Detecting thermal bridges in building envelopes should be a priority to improve the thermal performance of buildings. Recently, thermographic surveys are being used to detect thermal bridges. However, conventional methods of detecting thermal bridges from thermal images rely on the subjective judgment of audits. Research has been conducted to automatically detect thermal bridges from thermal images to improve problems caused by such subjective judgment, but most of these studies are still in the early stage. Therefore, this study proposes a linear thermal bridge detection method based on image processing and machine learning. The proposed method includes thermal anomaly area clustering, feature extraction, and an artificial-neural-network-based thermal bridge detection. The proposed method was validated by detecting the thermal bridges in actual buildings. As a result, the average precision, recall, and F-score were 89.29%, 87.29, and 87.63%, respectively.

This paper proposes the design process of optimized building Computational Fluid Dynamics (CFD) model based on Building Information Modelling (BIM). The proposed method consists of five-step processes: BIM data extraction, geometry simplification, grid optimization, attribute data matching, and finally, exporting a CFD case folder for OpenFOAM. Validation is performed to evaluate the improvement of the grid model and the accuracy of the simulation result. Validation is conducted for four indoor ventilation models. The number of grids increased or decreased, according to the optimization method, but did not change significantly. On the other hand, the maximum non-orthogonality improved by up to 20.78%, according to the optimization function. This proves that it is sufficiently effective in improving the grid quality. The accuracy of the proposed method is evaluated by relative error rate with the ANSYS simulation result. The error rates for flow and temperature are evaluated. The relative error rate is less than 5% under all conditions. Therefore, the accuracy of the proposed method is verified.

The energy consumption of low‐rise residential buildings in South Korea exceeds the targets set in national policies and the standards of other countries. Moreover, there are insufficient policies in place to improve the energy performance of existing low‐rise residential buildings and no means to investigate the current status. A standard model enables cost‐effective and fast load forecasting and can also be used to establish long‐term policies through evaluation of energy saving in buildings before and after the application of energy policies. This study developed a standard model for predicting energy consumption by reflecting the characteristics of low‐rise residential buildings in Korea. The standard model was developed based on reliable related standards, national statistical data, and national reports, and the energy variables applied were validated through a sensitivity analysis. Surveys and field measurements were conducted to investigate the energy usage of 70 households in low‐rise residential buildings in Korea, and the developed model was validated through comparison with the actual energy usage data. Consequently, the total energy consumption error rate was 12.67% (R² value: 0.8164), with a significance level higher than 80%, which indicated that the developed model was highly efficient and reliable.

A window set is defined as a window where the frame and the glass are combined and is used at the part that comes into contact with the air. As the performance evaluation of window sets has gained significance, the need for software that can simulate window set performance has also increased accordingly. However, the simulation of window sets is not carried out efficiently due to the difficulty in the window set modeling. Meanwhile, the design of building information modeling has recently proliferated so that the window set BIM library is distributed online. If such a window set BIM library is utilized in the window set simulation, it is expected that the productivity issue that occurs in the simulation process could be improved. Therefore, this study proposes a method to automatically convert the information required in the simulation of the window set heat transfer coefficient from the BIM. In order to achieve the purpose of this study, the following procedure is carried out. First, the framework for converting the information required in the simulation of the window set heat transfer coefficient from the BIM is suggested. Second, the method to extract and convert BIM data based on the suggested framework is proposed. Lastly, the BIM data conversion program is developed, and its performance is validated by applying the window set BIM case. The case study result showed that the information converted and entered from the window set data BIM conversion program coincided with the information entered in the window set BIM. It is expected that the result of this study will increase the productivity of window set simulations, which will lead to the increased use of certification through these simulations.