Gitae Roh

The bridge deck is more vulnerable to deterioration than other structural components. This is due to its direct exposure to environmental factors such as vehicular loads, chloride ingress, and freeze–thaw cycles. The resulting accelerated degradation often results in a serviceability life that is shorter than the intended design life. However, the absence of standardized condition assessment methods coupled with clear definitions of remaining service life has limited the establishment of rational guidelines for repair and strengthening. In a bid to address this lack, this study focuses on PSC-I type bridges in South Korea, utilizing long-term field inspection data to analyze environmental, structural, and material factors—including reinforcement corrosion, chloride diffusion, and freeze–thaw actions. Environmental zoning was applied based on regional conditions, while structural zoning was performed according to load characteristics, thereby allowing the classification of deck regions into moment zones and cantilever sections. Machine learning models were employed to identify dominant deterioration mechanisms, with the validity of the zoning classification being evaluated via model accuracy and SHAP value analysis. Additionally, a regression-based approach was proposed to estimate the remaining service life of the bridge deck for each corrosion phase, thereby providing a quantitative framework for durability assessment and maintenance planning.

The bridge deck is more vulnerable to deterioration than other structural components due to its direct exposure to environmental factors such as vehicular loads, chloride ingress, and freeze–thaw cycles. This accelerated degradation often results in a serviceability life that is shorter than the intended design life. However, the absence of standardized condition assessment methods and clear definitions of residual service life has limited the establishment of rational guidelines for repair and strengthening. This study focuses on PSC-I type bridges in South Korea, utilizing long-term field inspection data to analyze environmental, structural, and material factors—including reinforcement corrosion, chloride diffusion, and freeze–thaw actions. Environmental zoning was applied based on regional conditions, while structural zoning was per-formed according to load characteristics, allowing classification of deck regions into moment zones and cantilever sections. Machine learning models were employed to identify dominant deterioration mechanisms, and the validity of the zoning classification was evaluated through model accuracy and SHAP value analysis. Additionally, a regression-based approach was proposed to estimate the residual service life of the bridge deck for each corrosion phase, providing a quantitative framework for durability assessment and maintenance planning.

Bridge slabs are critical structural components that directly sustain vehicle loads and generally have the shortest service life among bridge elements, leading to increased maintenance needs and costs. In many countries, damage and repair histories have been systematically recorded for over four decades. In this study, a digital twin framework for predicting the future performance of bridge slabs by integrating long-term inspection data was proposed. Historical 2D damage drawings were digitized using the YOLOv7 deep-learning model to extract the spatial coordinates of the damaged locations. Based on this data, eight representative damage states were defined to support the prediction of the service life. The damage and repair history was embedded into the 3D bridge models using a unique coding system to enable temporal and spatial tracking. As the corrosion of the reinforcement cannot be directly observed by visual inspection, its development and progression is estimated using empirical models. The digital twin concept is validated using historical inspection records to demonstrate its applicability to existing bridge slabs. The integration of cumulative deterioration data significantly improves the accuracy of the performance predictions and facilitates data-driven maintenance and rehabilitation strategies.

The growing adoption of off-site construction methods has increased the critical role of mobile cranes within the construction sector. This study develops a Construction Digital Twin (CDT) framework to optimize crane lifting positions and capacities for the installation of prefabricated bridge decks. By integrating 3D site modeling, Building Information Modeling (BIM), and crane simulations within the Unity game engine, the CDT overcomes the limitations of conventional 2D-based planning by providing a three-dimensional representation of site conditions. An exhaustive search method identifies optimal crane configurations, enhancing precision and efficiency. Simulation calibration using video analysis of real bridge deck installations aligns crane speed and cycle times with actual operations, improving reliability. Case studies demonstrate the CDT’s ability to reduce crane operation costs by 27% when employing a smaller capacity crane while maintaining operational efficiency. Additional DFA-focused simulations with varying deck dimensions revealed a potential 10% cost reduction by optimizing crane operations and deck design strategies. The CDT framework supports early-stage planning, reduces operational risks, and contributes to cost-effective and safer construction practices, offering a scalable solution adaptable to various construction scenarios.

A digital twin is a dynamic, real-time digital representation of a physical object or system. For existing bridges, this involves the ability to monitor, simulate, and predict the behavior of structural members under various conditions. The seamless delivery of information from design through to maintenance is crucial for developing an effective digital twin model. This paper defines the essential Building Information Modeling (BIM) data required for creating a digital twin of a structural member. During the maintenance phase, additional data such as inspection and repair history are recorded to enhance assessment accuracy. The paper proposes several models encompassing material properties, damage assessment, and key performance indicators to effectively define the digital twin. Critical information for evaluating a prestressed concrete member includes the residual prestressing effect and the internal corrosion of prestressing steels. The proposed digital twin concept was validated through actual assessment of existing bridge members, demonstrating its efficacy and reliability.

Structural health monitoring using various sensors has been widely employed to assess the structural conditions of bridges. In addition, the concept of a digital twin was introduced, which encompasses the life cycle information of a bridge and its real-time data acquisition and utilization. However, the obtained real-time data from sensors primarily reflect the global behavior of the system, making it challenging to identify the root causes of structural changes. For a highly reliable assessment of the global behavior of a bridge, previous history information, that is, a prerequisite model, is required. This study defines a baseline digital twin model (B-DTM) as the stage preceding real-time data utilization in digital twins. The B-DTM is structured into a pre-update phase, which involves the collection of members and system historical data, and a post-update phase, which focuses on model updating. For the case of model updating, due to the inherent complexity of bridge systems, identifying the global optimum for updating remains challenging. In the pre-update phase, a probabilistic approach to historical data such as member stiffness restricts the search domain for model updating, whereas, in the post-update phase, deflection, mode shapes, and natural frequencies derived from load test results representing the real bridge’s behavior are utilized to explore the global optimum solution. The proposed B-DTM was validated using collected data and load test results from a PSC-I girder bridge decommissioned after 45 years of service.

The shear connector of a steel composite bridge is designed by predicting fatigue life using the fatigue strength curves (S-N curve) based on push-out test results. The fatigue strength curves of the current design codes present only a linear relationship between the stress range and fatigue life on a log scale based on push-out experiment results. However, an alternative to the current empirical formula is necessary for the fatigue design of shear connections involving many detailed variations or high strength steel materials. This study collected and reanalyzed data from push-out fatigue tests to determine the factors influencing fatigue life and propose a machine learning-based fatigue life prediction model. The proposed machine learning model demonstrated an improvement in predictive performance of approximately 2 to 8 times compared to the existing design codes when evaluated against experimental data. Feature importance analysis based on the proposed model revealed that the stress range most significantly influenced fatigue life prediction. Model validation results indicated that the proposed model provided reliable predictions with accuracy and generalization performance. Moreover, it effectively accounted for uncertainty by incorporating features previously overlooked in existing design codes. Plans for fine-tuning pretrained models were also discussed.

Existing design codes for predicting the strength of stud shear connections in composite structures are limited when adapting to constant changes in materials and configurations. Machine learning (ML) models for predicting shear connection are often constrained by the number of input variables, resembling conventional design equations. Moreover, these models tend to overlook considerations beyond those directly comprising the connection. In addition, the data used in ML are often biased and limited in quantity. This study proposes a model using AutoML to automate and optimize the process for predicting the ultimate strength and deformation capacity of shear connections. The proposed model leverages a comprehensive dataset derived from experimental studies and finite element analyses, offering an advanced data-driven solution to overcome the limitations of traditional empirical equations. A digital twin model for the static design of pushout specimens was defined to replace existing empirical design codes. The digital twin model incorporates predictions of the geometry model, ultimate strength, and slip as input parameters and provides criteria for evaluating the limit state through a bilinear load–slip curve. This study advances predictive methodologies in structural engineering by emphasizing the importance of ML in addressing the dynamic and multifaceted nature of shear connection behaviors.

Globally, bridges are rapidly aging, and traditional maintenance approaches face significant challenges in terms of efficiency and cost. To overcome these challenges, considerable research has been conducted to introduce enhanced bridge management systems (BMSs) based on bridge information modeling (BrIM) from various perspectives. However, most studies have highlighted the advantages of BrIM, while neglecting the practical issues that potential users may encounter on existing bridges. The primary problem is digitizing existing bridges that have not yet adopted BrIM. The universal applicability of BrIM should be carefully considered from the perspective of national maintenance authorities managing thousands of bridges, because modeling based on commercial software is expected to be time-consuming and costly. Therefore, in this study, information and functional requirements were derived from interviews with stakeholders, including bridge owners, managers, and site inspectors. Based on this understanding, a data-driven modeling approach using basic bridge information was implemented, and an inventory code system was integrated to efficiently manage and utilize the data. Moreover, mapping and deep learning-based vectorization were considered for managing inspection information, and features for bridge assessment, dashboards, and reporting were incorporated to support decision-making. The developed BrIM demonstrated the potential for enhancing maintenance efficiency through a case study. Particularly, significant improvements were observed in mandatory documentation tasks, along with their investigation and analysis, as required by regulations. Additionally, efficient modeling and data management were achieved for the existing bridge.