Data-Driven Structural Health Monitoring and Damage Detection through Deep Learning: State-of-the-Art Review.

Data-driven methods in structural health monitoring (SHM) is gaining popularity due to recent technological advancements in sensors, as well as high-speed internet and cloud-based computation. Since the introduction of deep learning (DL) in civil engineering, particularly in SHM, this emerging and promising tool has attracted significant attention among researchers. The main goal of this paper is to review the latest publications in SHM using emerging DL-based methods and provide readers with an overall understanding of various SHM applications. After a brief introduction, an overview of various DL methods (e.g., deep neural networks, transfer learning, etc.) is presented. The procedure and application of vibration-based, vision-based monitoring, along with some of the recent technologies used for SHM, such as sensors, unmanned aerial vehicles (UAVs), etc. are discussed. The review concludes with prospects and potential limitations of DL-based methods in SHM applications.

Design and retrofit methodology for building structures witn supplemental energy dissipating systems

The study described in this report on focuses on fundamental issues related to the design and use of supplemental damping devices in building structures. The principle objective is to develop a generic/practical analysis and design methodoly for structures that considers structural velocities and equivalent viscous damping of the devices. These two issues are explored in depth. Tools to transform the spectral velocity to an actual relative structural velocity are provided, and simple design procedure which incorporates power equivalent linear damping based on actual structural velocities is presented. The effectiveness of the design methodology is demonstrated with a retrofit design example using a supplemental load balancing tendom configuration

Experimental investigation and computational modeling of seismic response of a 1:4 scale model steel structure with a load balancing supplemental damping system

An experimental study to investigate the seismic behavior of steel structures under the simulated ground motions is described. It is argued that damper distribution should be based on: (i) either the interstory deformations or story shears, and (ii) the overturning moments generated by the lateral inertia loads. The former method was implemented in a non-ductile reinforced concrete frame (Pekcan et al., 1995), while for the latter method an innovative prestressed load-balancing tendon system was introduced in this report. Approximate alternatives were experimentally explored on a model steel structure. This load-balancing supplemental system consists of prestressed-draped tendons in the shape of the overturning moment diagram. The tendons are connected in series with the nonlinear dampers and sacrificial fuse-bar. It is concluded that the load-balancing tendon-fuse+damper system is an appropriate cost-effective method of mitigating the earthquake induced demands on a steel frame. By careful detailing, it is possible to ensure that under design earthquake loads the structure remains elastic, while under maximum credible motions fracture of the steel frame welded connections can be avoided