AI-Driven Structural Health Monitoring for the Tallest Curved Concrete Skyscraper

Abstract

With the rapid increase in the construction of tall buildings around the world, ensuring their safety and structural integrity has become of paramount importance. This paper focuses on the Al-Hamra Tower, a remarkable skyscraper standing at an impressive height of 412.6 meters (1,353’-6”) in Kuwait City in Kuwait, and explores the role of Structural Health Monitoring (SHM) as a powerful tool for assessing building conditions, detecting damage following extreme events, and optimizing cost-saving strategies. Among the various factors that can lead to building failures, extreme events such as earthquakes in the Gulf Region pose the greatest threat. If damage conditions are not promptly identified, they can leave the structure vulnerable to further deterioration. Early diagnosis of damage is not only crucial for the safety of occupants but also proves to be cost-effective, as repairing minor damage is generally more affordable than addressing major structural failures. This paper presents an advanced AI-powered SHM system specifically developed for the Al-Hamra Tower. The study delves into the implementation of a dense array of instrumentation strategically placed throughout the tower to capture and measure its structural response under different loadings, including wind, seismic activity, and thermal effects. The SHM system incorporates an automated triggering mechanism that responds to predefined events, such as earthquakes, and promptly sends text and email notifications to alert relevant authorities. By highlighting the case study of the Al-Hamra Tower, this research underscores the critical importance of SHM for tall and critical buildings, offering invaluable insights into the design and implementation of effective SHM systems for future skyscrapers. Keywords: AI, SHM, machine-learning, earthquake, tall-building, multi-sensing, big-data, analytics, early-warning, seismic-design, neural-network