• Proceedings of the Korean Society For Composite Materials Conference
• /
• 2003.04a
• /
• pp.184-187
• /
• 2003

Complete prediction of second order permeability tensor for three dimensional circular braided preform is critical to understand the resin transfer molding process of composites. The permeability can be predicted by considering resin flow through the multi-axial fiber structure. In this study, permeability tensor for a 3-D circular braided preform is calculated by solving a boundary problem of a periodic unit cell. Flow field through the unit cell is obtained by using a 3-D finite volume method (FVM) and Darcy's law is utilized to obtain permeability tensor. Flow analysis for two cases that a fiber tow is regarded as impermeable solid and permeable porous medium is carried out respectively. It is found that the flow within the intra-tow region of the braided preform is negligible if inter-tow porosity is relatively high but the flow through the tow must be considered when the porosity is low. To avoid checkerboard pressure field and improve the efficiency of numerical computation, a new interpolation function for velocity variation is proposed on the basis of analytic solutions. Permeability of the braided preform is measured through a radial flow experiment and compared with the permeability predicted numerically.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.15 no.2
• /
• pp.51-60
• /
• 2020

Optical character recognition (OCR) has been studied for decades because it is very useful in a variety of places. Nowadays, OCR's performance has improved significantly due to outstanding deep learning technology. Thus, there is an increasing demand for commercial-grade but affordable OCR systems. We have developed a low-cost, high-performance OCR system for the industry with the cheapest embedded developer kit that supports GPU acceleration. To achieve high accuracy for industrial use on limited computing resources, we chose a state-of-the-art text recognition algorithm that uses an end-to-end deep learning network as a baseline model. The model was then improved by replacing the feature extraction network with the best one suited to our conditions. Among the various candidate networks, EfficientNet-B3 has shown the best performance: excellent recognition accuracy with relatively low memory consumption. Besides, we have optimized the model written in TensorFlow's Python API using TensorFlow-TensorRT integration and TensorFlow's C++ API, respectively.

• Transactions of the Korean Society of Mechanical Engineers B
• /
• v.28 no.8 s.227
• /
• pp.902-909
• /
• 2004

A steady-state Reynolds averaged Navier-Stokes simulation was conducted to investigate the distribution of the Reynolds stress tensor inside tip leakage vortex of a linear compressor cascade. Two different inlet flow angles ${\beta}=29.3^{\circ}$(design condition) and $36.5^{\circ}$(off-design condition) at a constant tip clearance size of $1\%$ blade span were considered. Classical methods of solid mechanics, applied to view the Reynolds stress tensor in the principal direction system, clearly showed that the high anisotropic feature of turbulent flow field was dominant at the outer part of tip leakage vortex near the suction side of the blade and endwall flow separation region, whereas a nearly isotropic turbulence was found at the center of tip leakage vortex. There was no significant difference in the anisotropy of the Reynolds normal stresses inside tip leakage vortex between the design and off-design condition.

• Fibers and Polymers
• /
• v.6 no.2
• /
• pp.131-138
• /
• 2005

A theoretical model is proposed in order to investigate rheological behavior of bubble suspension with large deformation. Theoretical constitutive equations for dilute bubble suspensions are derived by applying a deformation theory of ellipsoidal droplet [1] to a phenomenological suspension theory [2]. The rate of deformation tensor within the bubble and the time evolution of interface tensor are predicted by applying the proposed constitutive equations, which have two free fitting parameters. The transient and steady rheological properties of dilute bubble suspensions are studied for several capillary numbers (Ca) under simple shear flow and uniaxial elongational flow fields. The retraction force of the bubble caused by the interfacial tension increases as bubbles undergo deformation. The transient and steady relative viscosity decreases as Ca increases. The normal stress difference (NSD) under the simple shear has the largest value when Ca is around 1 and the ratio Of the first NSD to the second NSD has the value of 3/4 for large Ca but 2 for small Ca. In the uniaxial elongational flow, the elongational viscosity is three times as large as the shear viscosity like the Newtonian fluid.

• KSCI Review
• /
• v.23 no.2
• /
• pp.9-15
• /
• 2015

• Journal of Digital Convergence
• /
• v.16 no.5
• /
• pp.221-229
• /
• 2018

Machine learning and artificial intelligence are core technologies for the 4th industrial revolution. However, it is difficult for the general public to get familiar with those technologies because most people lack programming ability. Thus, we developed a Graphic User Interface(GUI) to overcome this obstacle. We adopted TensorFlow and used .Net of Microsoft for the develop. With this new GUI, users can manage data, apply algorithms, and run machine learning without coding ability. We hope that this development will be used as a basis for developing artificial intelligence in various fields.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2016.05a
• /
• pp.441-444
• /
• 2016

Peace on the Korean Peninsula is threatened by physical aggressions and cyber terrors such as nuclear tests, missile launchings, senior government officials' smart phone hackings and DDos attacks to banking systems. Cyber attacks such as vulnerability for the hackings, malware distributions are generally defended by passive defense through the detecting signs of first invasion and attack, data analysis, adding library and updating vaccine programs. In this paper the concept of security program based on Google TensorFlow machine learning ability to perform adding libraries and solving security vulnerabilities by itself is researched and proposed.

• International Journal of Internet, Broadcasting and Communication
• /
• v.13 no.4
• /
• pp.135-142
• /
• 2021

Estimating the locations of workers in a shipyard is beneficial for a variety of applications such as selecting potential forwarders for transferring data in IoT services and quickly rescuing workers in the event of industrial disasters or accidents. In this work, we propose a human movement stream processing system for estimating worker locations in shipyards based on Apache Spark and TensorFlow serving. First, we use Apache Spark to process location data streams. Then, we design a worker location prediction model to estimate the locations of workers. TensorFlow serving manages and executes the worker location prediction model. When there are requirements from clients, Apache Spark extracts input data from the processed data for the prediction model and then sends it to TensorFlow serving for estimating workers' locations. The worker movement data is needed to evaluate the proposed system but there are no available worker movement traces in shipyards. Therefore, we also develop a mobility model for generating the workers' movements in shipyards. Based on synthetic data, the proposed system is evaluated. It obtains a high performance and could be used for a variety of tasksin shipyards.

• Korea-Australia Rheology Journal
• /
• v.17 no.3
• /
• pp.99-110
• /
• 2005

This work presents results of finite element analysis of isothermal incompressible creeping viscoelastic flows with the tensor-logarithmic formulation of the Leonov model especially for the planar geometry with singular comers in the domain. In the case of 4:1 contraction flow, for all 5 meshes we have obtained solutions over the Deborah number of 100, even though there exists slight decrease of convergence limit as the mesh becomes finer. From this analysis, singular behavior of the comer vortex has been clearly seen and proper interpolation of variables in terms of the logarithmic transformation is demonstrated. Solutions of 4:1:4 contraction/expansion flow are also presented, where there exists 2 singular comers. 5 different types spatial resolutions are also employed, in which convergent solutions are obtained over the Deborah number of 10. Although the convergence limit is rather low in comparison with the result of the contraction flow, the results presented herein seem to be the only numerical outcome available for this flow type. As the flow rate increases, the upstream vortex increases, but the downstream vortex decreases in their size. In addition, peculiar deflection of the streamlines near the exit comer has been found. When the spatial resolution is fine enough and the Deborah number is high, small lip vortex just before the exit comer has been observed. It seems to occur due to abrupt expansion of the elastic liquid through the constriction exit that accompanies sudden relaxation of elastic deformation.

• Journal of the Chungcheong Mathematical Society
• /
• v.26 no.3
• /
• pp.647-656
• /
• 2013

Taking into account the flexoelectric effects, we consider a gradient flow of Landau-de Gennes energy which generalizes the Oseen-Frank energy. In this article, we discuss existence of weak solutions of the gradient flow in an appropriate function space.