• Journal of the Korea Concrete Institute
• /
• v.24 no.3
• /
• pp.293-303
• /
• 2012

Recently, as construction technology improved, concrete structures not only became larger, taller and longer but were able to perform various functions. However, if extreme loads such as impact, blast, and fire are applied to those structures, it would cause severe property damages and human casualties. Especially, the structural responses from extreme loading are totally different than that from quasi-static loading, because large pressure is applied to structures from mass acceleration effect of impact and blast loads. Therefore, the strain rate effect and damage levels should be considered when concrete structure is designed. In this study, the low velocity impact loading test of steel fiber reinforced concrete (SFRC) slabs including 0%~1.5% (by volume) of steel fibers, and strengthened with two types of FRP sheets was performed to develop an impact resistant structural member. From the test results, the maximum impact load, dissipated energy and the number of drop to failure increased, whereas the maximum displacement and support rotation were reduced by strengthening SFRC slab with FRP sheets in tensile zone. The test results showed that the impact resistance of concrete slab can be substantially improved by externally strengthening using FRP sheets. This result can be used in designing of primary facilities exposed to such extreme loads. The dynamic responses of SFRC slab strengthened with FRP sheets under low velocity impact load were also analyzed using LS-DYNA, a finite element analysis program with an explicit time integration scheme. The comparison of test and analytical results showed that they were within 5% of error with respect to maximum displacements.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.37 no.3
• /
• pp.199-208
• /
• 2019

As the number of available satellites increases and technology advances, image information outputs are becoming increasingly diverse and a large amount of data is accumulating. In this study, we propose a change detection method for high-resolution satellite images that uses transfer learning and a deep learning network to overcome the limit caused by insufficient training data via the use of pre-trained information. The deep learning network used in this study comprises convolutional layers to extract the spatial and spectral information and convolutional long-short term memory layers to analyze the time series information. To use the learned information, the two initial convolutional layers of the change detection network are designed to use learned values from 40,000 patches of the ISPRS (International Society for Photogrammertry and Remote Sensing) dataset as initial values. In addition, 2D (2-Dimensional) and 3D (3-dimensional) kernels were used to find the optimized structure for the high-resolution satellite images. The experimental results for the KOMPSAT-3A (KOrean Multi-Purpose SATllite-3A) satellite images show that this change detection method can effectively extract changed/unchanged pixels but is less sensitive to changes due to shadow and relief displacements. In addition, the change detection accuracy of two sites was improved by using 3D kernels. This is because a 3D kernel can consider not only the spatial information but also the spectral information. This study indicates that we can effectively detect changes in high-resolution satellite images using the constructed image information and deep learning network. In future work, a pre-trained change detection network will be applied to newly obtained images to extend the scope of the application.