Research Assistant, Carnegie Mellon Univeristy
Use advanced machine learning algorithim to predict natural ventilation performance with a new index
The United Nations predicted that, by 2050, 66% of the world’s population will live in urban areas. However, high-density cities usually surfer deterioration of the urban built environment (such as urban heat island and urban pollution) due to slow or stagnant air movement. This deterioration could be mitigated by improved urban natural ventilation through good urban planning and building design. In addition, since indoor wind performance is highly related to the outdoor wind field, it is important to study the interactions between indoor and outdoor environments for natural ventilation assessment. Unfortunately, indoor natural ventilation requirements in current building standards only consider absolute indoor air speed without taking into account outdoor conditions. To fill this gap, this research proposes a new integrated index (CIOI index) to evaluate indoor natural ventilation potential, which couples both indoor and outdoor wind environments. In addition, to help designers understand the impact of different design scenarios on the indoor ventilation performance in the early design stage, this research applies an advanced machine learning algorithm to train a non-linear regression model based on parametric CFD simulations, which can predict the CIOI index in high-density urban areas using given key design variables.
The innovations are as follows: 1.Indoor wind environment is highly related to the outdoor wind field. It is therefore necessary to consider outdoor natural ventilation performance for indoor airflow evaluation. The coupled CFD model provides both indoor and outdoor wind environments in the same computational domain, which creates the possibility of comparing the wind velocity ratio of indoor and outdoor spaces.
Abstract: Publication date: March 2017 Source:Building and Environment, Volume 114 Author(s): J.A. Castillo, G. Huelsz Natural ventilation is an alternative to create comfortable and healthy indoor conditions. This work presents the development of a methodology to evaluate the thermal comfort produced by indoor natural ventilation in hot climates. This methodology includes the definition of the Heat Balance Index, H B I . It is based on models of the heat transfer of the human body to the surroundings. To estimate the comfort evaporation term a correlation between the Heat Balance Index (HBI) and the Predicted Mean Value (PMV) was made. The H B I gives the comfort air velocity range, which is useful to calculate the well-ventilated percentage of an indoor space for an specific climate condition in hot climates. A numerical simulation of a cross ventilated building is used as an application example. The numerical simulation is solved by using Computational Fluid Dynamics and is validated with experimental results. Graphical abstract
Pub.: 05 Jan '17, Pinned: 29 Jun '17
Abstract: This study applied a Reynolds Averaged Navier-Stokes (RANS) approach with Renormalization Group (RNG) k-ɛ turbulence model on a simplified cubical array with uniform height arranged in square layout to study the effect of different opening position on wind-induced ventilation performance in urban area. Nine different cross opening configurations located on both leeward and windward façade are tested. The velocity distribution inside the building is observed as well as the ventilation rate for all cases. The result shows that openings located in the upper part of windward wall allows higher flow rate while openings positioned near the floor exhibits the lowest.
Pub.: 30 Dec '16, Pinned: 29 Jun '17
Abstract: Energy prediction of machine tools can deliver many advantages to a manufacturing enterprise, ranging from energy-efficient process planning to machine tool monitoring. Physics-based, energy prediction models have been proposed in the past to understand the energy usage pattern of a machine tool. However, uncertainties in both the machine and the operating environment make it difficult to predict the energy consumption of the target machine reliably. Taking advantage of the opportunity to collect extensive, contextual, energy-consumption data, we discuss a data-driven approach to develop an energy prediction model of a machine tool in this paper. First, we present a methodology that can efficiently and effectively collect and process data extracted from a machine tool and its sensors. We then present a data-driven model that can be used to predict the energy consumption of the machine tool for machining a generic part. Specifically, we use Gaussian Process (GP) Regression, a non-parametric machine-learning technique, to develop the prediction model. The energy prediction model is then generalized over multiple process parameters and operations. Finally, we apply this generalized model with a method to assess uncertainty intervals to predict the energy consumed to machine any part using a Mori Seiki NVD1500 machine tool. Furthermore, the same model can be used during process planning to optimize the energy-efficiency of a machining process.
Pub.: 28 Jun '17, Pinned: 29 Jun '17