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.

供暖、通风和空调（HVAC）系统的能耗在建筑能耗中占有重要地位，约占总能耗的65%。而且，随着楼宇自动化的进步，通风系统的能耗不断增长。本研究的重点是提高暖通空调系统中球形风口的性能。它主要利用神经网络和多岛遗传算法（MIGA）进行多参数优化。通过采用结构参数化、精确快速的计算流体力学（CFD）模拟、最小化样本空间以及合理的优化策略等方法，缩短了优化过程的时间周期。此外，本研究提出了一种新的描述球形风口性能的综合评价指标，可以更准确地评估不同结构的球形风口。结果表明，通过建立神经网络预测模型并与多岛遗传算法相结合，成功实现了新型球形风口设计。优化后的新型球形风口与传统球形风口相比，球形风口有效指数（STEI）降低了27.05%。此外，阻力降低了15.68%，射流长度增加了7.57%。实验结果表明，我们提出的优化方法具有较高的精度、良好的泛化能力，并且在不同雷诺数下具有良好的一致性。