Risk management of deep excavation is always an important issue. One of the core problems is to accurately simulate and predict the time series of displacement collected from the site sensors to monitor the risk variation. Meanwhile, the applications of building information modelling (BIM) and geographic information system (GIS) can integrate the construction structures into the surrounding environment, visualizing various information and supporting decision making for risk treatment. Therefore, this paper proposes a risk management system to monitor the risk variation for deep excavation based on optimized grey Verhulst model (GVMm), BIM-3DGIS framework and risk monitoring. The grey Verhulst model (GVM) has demonstrated well performance on saturation curve, such as displacement of deep excavation. This paper establishes the GVMm by improving GVM to predict the displacement more precisely. BIM-3DGIS framework is also built by integrating BIM and 3DGIS in the application level for the efficiency of system operation and the interaction with the risk management platform. BIM-3DGIS framework, working with the risk management platform, can monitor the risk variation of deep excavation effectively and provide visual decision-making supports. A real case of deep excavation is used as an illustrative example to verify the practicability. The results show that the prediction precision of GVMm is better than that of GVM. The application scenarios also demonstrate the effectiveness of the risk management system.

Several natural and human factors are responsible for the defacement of the external walls and tiles of buildings, and the related deterioration can be a public safety hazard. Therefore, active building maintenance and repair processes are essential for ensuring building sustainability. However, conventional inspection methods are time‐, cost‐, and labor‐intensive processes. Therefore, herein, this study proposes a convolutional neural network (CNN) model for image‐based automated detection and localization of key building defects (efflorescence, spalling, cracking, and defacement). Based on a pretrained CNN VGG‐16 classifier, this model applies class activation mapping for object localization. After identifying its limitations in real‐life applications, this study determined the model’s robustness and ability to accurately detect and localize defects in the external wall tiles of buildings. For real‐time detection and localization, this study applied this model by using mobile devices and drones. The results show that the application of deep learning with UAV can effectively detect various kinds of external wall defects and improve the detection efficiency.

Construction has long been seen as a high-risk industry. Many studies conduct risk management by controlling construction risk indicators, but few studies associate risk indicators with time and space to propose long-term risk management methods. Therefore, this study proposes a dynamic analysis and visual tracking method based on behavior-based safety (BBS). This study establishes a BBS observation checklist and records workers’ unsafe behavior. The risk level of unsafe behavior is then determined by grey clustering model. When a high risk occurs, an improved grey correlation model is used to track key indicators that affect risk. In order to achieve visual risk management, this study develops semantic logic to predefine the relationship between components and space. In schedule simulation of BIM, the key indicators of BBS are transformed into an executable visual inspection between work items, components, and space through ARC. This method makes it easier for construction managers to combine time and space to manage safety risk and to adopt appropriate strategies in a timely manner to improve the efficiency of safety management.

This study proposes a hybrid grey model for forecasting annual maximum daily rainfall in order to determine long-term hydrological system trends. The proposed model uses an integral form of background value to improve accuracy, and applies two residual operators, the Fourier series and the exponential smoothing technique, to correct periodic and stochastic errors. The annual maximum daily rainfall measured by 5 stations around Taiwan are used to validation the proposed model. The performance of the proposed hybrid grey model is compared with those of the autoregressive integrated moving average (ARIMA) and artificial neural network (ANN) models. By evaluation of different indicators, it is shown that the proposed model outperforms both compared models. With more precise information, the proposed model will allow government officials and civil engineering-related industries to better prepare for heavy rainfall, averting potential disasters.