Road surfaces should be maintained in excellent condition to ensure the safety of motorists. To this end, there exist various road-surface monitoring systems, each of which is known to have specific advantages and disadvantages. In this study, a smartphone-based dual-acquisition method system capable of acquiring images of road-surface anomalies and measuring the acceleration of the vehicle upon their detection was developed to explore the complementarity benefits of the two different methods. A road test was conducted in which 1896 road-surface images and corresponding three-axis acceleration data were acquired. All images were classified based on the presence and type of anomalies, and histograms of the maximum variations in the acceleration in the gravitational direction were comparatively analyzed. When the types of anomalies were not considered, it was difficult to identify their effects using the histograms. The differences among histograms became evident upon consideration of whether the vehicle wheels passed over the anomalies, and when excluding longitudinal anomalies that caused minor changes in acceleration. Although the image-based monitoring system used in this research provided poor performance on its own, the severity of road-surface anomalies was accurately inferred using the specific range of the maximum variation of acceleration in the gravitational direction.

Signs of functional loss due to the deterioration of structures are primarily identified from cracks occurring on the surface of structures, and continuous monitoring of structural cracks is essential for socially important structures. Recently, many structural crack monitoring technologies have been developed with the development of deep-learning artificial intelligence (AI). In this study, stacking ensemble learning was applied to predict the structural cracks more precisely. A semantic segmentation model was primarily used for crack detection using a deep learning AI model. We studied the crack-detection performance by training UNet, DeepLabV3, DeepLabV3+, DANet, and FCN-8s. Owing to the unsuitable crack segmentation performance of the FCN-8s, stacking ensemble learning was conducted with the remaining four models. Individual models yielded an intersection over union (IoU) score ranging from approximately 0.4 to 0.6 for the test dataset. However, when the metamodel completed with stacking ensemble learning was used, the IoU score was 0.74, indicating a high-performance improvement. A total of 1235 test images was acquired with drones on the sea bridge, and the stacking ensemble model showed an IoU of 0.5 or higher for 64.4% of the images.

Poor road-surface conditions pose a significant safety risk to vehicle operation, especially in the case of autonomous vehicles. Hence, maintenance of road surfaces will become even more important in the future. With the development of deep learning-based computer image processing technology, artificial intelligence models that evaluate road conditions are being actively researched. However, as the lighting conditions of the road surface vary depending on the weather, the model performance may degrade for an image whose brightness falls outside the range of the learned image, even for the same road. In this study, a semantic segmentation model with an autoencoder structure was developed for detecting road surface along with a CNN-based image preprocessing model. This setup ensures better road-surface crack detection by adjusting the image brightness before it is input into the road-crack detection model. When the preprocessing model was applied, the road-crack segmentation model exhibited consistent performance even under varying brightness values.

Geosynthetic-reinforced piled embankments (GRPEs) are very complex structures with three differently behaving inclusions; i.e., piles, geosynthetics and soils. Very careful experiments are needed to investigate the behaviors of these GRPEs. In this study, the results of full-scale experiments conducted on GRPEs with three different geosynthetic reinforcements (GRs) and on an unreinforced piled embankment (PE) are presented. In the experiments, the vertical load transported towards the model piles and the vertical displacements of the soft foam layer underneath the reinforced embankment were measured and compared with the calculation results obtained by the concentric arches model used in the Netherlands. The vertical loads measured in the unreinforced PE and one GRPE agree well with the theoretical values. However, those measured in the two other GRPEs were significantly lower than the theoretically predicted values. It was concluded that these discrepancies were caused by two weak points in the execution of the experiments: inappropriate GR fixating at the sides of the model in combination with significant unexpected compaction in the soft foam layer that originated from the compaction procedure. These factors should be considered carefully in future experimental research to attain a better understanding of the behaviors of GRPEs.

The shape of soil arch is a key parameter in modern design of piled embankment. Design guidelines for piled embankment in the Netherlands, Germany, and the United Kingdom have been updated in 2011 to consider the improved understanding of the arching mechanism. Recently in Korea a national research project on the design code of the geosynthetic-reinforced piled embankment is being conducted. As part of the project, a series of finite element simulations have been performed. Numerical study mainly focuses on the visualization of soil arch under various different parametric conditions. By taking the local extremes in the vertical distributions of the vertical stress obtained from numerical simulations, the shapes and sizes of the soil arch zone were estimated. Numerical results show that the size of the dome-shaped soil arch zone remains constant in variation of the cohesion and friction angle of the fill material. However, the stiffness of the soft material between piles has a significant influence on the height of the soil arch zone. For the sufficient low stiffness of the soft material, the height of the dome-shaped soil arch zone is approximately 42% total embankment height.

The modern approach to the piled embankment includes the basal reinforcement of geosynthetic layers. Current design guidelines for piled embankment in the Netherlands, Germany, and U.K. have been updated to accurately estimate the practical tensile strains of employed geosynthetics, whereas the analytical approaches were usually underestimated against the experiment and in-situ results. In this study, a series of finite element simulations concerning different types of soil-geosynthetics interaction were conducted to reveal the difference of frictional modeling method. The geosynthetic strains along the diagonal and orthogonal direction from the pile center toward to the other pile were obtained according to the loading condition. The completely different responses were observed with respect to the type of the frictional model.