Modular building is becoming a common sight due to government policies promoting greater automation and productivity. When moving towards modularity, indoor comfort within volumetric modules, such as levels of humidity and temperature, natural ventilation, and air pollutant transport, have a major effect on human health and well-being. Computational fluid dynamics simulations (CFD) are used to evaluate the efficiency of natural ventilation. However, designers usually find it difficult to visualize the CFD simulation results, which can deepen users’ understanding of the wind environment and help optimize the design of modular buildings. To overcome this challenge, this paper presents an integrated approach based on building information modeling (BIM) and virtual reality (VR), with the aim of analyzing the aerodynamic design and wind comfort for modular buildings. The framework consists of four salient components. First, a new method, combining OpenStreetMap and Dynamo, is proposed to achieve rapid urban modeling of modular buildings. The second step involves the use of CFD to simulate the outdoor wind environment surrounding modular buildings. The third step emphasizes the integration of CFD-computed data with VR applications to create an immersive virtual environment for designers to analyze the wind environment of design alternates. Finally, the visual experience of non-professional users is used to improve the ventilation of the building and support more informed decision marking at the early stage of building design. The proposed framework is illustrated via a case study that focuses on a group of modular housings in the urban area of Singapore. The results indicate that visualization of CFD simulations in VR provides designers with more details regarding the actual space, and it is expected to help optimize the architectural design.

Building safety assessment based on single sensor data has the problems of low reliability and high uncertainty. Therefore, this paper proposes a novel multi-source sensor data fusion method based on Improved Dempster–Shafer (D-S) evidence theory and Back Propagation Neural Network (BPNN). Before data fusion, the improved self-support function is adopted to preprocess the original data. The process of data fusion is divided into three steps: Firstly, the feature of the same kind of sensor data is extracted by the adaptive weighted average method as the input source of BPNN. Then, BPNN is trained and its output is used as the basic probability assignment (BPA) of D-S evidence theory. Finally, Bhattacharyya Distance (BD) is introduced to improve D-S evidence theory from two aspects of evidence distance and conflict factors, and multi-source data fusion is realized by D-S synthesis rules. In practical application, a three-level information fusion framework of the data level, the feature level, and the decision level is proposed, and the safety status of buildings is evaluated by using multi-source sensor data. The results show that compared with the fusion result of the traditional D-S evidence theory, the algorithm improves the accuracy of the overall safety state assessment of the building and reduces the MSE from 0.18 to 0.01%.