Accurate seismic ground response analysis is crucial for the design and safety of civil infrastructure and establishing effective mitigation measures against seismic risks and hazards. This is a complex process due to the nonlinear soil properties and complicated underground geometries. As a simplified approach, the one-dimensional wave propagation model, which assumes that seismic waves travel vertically through a horizontally layered medium, is widely adopted for its reasonable performance in many practical applications. This study explores the potential of sequence deep learning models, specifically 1D convolutional neural networks (1D-CNNs), long short-term memory (LSTM) networks, and transformers, as an alternative for seismic ground response modeling. Utilizing ground motion data from the Kiban Kyoshin Network (KiK-net), we train these models to predict ground surface acceleration response spectra based on bedrock motions. The performance of the data-driven models is compared with the conventional equivalent-linear analysis model, SHAKE2000. The results demonstrate that the deep learning models outperform the physics-based model across various sites, with the transformer model exhibiting the smallest average prediction error due to its ability to capture long-range dependencies. The 1D-CNN model also shows a promising performance, albeit with occasional higher errors than the other models. All the data-driven models exhibit efficient computation times of less than 0.4 s for estimation. These findings highlight the potential of sequence deep learning approaches for seismic ground response modeling.

The purpose of a bridge maintenance strategy is to make effective decisions by evaluating current performance and predicting future conditions of the bridge. The social cost because of the rapid increase in the number of decrepit bridges. The current bridge maintenance system relies on traditional man-power-based methods, which determine the bridge performance by employing a material deterioration model, and thus shows uncertainty in predicting the bridge performance. In this study, a new type of performance degradation model is developed using the actual concrete deck condition index (or grade) data of the general bridge inspection history database (1995–2017) on the national road bridge of the bridge management system in Korea. The developed model uses the long short-term memory algorithm, which is a type of recurrent neural network, as well as layer normalization and label smoothing to improve the applicability of basic data. This model can express the discrete historical degradation indices in continuous form according to the service life. In addition, it enables the prediction of bridge performance by using only basic information about new and existing bridges.

Image-based inspection technologies involving various sensors and unmanned aerial vehicles are widely used for facility inspections. The level of data analysis technology required to process the acquired data algorithmically (e.g., image processing and machine learning) is also increasing. However, compared with their development rate, the applicability of new inspection technologies to actual bridges is low. In addition, only individual technologies (for inspecting specific deteriorations) are being developed; integrated inspection systems have been neglected. In this study, the bottom-up method (which systematizes the applications of a specific technology) is avoided; instead, several technologies are summarized and a system of preliminary frameworks is established using a top-down method, and the applicability of each technology is verified in a testbed. To this end, the utility of the initially constructed technical system was assessed for two bridges; then, a strong utility technology was selected and applied to an offshore bridge under extreme conditions. The data obtained from the inspection were accumulated in a database, and a 3D-type external inspection map was produced and applied in the subsequent inspection via virtual and augmented reality equipment. Through the system, it was possible to obtain cost-effective and objective bridge inspection images in extreme environments, and the applicability of various technologies was verified.

Bridge maintenance strategy is implemented to ensure that effective decisions are made based on the evaluation of the current performance and predicted future conditions of a bridge. The current bridge maintenance system relies on traditional manpower-based methods to determine bridge performance. However, the present techniques employ a material deterioration model that has uncertainty in predicting bridge performance. Moreover, the utilization of collected bridge inspection-related data is insignificant, and related research is lacking. Accordingly, a new type of bridge deterioration model is proposed using state performance data based on bridge inspection. To formulate the deterioration model, bridge condition inspection data accumulated over a long period were utilized. The data have been continuously updated since 1992 by the US Federal Highway Administration and consist of basic information and various influencing factors of bridges. The developed model uses the long short-term memory (LSTM) algorithm (a type of recurrent neural network) as well as layer normalization and label smoothing to improve the applicability of fundamental data. For the stable application of data, predicting the model performance for up to 30 years every 2 years is possible. By implementing the many-to-many type of the LSTM algorithm, the predicted probability of each grade derived for each sequence was weighted and averaged with the grade value to derive a continuous state grade result. Thus, the proposed model can express discrete historical degradation indices in continuous form according to the service life. In addition, it enables the prediction of bridge performance using only the fundamental information regarding new and existing bridges. For the effective use of basic data, an optimization model was derived using preprocessing and various regularization techniques. Additionally, a feed-forward deep learning model and stochastic model were developed using the same data. For performance assessment, a regression analysis evaluation method was applied, and comparative analysis was performed using the inspection data of an actual bridge. The use of a time-series model enabled the continuous and stable prediction of bridge performance.

When evaluating the fragility of structures in response to wind loads, vulnerability analyses are often conducted under intact conditions. Therefore, the actual strength of aged transmission towers may be compromised, resulting in severe damage. Especially for steel structures used over a long period in coastal areas, there is a potential for performance degradation due to corrosion. One of the high-voltage transmission towers, the 765 kV transmission tower, is taller than other towers, making it more vulnerable to strong winds in the event of corrosion. In this study, the structural performance degradation of 765 kV transmission towers in coastal regions based on their service life was investigated. Capacity distributions were provided considering the uncertainties in various parameters, such as the wind attack angle and material properties. A fragility assessment process that accounts for uncertainties in the wind conditions and aerodynamic parameters is proposed. Using the research results, we created limit-collapsed surfaces to evaluate the structural safety of transmission towers based on their service life, wind speed, and wind attack angle. The results showed a quantitative decrease in structural safety due to corrosion depending on the service life, with the most unfavorable wind attack angle being 0°. The proposed limit-collapsed surface can help efficiently evaluate structural conditions considering wind speed, wind attack angle, and service life. Hence, this study can serve as a basis for the structural evaluation of modern transmission towers to avoid power disruptions in major cities.

This paper presents a probabilistic method to predict fatigue crack growth for surface flaws in pipelines using a particle filtering method based on Bayes theorem. The random response of the fatigue behavior is updated continuously as measured data are accumulated by the particle filtering method. Fatigue crack growth is then predicted through an iterative process in which particles with a high probability are reproduced more during the update process, and particles with a lower probability are removed through a resampling procedure. The effectiveness of the particle filtering method was confirmed by controlling the depth and length direction of the cracks in the pipeline and predicting crack growth in one- and two-dimensional cases. In addition, the fatigue crack growth and remaining service life with a 90% confidence interval were predicted based on the findings of previous studies, and the relationship between the fatigue crack growth rate and the crack size was explained through the Paris’ law, which represents fatigue crack growth. Finally, the applicability of the particle filtering method under different diameters, aspect ratios, and materials was investigated by considering the negative correlation between the Paris’ law parameters.