A real-time prediction method using a multilayer feedforward neural network is proposed for estimating vertical dynamic displacements of a bridge from the longitudinal strains of the bridge when vehicles pass across it. A numerical model for an existing five-girder bridge spanning 36 m proved by actual experimental values was used to verify the proposed method. To obtain a realistic vehicle distribution for the bridge, vehicle type and actual headways of moving vehicles were taken, and the measured vehicle distribution was generalized using Pearson Type III theory. Twenty-five load scenarios were created with assumed vehicle speeds of 40 km/h, 60 km/h, and 80 km/h. The results indicate that the model can reasonably predict the overall displacements of the bridge (which is difficult to measure) from the strain (which is relatively easy to measure) in the field in real time.
Abstract. Measurement of dynamic displacement is one of the most essential aspects of a structural behavior because it portrays history of the global behavior of structure. In general, structural engineers are accepted these response as reliable physical quantities to evaluate the conditions of a structure. The reason is that these physical quantities can easily generate strain as well as stress, velocity and acceleration at the measuring points. However, it is difficult to directly measure the displacement of the bridge due to problems such as test conditions and the limitations of equipment. Therefore, in this study, an artificial neural network (ANN) demonstrates how it could overcome such limitations and utilize the random dynamic load to obtain the reliable estimations. Numerical analysis is conducted to obtain learning data about the axial strain as well as vertical displacement with time frame at multi-points and then applied to the ANN. The scenario centered on a variety of dynamic loads from the analysis of an urban bridge that was selected based on its general volume of traffic. The analysis was performed to estimate its displacement, which corresponds to the strain on the bridge caused by arbitrary loads of leaning results from the ANN. Then, it is confirmed that the estimated displacements of ANN show well agreements with that of an independent set of traffic scenario.
<p>This paper describes introduction about Yeosu Expo 2012 Bio-O project and the changed water stage in detailed design. Water stage is very important as a place which represents purpose and subject of this fair. Therefore, it intends that purpose and subject of this fair are more effectively and precisely given by changing pier type water stage to floating structure in detailed design.</p>
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.