A Study on the Application of Artificial Intelligence in Digital Twin Monitoring of Building Structural Health

With the continuous expansion of urban building volume and the significant increase of operational complexity, the monitoring of the health status of building structures has become a key means to ensure urban safety and sustainable operation of buildings. This paper focuses on the integration and application of artificial intelligence and digital twin technology in building structural health monitoring, and systematically constructs an intelligent monitoring system architecture driven by multi-source sensing data, with AI model as the core and digital twin platform as the carrier. Through the design of multi-dimensional sensing network, the dynamic perception of stress, vibration, displacement and other behaviors of key building components is realized; combined with AI models such as convolutional neural network (CNN), graphical neural network (GNN), and long and short-term memory network (LSTM), the ability of structural state identification, damage prediction and trend modeling is enhanced; and three-dimensional visualization and interactive display of the structural state of health is realized by relying on the BIM platform. The article selects a number of typical engineering scenarios such as high-rise steel structure buildings, underground hubs, and protective buildings to carry out experiments and case studies, and verifies the significant advantages of the AI-driven digital twin system in terms of real-time, accuracy, and adaptability.