Reduced-order urban wind interference

Abstract

A novel approach is demonstrated to approximate the effects of complex urban interference on the wind-induced surface pressure of tall buildings. This is achieved by decomposition of the domain into two components: the obstruction model (OM) of the static large-scale urban context, for which a single computational fluid dynamics (CFD) simulation is run; and the principal model (PM) of the isolated tall building under design, for which repeatable reduced-order model (ROM) predictions can be made. The ROM is generated with an artificial neural network (ANN), using a set of feature vectors comprising an input of local shape descriptors and a range of wind speeds from a training geometry, and an output response of pressure. For testing, the OM CFD simulation provides the flow boundary condition wind speeds to the PM ROM prediction. The result is vertexresolution surface pressure data for the PM mesh, intended for use within generative design exploration and optimisation. It is found that the mean absolute prediction error is around 5.0% (σ:7.8%) with an on-line process time of 390s, 27-times faster than conventional CFD simulation; considering full process time, only 3.2 design iterations are required for the ROM time to match CFD. Existing work in the literature focuses solely on creating generalised rules relating global configuration parameters and a global interference factor (IF). The work presented here is therefore a significantly alternative approach, with the advantages of increased geometric flexibility, output resolution, speed, and accuracy.

The State of the Art in Visual Analytics for 3D Urban Data

“…All of the surveyed papers about wind & ventilation were domain‐specific ones (43). Wilkinson et al present a data generation technique to approximate complex computational fluid dynamics (CFD) using an artificial neural network [WBH14]. The other surveyed papers were primarily analysis contributions that relayed on CFD for building‐level [AKH19] or neighborhood‐level [EGAB17, ZKL*21] wind load analysis (Figure 12 (Super‐imposition)), wind power potential [SDP20], inner building ventilation [SL19,HP20], wind impact on urban climate [GBI14,DL19, HP21], pollution dispersion [GL19,ZWLZ22,HZL*23, LMS*23], or the interplay between sunlight access and wind for thermal comfort [JY20].…”

CFD Simulation and Visualization Based Investigation of Small Wind Turbine Potential: A Case Study “Neuer Stöckach” for Stuttgart

“…In addition they performed a correlation analysis between the price and the rated power of vertical axis wind turbines (VAWT) rated below 5000 kWh. Wilkinson et al demonstrated a new approximation approach of computational fluid dynamics in high rise buildings with complex wind interference (Wilkinson et al, 2014). Wang et al compared and analyzed seven different urban tissues using CFD simulations in the area of Beijing.…”

Towards machine learning for architectural fabrication in the age of industry 4.0

“…The underlying approach is still in its infancy, the potential breadth of its application is however supported by a wide array of related research, investigating ML for simulation of wind, 19–21 structural 22 and climatic performance, 23 formfinding and analysis of bending active structures, 24 macroscopic material behaviour, 25 driving styles of cars 26 and the utilization of heavy equipment on construction sites. 27…”