A pinboard by
Chao Ding

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.

  1. This research proposes a new integrated index (CIOI index). The proposed CIOI provides the possibility to link indoor velocity with outdoor velocity and shows the ventilation potential, which is not considered in the current natural ventilation standards.
  2. For ventilation prediction, the traditional curve fitting method requires a predefined formulation and strong engineering knowledge, which creates a barrier for urban planners and architects. My data-driven prediction model shows robust performance with acceptable accuracy for an early design purpose on a generic urban geometry and real urban scenarios. Compared with traditional CFD simulation, this prediction model can provide real time results based on designer's input.

Towards a generalized energy prediction model for machine tools.

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