• Journal of the Korean Society of Manufacturing Process Engineers
• /
• v.19 no.7
• /
• pp.7-15
• /
• 2020

Recently, the fourth industrial revolution has been presented as a new paradigm and additive manufacturing (AM) has become one of the most important topics. For this reason, process monitoring for each cross-sectional layer of additive metal manufacturing is important. Particularly, deep learning can train a machine to analyze, optimize, and repair defects. In this paper, image classification is proposed by learning images of defects in the metal cross sections using the convolution neural network (CNN) image labeling algorithm. Defects were classified into three categories: crack, porosity, and hole. To overcome a lack-of-data problem, the amount of learning data was augmented using a data augmentation algorithm. This augmentation algorithm can transform an image to 180 images, increasing the learning accuracy. The number of training and validation images was 25,920 (80 %) and 6,480 (20 %), respectively. An optimized case with a combination of fully connected layers, an optimizer, and a loss function, showed that the model accuracy was 99.7 % and had a success rate of 97.8 % for 180 test images. In conclusion, image labeling was successfully performed and it is expected to be applied to automated AM process inspection and repair systems in the future.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.35 no.8
• /
• pp.883-888
• /
• 2011

Laparoscopic surgery is being used in various surgical fields because it minimizes scarring. Laparoscopic operations require practical hand skills, so surgeons train on animals and via surgery training tool sets. However, these tool sets do not give the surgeon the sensation of touching real organs. A recently developed laparoscope simulator has a high friction force along the translational axis and a high gravity force along the pitch axis, and therefore it does not permit the operator to control his or her hands delecately. In the paper, the friction force along the axes is auumed to depend on the veolcity, and the gravity force on the angle and distance. We develop a compensation model that combines the gravity and friction force models.

• The Journal of the Korea Contents Association
• /
• v.16 no.3
• /
• pp.694-711
• /
• 2016

National Competency Standards (NCS) is a good resource for curriculum development and operations corresponding to the industrial damand. Recently, four-year colleges and universities are committed to a restructuring of the industry demand-driven training courses in order to strengthen competitiveness. However, NCS is focused to train the technical personnel in vocational training institutions(ex. College, Polytechnic University). Accordingly, NCS applications of four-year colleges and universities are hard to find. In this study, we propose a new model for NCS-based curriculum development and operations. Also, NCS was utilized to complement the existing curriculum. This paper includes the following contents; 1) NCS-based curriculum development process, 2) NCS-based course development and operation, 3) learner satisfaction analysis. Finally, this study provide practical implications to four-year colleges and universities to consider NCS application.

• Journal of Korea Multimedia Society
• /
• v.16 no.9
• /
• pp.1031-1043
• /
• 2013

Extracting hand region from images is the first part in the process to recognize hand posture and gesture interaction. Therefore, a good segmenting method is important because it determines the overall performance of hand recognition systems. Conventional hand segmentation researches were prone to changing illumination conditions or limited to the ability to detect multiple people. In this paper, we propose a robust technique based on the fusion of skin-color data and depth information for hand segmentation process. The proposed algorithm uses skin-color data to localize accurate seed location for region-growing from a complicated background. Based on the seed location, our algorithm adjusts each detected blob to fill up the hole region. A region-growing algorithm is applied to the adjusted blob boundary at the detected depth image to obtain a robust hand region against illumination effects. Also, the resulting hand region is used to train our skin-model adaptively which further reduces the effects of changing illumination. We conducted experiments to compare our results with conventional techniques which validates the robustness of the proposed algorithm and in addition we show our method works well even in a counter light condition.

• Journal of Communications and Networks
• /
• v.7 no.2
• /
• pp.157-170
• /
• 2005

The combination of multiple antennas and multi-carrier code division multiple-access (MC-CDMA) is a strong candidate for the downlink of the next generation mobile communications. The study of such systems in scenarios that model real-life trans-missions is an additional step towards an optimized achievement. We consider a realistic MIMO channel with two or four transmit antennas and up to two receive antennas, and channel state information (CSI) mismatches. Depending on the mobile terminal (MT) class, its number of antennas or complexity allowed, different data-rates are proposed with turbo-coding and asymptotic spectral efficiencies from 1 to 4.5 bit/s/Hz, using three algorithms developed within the European IST-MATRICE project. These algorithms can be classified according to the degree of CSI at base-station (BS): i) Transmit space-frequency prefiltering based on constrained zero-forcing algorithm with complete CSI at BS; ii) transmit beamforming based on spatial correlation matrix estimation from partial CSI at BS; iii) orthogonal space-time block coding based on Alamouti scheme without CSI at BS. All presented schemes require a reasonable complexity at MT, and are compatible with a single-antenna receiver. A choice between these algorithms is proposed in order to significantly improve the performance of MC-CDMA and to cover the different environments considered for the next generation cellular systems. For beyond-3G, we propose prefiltering for indoor and pedestrian microcell environments, beamforming for suburban macrocells including high-speed train, and space-time coding for urban conditions with moderate to high speeds.

• Transactions of the Korean Society of Automotive Engineers
• /
• v.12 no.4
• /
• pp.119-128
• /
• 2004

With the growing traffic density and increasing comfort requirements, the automation of the drive train will gain importance in vehicles. The automatic clutch actuation relieves the drivers especially in urban driving and stop-and-go traffic conditions. This paper describes the dynamic modeling of a clutch actuator and clutch spring. The dynamic model of the clutch system is developed using MATLAB/Simulink, and evaluated by experimental data using a test rig. This performance simulator is useful to develop the clutch-by-wire (CBW) system for an automated manual transmission (AMT). The electro-mechanical type CBW system is also implemented as an automatic clutch for AMT. The prototype of CBW system is designed and implemented systematically, which is composed of an electric motor, worm gear and slider-crank mechanism. The test rig is developed to perform the basic function test of the automatic clutch, and the developed prototype is validated by the experimental data on the test rig.

• Journal of the Korean Society for Precision Engineering
• /
• v.27 no.5
• /
• pp.36-47
• /
• 2010

The Korean Railroad Research Institute (KRRI) has developed the rubber tired AGT system (Model: K-AGT) between 1999 and 2005. The K-AGT is a light rail transit system does not require a driver and generally operates on an elevated railroad for transporting passengers. Accidents caused by driverless vehicles can severely affect social confidence, safety and economy therefore, it is very important to minimize the occurrences of such faults, and to accurately perform detailed maintenance tasks and thoroughly investigate the cause of any repeated failures. This research develops the web-based Preventive Maintenance (PM) system for the KAGT train system. The framework of the PM system is based on performing a reliability analysis and a failure mode effects analyses (FMEA) procedure on all the sub-systems in the K-AGT system. Out of the devices that have a low reliability, the high failure ranked devices are included high in the list for performing the overall maintenance plans. Through registration of historical failure data, the reliability indexes can be updated. Such a process is repeated continuously and can achieve very accurate predictions for device operational life times and failure rates. Therefore, this research describes the development of the overall PM system consists of a reliability analysis module, a failure mode effect analysis module, and maintenance request module.

• Journal of Welding and Joining
• /
• v.26 no.2
• /
• pp.85-91
• /
• 2008

In general, the quality of a welding process tends to vary with depending on the work environment or external disturbances. Hence, in order to achieve the desirable quality of welding, we should have the optimal welding condition that is not significantly affected by these changes in the environment or external disturbances. In this study, we used a dual response surface method in consideration of both the mean output variables and the standard deviation in order to optimize the V-groove arc welding process. The input variables for GMA welding process with the dual response surface are welding voltage, welding current and welding speed. The output variables are the welding quality function using the shape factor of bead geometry. First, we performed welding experiment on the interested area according to the central composite design. From the results obtained, we derived the regression model on the mean and standard deviation between the input and output variables of the welding process and then obtained the dual response surface. Finally, using the grid search method, we obtained the input variables that minimize the object function which led to the optimal V-groove arc welding process.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.2 no.1
• /
• pp.23-35
• /
• 2008

Mobile IP (MIP) is the solution supporting the mobility of Mobile Nodes (MNs), however, it is known to lack the support for NEtwork MObility (NEMO). NEMO manages situations when an entire network, composed of one or more subnets, dynamically changes its point of attachment to the Internet. NEMO Basic Support (NBS) protocol ensures session continuity for all the nodes in a mobile network, however, there exists a serious pinball routing problem. To overcome this weakness, there are many Route Optimization (RO) solutions such as Bi-directional Tunneling (BT) mechanism, Aggregation and Surrogate (A&S) mechanism, Recursive Approach, etc. The A&S RO mechanism is known to outperform the other RO mechanisms, except for the Binding Update (BU) cost. Although Improved Prefix Delegation (IPD) reduces the cost problem of Prefix Delegation (PD), a well-known A&S protocol, the BU cost problem still presents, especially when a large number of Mobile Routers (MRs) and MNs exist in the environment such as train, bus, ship, or aircraft. In this paper, a solution to reduce the cost of delivering the BU messages is proposed using a multicast mechanism instead of unicasting such as the traditional BU of the RO. The performance of the proposed multicast-based BU scheme is examined with an analytical model which shows that the BU cost enhancement is up to 32.9% over IPDbased, hence, it is feasible to predict that the proposed scheme could benefit in other NEMO RO protocols.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.16 no.4
• /
• pp.2911-2916
• /
• 2015

The elevated railway station, above which a train is passing, is vulnerable to noise and vibration compared to other station types. To better identify the vibration characteristics of the elevated railway station, the transferred vibration from approach bridges should be analyzed. In this paper, through experiments and simulations, the transfer characteristics of the vibration from approach bridges is analyzed. The study structure is Geomgok station and the anaylses are conducted using ABAQUS three dimensional numerical model. To identify the change in the transfer characteristics for various bearing types, the analyses are performed considering mechanical properties of bearing for railway bridges. The measurement is performed using the accelerometers attached to the approach bridges and the station structure along the passing path of trains.