• Journal of the Korean Recycled Construction Resources Institute
• /
• v.9 no.2
• /
• pp.208-215
• /
• 2021

In this study, a customiz ed bridge system was developed for North Korea application. For the application of North Korea, the customized bridge system design, fabrication, and construction performance evaluation were performed using ultra-high performance concrete a compressive strength 120MPa or more and a direct tensile strength 7MPa or more. The comparison of the North Korean truck luggage load(30, 40, 55) and the Korean standard KL-510 load showed that cross-section increased as the load increased. Furthermore, a bridge with a span length of 30m was fabricated with ultra-high performance concrete for the construction performance evaluation. The evaluation of the load condition analysis was performed by a flexural test. The results showed that a bridge with a span length of 30m secured about 167% of sectional performance under initial cracking load conditions and about 134% of load bearing capacity under ultimate load conditions. As a result of economic analysis, the customized bridge system using ultra-high-performance concrete was less than about 11% of the upper construction cost compared to the steel composite girder bridge. Therefore, these results suggest that the price competitiveness can be secured when applying the ultra-high-performance concrete long-span bridge developed through this study.

• Smart Structures and Systems
• /
• v.29 no.1
• /
• pp.1-16
• /
• 2022

Despite recent breakthroughs in deep learning and computer vision fields, the pixel-wise identification of tiny objects in high-resolution images with complex disturbances remains challenging. This study proposes a modified U-net for tiny crack segmentation in real-world steel-box-girder bridges. The modified U-net adopts the common U-net framework and a novel Self-Attention-Self-Adaption (SASA) neuron as the fundamental computing element. The Self-Attention module applies softmax and gate operations to obtain the attention vector. It enables the neuron to focus on the most significant receptive fields when processing large-scale feature maps. The Self-Adaption module consists of a multiplayer perceptron subnet and achieves deeper feature extraction inside a single neuron. For data augmentation, a grid-based crack random elastic deformation (CRED) algorithm is designed to enrich the diversities and irregular shapes of distributed cracks. Grid-based uniform control nodes are first set on both input images and binary labels, random offsets are then employed on these control nodes, and bilinear interpolation is performed for the rest pixels. The proposed SASA neuron and CRED algorithm are simultaneously deployed to train the modified U-net. 200 raw images with a high resolution of 4928 × 3264 are collected, 160 for training and the rest 40 for the test. 512 × 512 patches are generated from the original images by a sliding window with an overlap of 256 as inputs. Results show that the average IoU between the recognized and ground-truth cracks reaches 0.409, which is 29.8% higher than the regular U-net. A five-fold cross-validation study is performed to verify that the proposed method is robust to different training and test images. Ablation experiments further demonstrate the effectiveness of the proposed SASA neuron and CRED algorithm. Promotions of the average IoU individually utilizing the SASA and CRED module add up to the final promotion of the full model, indicating that the SASA and CRED modules contribute to the different stages of model and data in the training process.