can be determined in turn. For the large and tall building types addressed in this paper, the optimal air-supply angle is 2°, the optimal air-supply velocity is 8 m/s, and the optimal air-supply temperature is 19 °C.

The coupling effect of local components is common in buildings and results in energy loss and local drag. This effect is significantly influenced by the shape and size of the components. However, only a few studies have focused on this topic. The numerical simulation method of Reynolds stress model (RSM) is adopted in the present study to investigate the typically coupled local components of ventilation and air conditioning ducts, namely, the coupled bend. By focusing on the core speed and segmented drag in the coupled bend, this study explores the effects of aspect ratio and curvature radius on drag and core speed. This study provides a theoretical basis for the design, construction, and operation management of local components of ventilation and air conditioning ducts. Two evident core-speed reduction processes are observed in the coupled bend and its downstream. With increasing curvature radius (R/D), the drop in core speed downstream decreases gradually in the S-shaped and U-shaped bends.