Machine learning (ML) is a useful technique for improving building operations. However, if data can only be obtained from a target building, the data shortage will limit the use of general ML models. To overcome this issue, simplified targets and limited numbers of feature variables are required. In building engineering, building physics can be used to promote ML implementations. In this paper, a case study targeting the operation of engineered natural ventilation is performed based on energy simulations. The target issue is simplified to select the preferable opening pattern, full or half open, throughout the day. Two models using two or three feature variable types are compared. The ML method can effectively predict the correct operation scheme, even in the first year of use. The correct answer rate in the case of three variable types increases from 83% to 95% in the second year, although no significant improvement is observed in the case with two variable types. The results imply the strategy of creating a simplified model first and improving the model following data acquisition works for ML model implementation in building operations.
Airflow windows (AFWs) help to stabilize the thermal environment in the perimeter zone and also allows for switching between solar-shielding and solar heat acquisition operations. This is based on the method of channelizing the air discharged from its cavity layer, either by using a total heat enthalpy exchanger and choosing to exchange heat or otherwise. It has a certain thickness owing to the blinds that are installed in its cavity layer. The purpose of this research is to develop a window system that uses electrochromic (EC) glass, instead of blinds, as a solar-shielding device. This study also provides the specifications of the window system of reduced thickness. The performance of the window system is assessed by CFD analysis. The solar heat gain coefficient (SHGC) of the proposed window system is found to range from 0.083 to 0.268 and its solar radiation properties can be controlled in a flexible manner. These characteristics contribute to an improvement in the building environmental performance in the form of climate-adaptive building shells (CABS) in places with four distinct seasons such as Japan that require solar-shielding to reduce the cooling load in summer and solar heat gain to reduce the heating load in winter.
It is necessary to improve solar blocking performance and reduce solar heat gain coefficient (SHGC) of openings in office buildings in order to reduce the cooling loads. Airflow windows are often practiced in Japan’s office buildings. In this research, we apply a Dynamic Insulation (DI) technique into an airflow window system to improve the solar blocking performance. Computational fluid dynamics (CFD) analyses have been used to measure the thermal performance of the numerical opening model. In the case of using a conventional airflow window model, the inner-surface temperature of the inner glass is 29.4℃. In case the DI technique is applied, it is 27.0℃. The declination of the inner-surface temperature of the window improves the radiant environment in the building perimeter space. Moreover, the heat flux into the room is decreased due to the decline in the temperature difference between indoor temperature and the inner glass surface temperature.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.