用稀疏传感器重建屋顶风场，深度学习比传统方法更准且更稳。
Rooftop Wind Field Reconstruction Using Sparse Sensors: From Deterministic to Generative Learning Methods
- 用实验数据训练UNet、ViTAE和CWGAN模型，替代传统插值法
- 深挖模型在5-30个传感器下性能超克里金插值，最高提升173.7%
- 混合风向训练+传感器优化可显著提升鲁棒性，适合真实部署
实时获取屋顶风速分布对无人机安全飞行、城市空中交通及屋顶利用至关重要。但屋顶流场具有强非线性、分离与跨方向变异特性，导致稀疏传感器下的流场重构困难。本研究基于粒子图像测速（PIV）的风洞实验数据，构建观测学习框架，对比克里金插值与三种深度学习模型：UNet、视觉变换器自编码器（ViTAE）和条件瓦瑟斯坦生成对抗网络（CWGAN）。评估单风向训练（SDT）与混合风向训练（MDT）两种策略，覆盖5至30个传感器密度，测试传感器位置扰动±1格的鲁棒性，并通过本征正交分解结合QR分解优化传感器布局。结果表明，深度学习方法能有效重构稀疏传感器下的屋顶风场。相比克里金插值，深度模型使结构相似性（SSIM）提升最高达32.7%，相关系数（FAC2）提升24.2%，归一化均方误差（NMSE）降低27.8%。混合风向训练进一步提升性能，相较单向训练，SSIM提升达173.7%，FAC2提升16.7%，平均梯度（MG）提升98.3%。结果还显示，传感器配置、优化与训练策略需协同设计以保障可靠部署。基于QR的优化在传感器扰动下将鲁棒性提升最高27.8%，但存在指标依赖性权衡。基于真实实验数据而非仿真数据的训练，为不同场景下的方法选择与传感器布置提供实用指导。
原文摘要 · Abstract (English)
Real-time rooftop wind-speed distribution is important for the safe operation of drones and urban air mobility systems, wind control systems, and rooftop utilization. However, rooftop flows show strong nonlinearity, separation, and cross-direction variability, which make flow field reconstruction from sparse sensors difficult. This study develops a learning-from-observation framework using wind-tunnel experimental data obtained by Particle Image Velocimetry (PIV) and compares Kriging interpolation with three deep learning models: UNet, Vision Transformer Autoencoder (ViTAE), and Conditional Wasserstein GAN (CWGAN). We evaluate two training strategies, single wind-direction training (SDT) and mixed wind-direction training (MDT), across sensor densities from 5 to 30, test robustness under sensor position perturbations of plus or minus 1 grid, and optimize sensor placement via Proper Orthogonal Decomposition with QR decomposition. Results show that deep learning methods can reconstruct rooftop wind fields from sparse sensor data effectively. Compared with Kriging interpolation, the deep learning models improved SSIM by up to 32.7%, FAC2 by 24.2%, and NMSE by 27.8%. Mixed wind-direction training further improved performance, with gains of up to 173.7% in SSIM, 16.7% in FAC2, and 98.3% in MG compared with single-direction training. The results also show that sensor configuration, optimization, and training strategy should be considered jointly for reliable deployment. QR-based optimization improved robustness by up to 27.8% under sensor perturbations, although with metric-dependent trade-offs. Training on experimental rather than simulated data also provides practical guidance for method selection and sensor placement in different scenarios.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。