AI-BASED STRUCTURAL HEALTH MONITORING SYSTEMS: IMPROVING SAFETY AND REDUCING MAINTENANCE COSTS IN HIGH-RISE BUILDINGS

Abstract

The rapid growth of high-rise buildings in urban areas has rendered the need to identify reliable, effective and inexpensive methods of managing structural safety a greater priority. The article under consideration considers how AIs-based Structural Health Monitoring (SHM) can be used to provide better safety and reduce maintenance costs in high-rise buildings. Meanwhile, the structural problems were discovered with the help of advanced machine learning and deep learning algorithms, how bad the damage was was determined, and how the structure is thought to work in the future was guessed. This was performed based on information of distributed sensors which recorded the vibration, strain, displacement and the environmental factors. It can be seen that AI-based SHM systems are significantly superior to old-fashioned manual inspection and threshold-based monitoring in detecting the presence of the early signs of deterioration and unusual behaviour of buildings. The predictive analytics allowed performing repair work in time, thus reducing unnecessary inspections, maintenance bills, and the risk of a structural collapse. It was also demonstrated by the system that it could easily respond to various load conditions and environmental conditions and this indicated that it fitted in complex high rise buildings. In general, the analysis demonstrates that AI-based SHM is a powerful, adaptable, and intelligent method of making modern high-rise buildings safer, allowing people to make decisions grounded on information, and reducing the costs of maintaining a building throughout its service.