It is witnessed that building information modeling (BIM) technology has shown its capabilities in data integration in the construction industry. Incorporating innovative geotechnical theories into BIM helps to further develop its application potential. In the practice of deep excavation engineering, obtaining accurate soil parameters is the key to preventing deep excavation accidents and reducing construction costs. Aiming at the complexity of soil properties in soft soil deep excavations, an intelligent inversion framework for soil parameters in deep excavations is established by using BIM technology, finite difference method (FDM), and nondominated sorting genetic algorithm II (NSGA-II). Firstly, a building information modeling-numerical simulation (BIM-NS) integrated component is implemented based on a transformation interface, including geometric meshing processing and controlled script automated execution. Then, a back-analysis component based on NSGA-II optimization is attached to the BIM-NS processing to improve the accuracy of soil parameters. Subsequently, a framework of the building information modeling- numerical simulation-machine learning (BIM-NS-ML) integrated technology is established, enabling the usage of optimal soil parameters for automatic deep excavation simulation. Finally, the integrated framework is applied to a subway deep excavation project, which verifies that the proposed intelligent integration framework can accurately identify soil parameters in an efficient manner. The BIM-NS-ML integrated technology significantly improves the efficiency of modeling and calculating. The multi-objective optimization algorithm effectively addresses the problem of parameter complexity in soft soil. In addition, the intuitiveness of parameter inversion results is further enhanced to provide support for construction management and decision-making.

Smart buildings represent a significant trend in the future of the construction industry. The performance of human-computer interaction plays a vital role in achieving this from a human perspective. However, existing human-computer interaction algorithms are often limited to simple commands and fail to meet the complex and diverse needs of users. To address this issue, this paper introduces large language models (LLMs) and AI agents into smart buildings, proposing a general AI agent framework based on the ReAct strategy. The LLM serves as the system’s brain, responsible for reasoning and action planning, while tool calling mechanism puts the LLM’s plans into practice. Through this framework, developers can rely on prompt engineering alone to enable the LLM to interpret user intent accurately, perform appropriate actions, and manage conversation history effectively, without any pre-training or fine-tuning. To examine this framework, an experiment was conducted in a virtual building, which showed that the proposed agent successfully completed 91% of simulated tasks. Additionally, the agent was deployed on a single-board computer to control devices in a model building, demonstrating its effectiveness in the real world. The successful operation of the agent in this environment highlighted the potential applications of the proposed framework using existing IoT systems, providing a new perspective for the upgrading of human-computer interaction systems in smart buildings in the near future.

Ground and building settlements induced by tunneling excavation are common in cities. Such settlements can cause instability of the ground and threaten the safety of the upper infrastructures or buildings. Hence, it is vital to monitor the settlements during tunnel excavation to identify any potential risk. The current approach for settlement monitoring relies on manual measurements, which suffers from low efficiency and high labor cost. To improve monitoring efficiency, this study presents a settlement monitoring method based on terrestrial LiDAR data, which mainly consists of rough and fine alignment steps. Algorithms are developed to automatically process the 3D point cloud data obtained from terrestrial LiDAR and obtain settlement values for grounds and buildings. The proposed technique was applied and validated in a region with on-going tunneling works in Singapore. Different monitoring strategies including local-scan based method and registration-based method were examined and compared in this case study. Results demonstrated that the local scan-based monitoring method could yield more accurate settlement measurements compared with the traditional survey method. Registration-based method had higher calculation efficiency but with insufficient accuracy. In general, it is demonstrated that the LiDAR based settlement monitoring method is feasible in engineering practice, with measurement errors controlled within 2–3 mm, and has great potential to improve efficiency and reduce labor cost required by the traditional method.

The production of precast concrete (PC) component in factory is a very influential and complex work for the construction of the project. The rhythm of production is often delayed because the production process in most PC component factories is discrete at present. This study focuses on the production process of PC components and aims to propose regular scheduling and dynamic rescheduling models in prefabricated building project management. Based on the swarm-intelligence (SI) collaboration mechanism, the dynamic-interval synergy auction (DISA) strategy is proposed to improve contract net protocol (CNP). The genetic algorithm based on Tchebycheff (TCH) decomposition strategy is used to obtain the optimal production scheduling schemes. In addition, this model designs a coding mechanism for components based on Omniclass classification standard and the attributes of components are extended based on IFC extension mechanism. This model was verified in a PC factory. The experimental results showed that the decentralized negotiation mode with dynamic time window mechanism can avoid local optimization of schemes. Compared with traditional calculation method, this method could obtain more comprehensive and lower cost schemes. Based on the collaboration mechanism, with improved CNP and TCH strategies introduced, the dynamic model can improve the integrity and intelligence of PC factory.

Digital twins (DTs) are emerging as a promising technology for effective infrastructure management by continuously capturing the dynamic and comprehensive state of physical systems. However, their adoption for managing road infrastructure during the operation and maintenance (O&M) phase remains limited, which is otherwise the most prolonged and critical phase of the asset life cycle. This study proposed a multitier DT framework specifically tailored for road O&M, which is designed to be flexible, modular, interoperable, and, importantly, trustworthy. A core component of this framework is a trustworthy AI-supported module that assists users in making informed decisions that align with their preferences and expectations, thereby fostering user trust and satisfaction in the road DT system. The framework was piloted on three major roads in the United Kingdom, demonstrating its effectiveness through the implementation of vegetation control. This study aims to actively promote the development and deployment of DT technologies and trustworthy AI within advanced road infrastructure management.

Digital twin (DT) technology is revolutionizing the construction industry by creating real-time digital replicas of physical assets, enabling enhanced monitoring, optimization, and decision-making. In Denmark, the integration of DTs aligns with national objectives for sustainability and digital innovation, supported by collaborative efforts among research institutions, government, and industry stakeholders. Despite significant progress, several challenges persist, including integrating diverse data sources, ensuring cybersecurity, and managing implementation costs. Addressing these barriers is critical to scaling DT adoption and maximizing its potential in construction applications. This paper anticipates significant advancements, such as AI-driven predictive analytics, integration with circular economy practices, and the establishment of open standards to ensure seamless interoperability. The findings demonstrate how Denmark’s DT initiatives are reshaping the construction landscape, offering practical insights into overcoming barriers and advancing sustainability goals. In conclusion, Denmark’s proactive adoption of DT technology serves as a blueprint for leveraging innovation to create smarter, more sustainable construction practices, setting a benchmark for global efforts in this domain.