• Journal of the Korea institute for structural maintenance and inspection
• /
• v.2 no.4
• /
• pp.137-147
• /
• 1998

The neural net application was tried to develop the technique for monitoring the health status of a steel truss bridge which was scaled down to 1/15 of the real bridge for the laboratory experiments. The damage scenarios were chosen as 7 cases. The dynamic behavior, which was changed due to the breakage of the members, of the bridge was investigated by finite element analysis. The bridge consists of single spam, and eight (8) main structural subsystems. The loading vehicle, which weighs as 100 kgf, was operated by the servo-motor controller. The accelerometers were bonded on the surface of 7 cross-beams to measure the dynamic behavior induced by the abnormal structural condition. Artificial neural network technique was used to determine the severity of the damage. At first, the neural net was learnt by the results of finite element analysis, and also, the maximum detection error was 3.65 percents. Another neural net was also learnt, and verified by the experimental results, and in this case, the maximum detection error was 1.05 percents. In future study, neural net is necessary to be learnt and verified by various data from the real bridge.

• Steel and Composite Structures
• /
• v.44 no.2
• /
• pp.241-254
• /
• 2022

The cables in a cable-stayed bridge are critical load-carrying parts. The potential damage to cables should be identified early to prevent disasters. In this study, an efficient deep learning model is proposed for the damage identification of cables using both a multi-layer perceptron (MLP) and a graph neural network (GNN). Datasets are first generated using the practical advanced analysis program (PAAP), which is a robust program for modeling and analyzing bridge structures with low computational costs. The model based on the MLP and GNN can capture complex nonlinear correlations between the vibration characteristics in the input data and the cable system damage in the output data. Multiple hidden layers with an activation function are used in the MLP to expand the original input vector of the limited measurement data to obtain a complete output data vector that preserves sufficient information for constructing the graph in the GNN. Using the gated recurrent unit and set2set model, the GNN maps the formed graph feature to the output cable damage through several updating times and provides the damage results to both the classification and regression outputs. The model is fine-tuned with the original input data using Adam optimization for the final objective function. A case study of an actual cable-stayed bridge was considered to evaluate the model performance. The results demonstrate that the proposed model provides high accuracy (over 90%) in classification and satisfactory correlation coefficients (over 0.98) in regression and is a robust approach to obtain effective identification results with a limited quantity of input data.

• Proceedings of the Computational Structural Engineering Institute Conference
• /
• 2008.04a
• /
• pp.387-390
• /
• 2008

The importance of the life cycle cost analysis for construction projects of bridge has been recognized over the last decades. Accordingly, theoretical models, guidelines, and supporting softwares have been developed for the life cycle cost analysis of bridges. However, it is difficult to predict life cycle cost considering uncertainties precisely. This paper presents methodology for optimal design of substructure for a steel box bridge. Total life cycle cost for the service life is calculated as sum of initial cost, damage cost considering uncertainty, maintenance cost, repair and rehabilitation cost. The optimization method is applied to design of a bridge substructure with minimal cost, in which the objective function is set to life cycle cost and constraints are formulated on the basis of Korean Bridge Design Specification. Initial cost is calculated based on standard costs of the Korea Construction Price Index and damage cost on the damage probabilities to consider the uncertainty of load and resistance. An advanced first-order second moment method is used as a practical tool for reliability analysis using damage probability. Maintenance cost and cycle is determined by a stochastic method and user cost includes traffic operation costs and time delay costs.

• Smart Structures and Systems
• /
• v.15 no.3
• /
• pp.523-541
• /
• 2015

Structural health monitoring of steel truss bridge based on changes in modal properties was investigated in this study. Vibration measurements with five sensors were conducted at an existing Warren truss bridge with partial fractures in diagonal members before and after an emergency repair work. Modal properties identified by the Eigensystem Realization Algorithm showed evidences of increases in modal damping due to the damage in diagonal member. In order to understand the dynamic behavior of the bridge and possible mechanism of those increases in modal damping, theoretical modal analysis was conducted with three dimensional frame models. It was found that vibrations of the main truss could be coupled internally with local vibrations of diagonal members and the degree of coupling could change with structural changes in diagonal members. Additional vibration measurements with fifteen sensors were then conducted so as to understand the consistency of those theoretical findings with the actual dynamic behavior. Modal properties experimentally identified showed that the damping change caused by the damage in diagonal member described above could have occurred in a diagonal-coupled mode. The results in this study imply that damages in diagonal members could be detected from changes in modal damping of diagonal-coupled modes.

• Journal of the Korea institute for structural maintenance and inspection
• /
• v.18 no.6
• /
• pp.60-71
• /
• 2014

Cable-stayed bridge, which is one of the representative long-spanned bridge, needs prompt maintenances when a stay cable is damaged because it may cause structural failure of the entire bridge. Many researches are being conducted to develop abnormal behavior detection algorithms for the purpose of shortening the reaction time after the occurrence of structural damage. To improve the accuracy of the damage detection algorithm, ample observation data from various kinds of damage responses is needed. However, it is difficult to measure an abnormal response by damaging an existing bridge, numerical simulation can be an effective alternative. In most previous studies, which simulate the damage responses of a cable-stayed bridge, the damages has been considered as a load variation without regard to its stiffness variation. The analyses of using these simplification could not calculate exact responses of damaged structure, though it may reserve a sufficient accuracy for the purpose of bridge design. This study suggests Gradual Bilinear Method (GBM) which simulate the damage responses of cable-stayed bridge considering the stiffness and mass variation, and develops an analysis program. The developed program is verified from the responses of a simple model. The responses of a existing cable-stayed bridge model are analyzed with respect to the fracture delay time and damage ratio. The results of this study can be used to develop and verify the highly accurate abnormal behavior detection algorithm for safety management of architecture/large structures.

• Steel and Composite Structures
• /
• v.31 no.6
• /
• pp.575-589
• /
• 2019

The main focus of this study is to numerically investigate the influence of strong earthquake and tsunami-induced wave impact on the response and behavior of a cable-stayed steel bridge with large caisson foundations, by assuming that the earthquake and the tsunami come from the same fault motion. For this purpose, a series of numerical simulations were carried out. First of all, the tsunami-induced flow speed, direction and tsunami height were determined by conducting a two-dimensional (2D) tsunami propagation analysis in a large area, and then these parameters obtained from tsunami propagation analysis were employed in a detailed three-dimensional (3D) fluid analysis to obtain tsunami-induced wave impact force. Furthermore, a fiber model, which is commonly used in the seismic analysis of steel bridge structures, was adopted considering material and geometric nonlinearity. The residual stresses induced by the earthquake were applied into the numerical model during the following finite element analysis as the initial stress state, in which the acquired tsunami forces were input to a whole bridge system. Based on the analytical results, it can be seen that the foundation sliding was not observed although the caisson foundation came floating slightly, and the damage arising during the earthquake did not expand when the tsunami-induced wave impact is applied to the steel bridge. It is concluded that the influence of tsunami-induced wave force is relatively small for such steel bridge with large caisson foundations. Besides, a numerical procedure is proposed for quantitatively estimating the accumulative damage induced by the earthquake and the tsunami in the whole bridge system with large caisson foundations.

• Structural Engineering and Mechanics
• /
• v.39 no.2
• /
• pp.187-206
• /
• 2011

This paper uses dynamic computer simulation techniques to develop and apply a multi-criteria procedure using non-destructive vibration-based parameters for damage assessment in truss bridges. In addition to changes in natural frequencies, this procedure incorporates two parameters, namely the modal flexibility and the modal strain energy. Using the numerically simulated modal data obtained through finite element analysis of the healthy and damaged bridge models, algorithms based on modal flexibility and modal strain energy changes before and after damage are obtained and used as the indices for the assessment of structural health state. The application of the two proposed parameters to truss-type structures is limited in the literature. The proposed multi-criteria based damage assessment procedure is therefore developed and applied to truss bridges. The application of the approach is demonstrated through numerical simulation studies of a single-span simply supported truss bridge with eight damage scenarios corresponding to different types of deck and truss damage. Results show that the proposed multi-criteria method is effective in damage assessment in this type of bridge superstructure.

• Journal of KIBIM
• /
• v.10 no.2
• /
• pp.21-28
• /
• 2020

As the number of aging bridges increases, more studies are being conducted on developing effective and reliable methods for the assessment and maintenance of bridges. With the advancement in new sensing systems and data learning techniques through AI technology, there is growing interests in how to evaluate bridges using these advanced techniques. This paper presents a CNN(Convolution Neural Network) deep learning based technique for evaluating the damage existence and for estimating the damage location in PSC bridges using static strain data. Simulation studies were conducted to investigate the proposed method with error analysis. Damage was simulated as the reduction in the stiffness of a finite element. A data learning model was constructed by applying the CNN technique as a type of deep learning. The damage status and its location were estimated using data set built through simulation. It was assumed that the strain gauges were installed in a regular interval under the PSC bridge girders. In order to increase the accuracy in evaluating damage, the squared error between the intact and measured strains are computed and applied for training the data model. Considering the damage occurring near the supports, the results of error analysis were compared according to whether strain data near the supports were included.

• Proceedings of the Korean Institute of Building Construction Conference
• /
• 2022.04a
• /
• pp.208-209
• /
• 2022

This study aims to analyze the risk factors caused by object damage and third-party damage loss in actual bridge construction based on past insurance premium payment data from major domestic insurers for bridge construction projects, and develop a quantitative loss prediction model. For the development of quantitative bridge construction loss model, the dependent variable was selected as the loss ratio, and the independent variable adopted 1) Technical factors: superstructure type, foundation type, construction method, and bridge length 2) Natural hazards: flood anf Typhoon, 3) Project information: total construction duration, total cost and ranking. Among the selected independent variables, superstructure type, construction method, and project period were shown to affect the ratio of bridge construction losses, while superstructure, foundation, flood and ranking were shown to affect the ratio of the third-party losses.

• Journal of the Korea institute for structural maintenance and inspection
• /
• v.24 no.6
• /
• pp.206-216
• /
• 2020

As the number of aging railway bridges in Korea increases, maintenance costs due to aging are increasing and continuous management is becoming more important. However, while the number of old facilities to be managed increases, there is a shortage of professional personnel capable of inspecting and diagnosing these old facilities. To solve these problems, this study presents an improved model that can detect Local damage to structures using machine learning techniques of AI technology. To construct a damage detection machine learning model, an analysis model of the bridge was set by referring to the design drawing of a non-ballasted plate-girder railroad bridge. Static strain data according to the damage scenario was extracted with the analysis model, and the Local damage index based on the reliability of the bridge was presented using statistical techniques. Damage was performed in a three-step process of identifying the damage existence, the damage location, and the damage severity. In the estimation of the damage severity, a linear regression model was additionally considered to detect random damage. Finally, the random damage location was estimated and verified using a machine learning-based damage detection classification learning model and a regression model.