• Proceedings of the Korean Society of Machine Tool Engineers Conference
• /
• 1995.10a
• /
• pp.60-63
• /
• 1995

The behavior of the work materials in the chip-tool interface in extremely high strain rates and temperatures is more that of viscous liquids than that of normal solid metals. In these circumstances the principles of fluid mechanics can be invoked to describe the metal flow in the neighborhood of the cutting edge. In the present paper an Eulerian finite element model is presented that simulates metal flow in the vicinity of the cutting edge when machining a low carbon steel with carbide cutting tool. The work material is assumed to obey visco-plastic (Bingham solid) constitutive law and Von Mises criterion. Heat generation is included in the model, assuming adiabatic conditions within each element. the mechanical and thermal properties of the work material are accepted to vary with the temperature. The model is based on the virtual work-stream function formulation, emphasis is given on analyzing the formation of the stagnant metal zone ahead of the cutting edge. The model predicts flow field characteristics such as material velocity effective stress and strain-rate distributions as well as built-up layer configuration

• Smart Structures and Systems
• /
• v.28 no.6
• /
• pp.779-789
• /
• 2021

Cracks in railway sleeper are an inevitable condition and has a significant influence on the safety of railway system. Although the technology of railway sleeper condition monitoring using machine learning (ML) models has been widely applied, the crack recognition accuracy is still in need of improvement. In this paper, a two-stage method using edge detection and convolutional neural network (CNN) is proposed to reduce the burden of computing for detecting cracks in railway sleepers with high accuracy. In the first stage, the edge detection is carried out by using the 3×3 neighborhood range algorithm to find out the possible crack areas, and a series of mathematical morphology operations are further used to eliminate the influence of noise targets to the edge detection results. In the second stage, a CNN model is employed to classify the results of edge detection. Through the analysis of abundant images of sleepers with cracks, it is proved that the cracks detected by the neighborhood range algorithm are superior to those detected by Sobel and Canny algorithms, which can be classified by proposed CNN model with high accuracy.

• Journal of Internet Computing and Services
• /
• v.17 no.3
• /
• pp.25-32
• /
• 2016

In this paper, we propose a method that is tracking an object in real time using particle filter and the observation model with edge. First of all, the proposed method defines the object to be tracked in the initial frame. Then, it generates the edge observation model for the object to be tracked and a set of particles. It calculates the weight by comparing the average of the middle distance in eight-way of particle filter edge model with that in edge observation model, and then updates the weight with the calculated value. After resampling particles using the updated weights, it estimates the current location of the tracked object. Finally, this paper demonstrates the performance of the stable tracking through comparison with the existing method by using a number of experimental data.

• Transactions of the Korean Society of Mechanical Engineers B
• /
• v.23 no.7
• /
• pp.831-840
• /
• 1999

In this work, an aerothermodynamic calculation model for cooled axial flow turbine blades with trailing edge ejection is suggested and a mean line performance analysis of a turbine stage with nozzle cooling is carried out. A unique model regarding the interaction between coolant and main gas is proposed, while existing correlations are adopted to predict viscous loss and blade outflow angle. The interactions considered are the heat transfer from main gas to coolant and the temperature and pressure losses by the mixing of two streams due to the trailing edge coolant ejection. For a stator blade without ejection, trailing edge loss calculated by the trailing edge analysis is compared with that calculated by loss correlation. The effect of heat transfer effectiveness of coolant passage on the mixing loss is analyzed. For a model turbine stage with nozzle cooling, parametric analyses are carried out to investigate the effect of main design variables(coolant mass flow ratio, temperature and ejection area) on the stage performance.

• KIPS Transactions on Software and Data Engineering
• /
• v.10 no.3
• /
• pp.109-114
• /
• 2021

GAN(Generative Adversarial Network) is an image generation model, which is composed of a generator network and a discriminator network, and generates an image similar to a real image. Since the image generated by the GAN should be similar to the actual image, a loss function is used to minimize the loss error of the generated image. However, there is a problem that the loss function of GAN degrades the quality of the image by making the learning to generate the image unstable. To solve this problem, this paper analyzes GAN-related studies and proposes an edge GAN(eGAN) using edge detection. As a result of the experiment, the eGAN model has improved performance over the existing GAN model.

• Tribology and Lubricants
• /
• v.36 no.6
• /
• pp.359-364
• /
• 2020

Numerical investigation of the groove trap effect with variation in the groove-edge radius of curvature is presented here. The trap effect is evaluated in a two-dimensional sliding bearing using computational fluid dynamics (CFD). This simulation is based on the discrete phase model (DPM) and standard k - ε turbulence model using commercial CFD software, FLUENT. The numerical results are evaluated by comparisons with streamlines and particle trajectories in the grooves. Grooves are applied to various lubrication systems to improve their lubrication characteristics, such as load carrying capacity increment, leakage reduction, frictional loss reduction, and preventing three-body abrasive wear due to trapping effect. This study investigates the grove trapping effect for various groove-edge radius of curvature values and Reynolds numbers. The particle is assumed to be made of steel, with a circular shape, and is injected as a single particle in various positions. One-way coupling is used in the DPM model because the single particle injection condition is applied. Further, the "reflect" condition is applied to the wall boundary and "escape" condition is used for the "pressure inlet" and "pressure outlet" boundaries. From the numerical results, the groove edge radius is found to influence the groove trap effect. Moreover, the groove trap effect is more effective when applying the groove edge radius.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.17 no.2
• /
• pp.77-83
• /
• 2022

In this paper, the two-stage object detection approach is proposed to implement a deep learning-based label inspection system on edge computing environments. Since the label printed on the products during the production process contains important information related to the product, it is significantly to check the label information is correct. The proposed system uses the lightweight deep learning model that able to employ in the low-performance edge computing devices, and the two-stage object detection approach is applied to compensate for the low accuracy relatively. The proposed Two-Stage object detection approach consists of two object detection networks, Label Area Detection Network and Character Detection Network. Label Area Detection Network finds the label area in the product image, and Character Detection Network detects the words in the label area. Using this approach, we can detect characters precise even with a lightweight deep learning models. The SF-YOLO model applied in the proposed system is the YOLO-based lightweight object detection network designed for edge computing devices. This model showed up to 2 times faster processing time and a considerable improvement in accuracy, compared to other YOLO-based lightweight models such as YOLOv3-tiny and YOLOv4-tiny. Also since the amount of computation is low, it can be easily applied in edge computing environments.

• Computers and Concrete
• /
• v.32 no.5
• /
• pp.499-511
• /
• 2023

Anchor channels are commonly used for façade, tunnel, and structural connections. These connections encounter various types of loadings during their service life, including high rate or impact loading. For anchor channels that are placed close and parallel to an edge and loaded in shear perpendicular to and towards the edge, the failure is often governed by concrete edge breakout. This study investigates the transverse shear behavior of the anchor channels under quasi-static and high rate loadings using a numerical approach (3D finite element analysis) utilizing a rate-sensitive microplane model for concrete as constitutive law. Following the validation of the numerical model against a test performed under quasi-static loading, the rate-sensitive static, and rate-sensitive dynamic analyses are performed for various displacement loading rates varying from moderately high to impact. The increment in resistance due to the high loading rate is evaluated using the dynamic increase factor (DIF). Furthermore, it is shown that the failure mode of the anchor channel changes from global concrete edge failure to local concrete crushing due to the activation of structural inertia at high displacement loading rates. The research outcomes could be valuable for application in various types of connection systems where a high rate of loading is expected.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.38 no.4
• /
• pp.422-433
• /
• 2001

In this paper, we propose a flew edge detection method based on water flow model, in which gradient image surface is considered as a 3-dimensional (3-D) geographical feature. The edges of the objects in the background can be detected by the large gradient magnitude areas and to make the edges immersed it is required to invert the gradient image. The proposed edge detector uses a water flow model based enhancement and locally adaptive thresholding technique applied to the inverted gradient image resulting in better noise performance. Computer simulations with a few synthetic and real images show that the Proposed method can extract edge contour effectively.

• Journal of Ship and Ocean Technology
• /
• v.12 no.1
• /
• pp.1-15
• /
• 2008

An edgetone is the discrete tone or narrow-band sound produced by an oscillating free shear layer, impinging on a rigid surface. In this paper, 2-dimensional edgetone to predict the frequency characteristics of the discrete oscillations of a jet-edge feedback cycle is presented using lattice Boltmznan model with 21 bits, which is introduced a flexible specific heat ratio y to simulate diatomic gases like air. The blown jet is given a parabolic inflow profile for the velocity, and the edges consist of wedges with angle 20 degree (for symmetric wedge) and 23 degree (for inclined wedge), respectively. At a stand-off distance w, the edge is inserted along the centerline of the jet, and a sinuous instability wave with real frequency is assumed to be created in the vicinity of the nozzle exit and to propagate towards the downward. Present results presented have shown in capturing small pressure fluctuating resulting from periodic oscillation of the jet around the edge. The pressure fluctuations propagate with the speed of sound. Their interaction with the wedge produces an irrotational feedback field which, near the nozzle exit, is a periodic transverse flow producing the singularities at the nozzle lips. It is found that, as the numerical example, satisfactory simulation results on the edgetone can be obtained for the complex flow-edge interaction mechanism, demonstrating the capability of the lattice Boltzmann model with flexible specific heat ratio to predict flow-induced noises in the ventilating systems of ship.