Application of Big Data Analysis and Mathematical Models in Civil and Structural Engineering

This paper proposes a comprehensive approach that combines big data analysis techniques with mathematical models for design optimization and health monitoring in civil and structural engineering. The study collects real-time data on stress, deformation, and environmental conditions of structures through a sensor network and processes these data using finite element analysis, stochastic process models, and dynamic models. Experiments on a three-layer frame structure demonstrate the maximum displacement response results under different load conditions, with seismic loads having a significantly higher impact on the structure than static and wind loads. The optimized seismic design, achieved by increasing the shear wall thickness, optimizing column cross-section dimensions, and adding dampers, reduced the inter-story drift angle by 15%. Additionally, stochastic process models were used to assess the risks faced by building clusters under extreme weather conditions, predicting the potential impact of strong winds and heavy rain on the structures. The results show that this method, through real-time monitoring and data analysis, effectively improves the precision and safety of structural design, optimizes engineering solutions, and provides disaster warnings.