Field monitoring and prediction on temperature distribution of glass curtain walls of a super high-rise building

Abstract

Temperature action has a significant effect on the behavior of a supertall structure but has rarely been investigated due to lack of knowledge on the actual temperature measurements. It would be of great significance to predict the time-pace temperature distribution of a high-rise building by using the general environmental monitoring data which is more easily acquired and has a close relation with structural thermal action. In this study, the actual temperature distribution of the exterior glass curtain wall of Shanghai Tower is investigated using the field monitoring data achieved by the integrated real-time Structural Health Monitoring (SHM) system installed on the tower. The data recorded during 2018.1.1–2018.10.13 (283 days) are employed. A data-driven model is developed based on Artificial Neural Network (ANN), which is capable of predicting the temperature distribution of the curtain wall by using the environmental monitoring data including the wind velocity and direction measurements as well as the public weather information. Compared with the discrete temperature measurements at a few limited locations, the proposed model provides continuous time-space temperature distribution of the curtain wall, which adds insights into the knowledge of temperature actions for the maintenance of the Shanghai Tower and the design of glass curtain wall of a supertall structure.