Computational fluid dynamics (CFD) is a powerful but time-consuming simulation tool for building indoor environment analysis. Artificial intelligence (AI)-based surrogate models, especially artificial neural networks (ANN)-based models which are the dominated ones, have demonstrated a great potential in accelerating CFD simulations. However, the published AI-based models are not good at capturing local spatial features in indoor airflow distribution, leading to poor local simulation accuracy. To overcome this challenge, this study proposes a convolutional neural networks (CNN)-based surrogate model for fast CFD simulations of indoor airflow distribution. Compared with other published AI-based models, this model can capture local spatial features in indoor airflow distribution datasets simulated by CFD, leading to higher accuracy. To enable this model to process room geometry information, a geometry representation strategy is proposed to convert room geometry information into inputs suitable for CNN models. Simulation data of 2000 indoor airflow velocity fields with various boundary conditions are generated using COMSOL Multiphysics. Five cases with various model training strategies are designed based on these simulation data to verify the performance of the CNN-based model by comparing this model with ANN-based and GNN-based models. The results show that the CNN-based model outperforms other models in all cases. The CNN-based and GNN-based models have significantly smaller local simulation errors than the ANN-based model. The simulation accuracy of the CNN-based model is improved by an average of 45.55 % and 32.90 % compared with the ANN-based and GNN-based models, respectively. Moreover, the computational time of the CNN-based model is reduced to about 0.05 % of the computational time of CFD simulations.

中文翻译：

---

基于卷积神经网络的代理模型，用于室内气流分布的快速计算流体动力学仿真


计算流体动力学 （CFD） 是一种功能强大但耗时的仿真工具，用于建筑室内环境分析。基于人工智能 （AI） 的代理模型，尤其是基于人工神经网络 （ANN） 的模型，是占主导地位的模型，在加速 CFD 仿真方面表现出了巨大的潜力。然而，已发布的基于 AI 的模型并不擅长捕获室内气流分布中的局部空间特征，导致局部仿真精度较差。为了克服这一挑战，本研究提出了一种基于卷积神经网络 （CNN） 的代理模型，用于室内气流分布的快速 CFD 仿真。与其他已发布的基于 AI 的模型相比，该模型可以在 CFD 模拟的室内气流分布数据集中捕获局部空间特征，从而提高准确性。为了使该模型能够处理房间几何信息，提出了一种几何表示策略，将房间几何信息转换为适合 CNN 模型的输入。使用 COMSOL Multiphysics 生成了 2000 个具有不同边界条件的室内气流速度场的仿真数据。基于这些仿真数据设计了 5 个具有不同模型训练策略的案例，通过将该模型与基于 ANN 和基于 GNN 的模型进行比较来验证基于 CNN 的模型的性能。结果表明，基于 CNN 的模型在所有情况下都优于其他模型。基于 CNN 和基于 GNN 的模型的局部仿真误差明显小于基于 ANN 的模型。与基于 ANN 和基于 GNN 的模型相比，基于 CNN 的模型的模拟精度分别平均提高了 45.55% 和 32.90 %。此外，基于 CNN 的模型的计算时间减少到大约 0。05 % 的 CFD 模拟计算时间。