For a supertall structure, the temperature effect is an important factor that must be considered during the design, construction, and performance assessment. In this article, temperature-induced displacement of the 600-m-high Canton Tower is studied by the data-driven approach based on the sufficient real measurement data obtained from the structural health monitoring system. A multiple linear regression model is employed to establish the quantitative relation between the displacement and temperature data at different facades and sections of the structure in different seasons. Results show that an ordinary linear regression model is able to fit the monitoring data well. However, the model fails to interpret the physical meaning of the model coefficients. A regularized linear regression model is then employed and validated to describe the temperature-induced displacement of the structure. The physical relationship between the temperature and displacement is provided. Finally, the model is also used to separate the temperature- and wind-induced displacement of the supertall structure.
- linear regression
- supertall structure
ASJC Scopus subject areas
- Civil and Structural Engineering
- Building and Construction