Faulkner Cary A, Jankowski Dominik S, Castellini John E, Zuo Wangda, Epple Philipp, Sohn Michael D, Kasgari Ali Taleb Zadeh, Saad Walid
Department of Mechanical Engineering, University of Colorado Boulder, Boulder, CO USA.
HySON Institut, Sonneberg, Germany.
Build Simul. 2023 Mar 13:1-20. doi: 10.1007/s12273-023-0989-1.
Prediction of indoor airflow distribution often relies on high-fidelity, computationally intensive computational fluid dynamics (CFD) simulations. Artificial intelligence (AI) models trained by CFD data can be used for fast and accurate prediction of indoor airflow, but current methods have limitations, such as only predicting limited outputs rather than the entire flow field. Furthermore, conventional AI models are not always designed to predict different outputs based on a continuous input range, and instead make predictions for one or a few discrete inputs. This work addresses these gaps using a conditional generative adversarial network (CGAN) model approach, which is inspired by current state-of-the-art AI for synthetic image generation. We create a new Boundary Condition CGAN (BC-CGAN) model by extending the original CGAN model to generate 2D airflow distribution images based on a continuous input parameter, such as a boundary condition. Additionally, we design a novel feature-driven algorithm to strategically generate training data, with the goal of minimizing the amount of computationally expensive data while ensuring training quality of the AI model. The BC-CGAN model is evaluated for two benchmark airflow cases: an isothermal lid-driven cavity flow and a non-isothermal mixed convection flow with a heated box. We also investigate the performance of the BC-CGAN models when training is stopped based on different levels of validation error criteria. The results show that the trained BC-CGAN model can predict the 2D distribution of velocity and temperature with less than 5% relative error and up to about 75,000 times faster when compared to reference CFD simulations. The proposed feature-driven algorithm shows potential for reducing the amount of data and epochs required to train the AI models while maintaining prediction accuracy, particularly when the flow changes non-linearly with respect to an input.
室内气流分布的预测通常依赖于高保真、计算密集型的计算流体动力学（CFD）模拟。通过CFD数据训练的人工智能（AI）模型可用于快速准确地预测室内气流，但目前的方法存在局限性，例如只能预测有限的输出，而非整个流场。此外，传统的AI模型并非总是设计用于基于连续输入范围预测不同的输出，而是针对一个或几个离散输入进行预测。这项工作使用条件生成对抗网络（CGAN）模型方法来解决这些差距，该方法受到当前用于合成图像生成的最先进AI的启发。我们通过扩展原始的CGAN模型创建了一个新的边界条件CGAN（BC-CGAN）模型，以基于连续输入参数（如边界条件）生成二维气流分布图像。此外，我们设计了一种新颖的特征驱动算法来策略性地生成训练数据，目标是在确保AI模型训练质量的同时，尽量减少计算成本高昂的数据量。针对两个基准气流案例对BC-CGAN模型进行了评估：等温顶盖驱动方腔流和带有加热箱的非等温混合对流。我们还研究了基于不同验证误差标准停止训练时BC-CGAN模型的性能。结果表明，与参考CFD模拟相比，训练后的BC-CGAN模型能够以小于5%的相对误差预测速度和温度的二维分布，速度快约75000倍。所提出的特征驱动算法在减少训练AI模型所需的数据量和轮次同时保持预测精度方面显示出潜力，特别是当流相对于输入呈非线性变化时。
