Abstract: Chemical spills on complex geometry are difficult to model due to the uneven concentration distribution caused by air flow over ground obstacles. Computational fluid dynamics (CFD) is one of the powerful tools to estimate the building-resolving wind flow as well as pollutant dispersion. However, it takes too much time and requires enormous computational power in emergency situations. As a time demanding task, the estimation of the chemical spill consequence for emergency response requires abundant wind field information. In this paper, a comprehensive wind field reconstruction framework is proposed, providing the ability of parameter tuning for best reconstruction accuracy. The core of the framework is a data regression model built on principal component analysis (PCA) and extreme learning machine (ELM). To improve the accuracy, the wind field estimation from the regression model is further revised from local wind observations. The optimal placement of anemometers is provided based on the maximum projection on minimum eigenspace (MPME) algorithm. The fire dynamic simulator (FDS) generates high-resolution data of wind flow over complex geometries for the framework to be implemented. The reconstructed wind field is evaluated against simulation data and an overall reconstruction error of 9% is achieved. When used in real case, the error increases to around 12% since no convergence check is available. With parameter tuning abilities, the proposed framework provides an efficient way of reconstructing the wind flow in congested areas.

Key words: Wind field reconstruction, CFD, PCA, Extreme learning machine, Sensor placement

摘要： Chemical spills on complex geometry are difficult to model due to the uneven concentration distribution caused by air flow over ground obstacles. Computational fluid dynamics (CFD) is one of the powerful tools to estimate the building-resolving wind flow as well as pollutant dispersion. However, it takes too much time and requires enormous computational power in emergency situations. As a time demanding task, the estimation of the chemical spill consequence for emergency response requires abundant wind field information. In this paper, a comprehensive wind field reconstruction framework is proposed, providing the ability of parameter tuning for best reconstruction accuracy. The core of the framework is a data regression model built on principal component analysis (PCA) and extreme learning machine (ELM). To improve the accuracy, the wind field estimation from the regression model is further revised from local wind observations. The optimal placement of anemometers is provided based on the maximum projection on minimum eigenspace (MPME) algorithm. The fire dynamic simulator (FDS) generates high-resolution data of wind flow over complex geometries for the framework to be implemented. The reconstructed wind field is evaluated against simulation data and an overall reconstruction error of 9% is achieved. When used in real case, the error increases to around 12% since no convergence check is available. With parameter tuning abilities, the proposed framework provides an efficient way of reconstructing the wind flow in congested areas.

关键词: Wind field reconstruction, CFD, PCA, Extreme learning machine, Sensor placement