Performance evaluation of retrofitted reinforced concrete structures by machine learning

Abstract

With an emphasis on high-rise structures exposed to dynamic forces such as seismic and wind forces, this collection of research examines cutting-edge tactics and technology meant to increase the seismic resilience of buildings. Numerous studies look into improving damping systems, such as where to place base isolators (BI) and fluid viscous dampers (FVD). According to these studies, spreading dampers over several levels or the whole building improves seismic stability and lessens undesired structural motions. Another effective method for anticipating seismic reactions and enhancing structural performance is ML (machine learning). Predicting the seismic risk of reinforced concrete moment-resistant frames (RC MRFs), including story displacements and inter story drift, is a key application. For more precise seismic load reconstruction, the application of data-driven dynamic load identification algorithms—like deep learning (LSTM) and artificial neural networks (ANNs)—is also investigated. When taken as a whole, these studies demonstrate how optimization algorithms, machine learning, and sophisticated damping technologies can revolutionize contemporary seismic design and open the door to more durable and affordable tall building options in seismically active areas.