• Journal of the Korean Society for Precision Engineering
• /
• v.32 no.12
• /
• pp.1073-1080
• /
• 2015

A drive shaft is used to transmit torque and rotation through the connection of components of a drive train. Recently, a monobloc drive shaft without welding regions is developed to improve the safety of the drive shaft. The drive shaft bears the shear stress induced by torque. The objective of this paper is to investigate into the structural safety of a monobloc tubular drive shaft subjected to torque. Elasto-plastic finite element (FE) analysis is performed to estimate the deformation behavior of the drive shaft and stress-strain distribution in the drive shaft. Several techniques are used to create finite element (FE) model of the monobloc tubular drive shaft subjected to torque. Through the comparison of the results of FE analyses with those of experiments from the viewpoint of rotational angle, appropriate correction coefficients for different load conditions are estimated. The safety of the tubular drive shaft is examined using the results of FE analyses for different load conditions. Finally, it is noted that the designed tubular drive shaft has a sufficient structural safety.

• Journal of Electrical Engineering and Technology
• /
• v.12 no.6
• /
• pp.2411-2418
• /
• 2017

This study focuses on the effects of using open stator slots in an interior permanent magnet traction motor with a magnetic slot wedge design in order to increase the power density at its base speed. In addition, such a configuration reduces the torque ripple under field-weakening conditions. Five different wedge models were selected, each of which was evaluated using a finite element analysis (FEA). Based on the initial model, we designed magnetic slot wedges for maximum back-EMF and minimum cogging torque. In addition, the d-q axis inductance was slightly altered due to the magnetic slot wedges. Finally, we analyzed the performance of a traction machine under field weakening control. Moreover, we have outlined the requirements for an ideal magnetic slot wedge design.

• Proceedings of the Korean Society for Bioinformatics Conference
• /
• 2003.10a
• /
• pp.133-138
• /
• 2003

The prediction of protein secondary structure has been an important bioinformatics tool that is an essential component of the template-based protein tertiary structure prediction process. It has been known that the predicted secondary structure information improves both the fold recognition performance and the alignment accuracy. In this paper, we describe several novel ideas that may improve the prediction accuracy. The main idea is motivated by an observation that the protein's structural information, especially when it is combined with the evolutionary information, significantly improves the accuracy of the predicted tertiary structure. From the non-redundant set of protein structures, we derive the 'potential' parameters for the protein secondary structure prediction that contains the structural information of proteins, by following the procedure similar to the way to derive the directional information table of GOR method. Those potential parameters are combined with the frequency matrices obtained by running PSI-BLAST to construct the feature vectors that are used to train the support vector machines (SVM) to build the secondary structure classifiers. Moreover, the problem of huge model file size, which is one of the known shortcomings of SVM, is partially overcome by reducing the size of training data by filtering out the redundancy not only at the protein level but also at the feature vector level. A preliminary result measured by the average three-state prediction accuracy is encouraging.

• Korean Institute of Interior Design Journal
• /
• no.38
• /
• pp.182-191
• /
• 2003

Until now, the carriage's design has been performed by built-carriage engineers in urban railway company without the notion of railway design. Furthermore, there is no prominent change the shape of exterior and interior design between the 1970's trains and the latest one. In terms of the notion of interior space, there are a lot of differences between Oriental and Western, also region of each countries. Especially, Among Orientals, Korean is not good at utilizing the small space and react effectively as compared to Japanese. Therefore, the interior space of public transportation needs to be relatively developed to highly reasonable level in Korea. The purpose of this paper is to apply vernacular design elements for developing interior design in Korean lightrail, which is the next generation public transportation. In order to develope ideal interior design, the interior layout in carriage considers the emotional aspect as well as functional one. Also, the research of vernacular design in urban train can provide national character and traditional design and can make a success in a practical use and a visual effect. This study focused on the application of vernacular design elements for developing the design-processed model will be proposed the outline of interior layout and the shape of interior trims in the public transportation in Korea.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.11
• /
• pp.5427-5445
• /
• 2019

While deep neural networks have achieved remarkable performance in representation learning, a huge amount of labeled training data are usually required by supervised deep models such as convolutional neural networks. In this paper, we propose a new representation learning method, namely generative adversarial networks (GAN) based bagging deep convolutional autoencoders (GAN-BDCAE), which can map data to diverse hierarchical representations in an unsupervised fashion. To boost the size of training data, to train deep model and to aggregate diverse learning machines are the three principal avenues towards increasing the capabilities of representation learning of neural networks. We focus on combining those three techniques. To this aim, we adopt GAN for realistic unlabeled sample generation and bagging deep convolutional autoencoders (BDCAE) for robust feature learning. The proposed method improves the discriminative ability of learned feature embedding for solving subsequent pattern recognition problems. We evaluate our approach on three standard benchmarks and demonstrate the superiority of the proposed method compared to traditional unsupervised learning methods.

• Steel and Composite Structures
• /
• v.14 no.4
• /
• pp.367-377
• /
• 2013

Damage in structures often leads to failure. Thus it is very important to monitor structures for the occurrence of damage. When damage happens in a structure the consequence is a change in its modal parameters such as natural frequencies and mode shapes. Artificial Neural Networks (ANNs) are inspired by human biological neurons and have been applied for damage identification with varied success. Natural frequencies of a structure have a strong effect on damage and are applied as effective input parameters used to train the ANN in this study. The applicability of ANNs as a powerful tool for predicting the severity of damage in a model steel girder bridge is examined in this study. The data required for the ANNs which are in the form of natural frequencies were obtained from numerical modal analysis. By incorporating the training data, ANNs are capable of producing outputs in terms of damage severity using the first five natural frequencies. It has been demonstrated that an ANN trained only with natural frequency data can determine the severity of damage with a 6.8% error. The results shows that ANNs trained with numerically obtained samples have a strong potential for structural damage identification.

• Structural Monitoring and Maintenance
• /
• v.4 no.2
• /
• pp.115-131
• /
• 2017

Classical flutter of wind turbine blades indicates a type of aeroelastic instability with fully attached boundary layer where a torsional blade mode couples to a flapwise bending mode, resulting in a mutual rapid growth of the amplitudes. In this paper the monitoring problem of onset of flutter is investigated from a detection point of view. The criterion is stated in terms of the exceeding of a defined envelope process of a specific maximum torsional vibration threshold. At a certain instant of time, a limited part of the previously measured torsional vibration signal at the tip of blade is decomposed through the Empirical Mode Decomposition (EMD) method, and the 1st Intrinsic Mode Function (IMF) is assumed to represent the response in the flutter mode. Next, an envelope time series of the indicated modal response is obtained in terms of a Hilbert transform. Finally, a flutter onset criterion is proposed, based on the indicated envelope process. The proposed online flutter monitoring method provided a practical and direct way to detect onset of flutter during operation. The algorithm has been illustrated by a 907-DOFs aeroelastic model for wind turbines, where the tower and the drive train is modelled by 7 DOFs, and each blade by means of 50 3-D Bernoulli-Euler beam elements.

• Geomechanics and Engineering
• /
• v.12 no.4
• /
• pp.579-593
• /
• 2017

Geosynthetic reinforced soil retaining walls can be employed as railway embankments to carry large static and dynamic train loads, but very few studies can be found in the literature that investigate their dynamic behavior under simulated wheel loading. A large-scale dynamic test on a reinforced soil railway embankment was therefore carried out. The model embankment was 1.65 meter high and designed to have a soilbag facing. It was reinforced with HDPE geogrid layers at a vertical spacing of 0.3 m and a length of 2 m. The dynamic test consisted of 1.2 million cycles of harmonic dynamic loading with three different load levels and four different exciting frequencies. Before the dynamic loading test, a static test was also carried out to understand the general behavior of the embankment behavior. The study indicated the importance of loading frequency on the dynamic response of reinforced soil railway embankment. It also showed that toe resistance played a significant role in the dynamic behavior of the embankment. Some limitations of the test were also discussed.

• Journal of the Korean Society of Systems Engineering
• /
• v.10 no.1
• /
• pp.43-48
• /
• 2014

The door system for railway vehicles is the critical device directly influences on safety and satisfaction of passengers, Recently, electrical type of passenger door system is widely used for EMU type train instead of pneumatic type of passenger door system. The estimation of MTBF and failure rates for electrical type door system is essential. The manufacturor simply provides intrinsic reliability data for the railway operator. But actual reliability data based on operation and maintenance data is not complying with intrinsic reliability. In this study, operation and failure data associated with electrical door system were analyzed in order to determine actual MTBF and failure data. Intrinsic reliability data and service reliability data were studied to finallize much more practical and reliable actual reliability. Relax 2011 was used to predict intrinsic reliability and 217Plus model was also used to estimate of actual reliability data based on field data. Furthermore, it is necessary to keep studying on reliability prediction methodology and applying it in the field and doing research on improvement of reliability through feedback as well.

• Proceedings of the KOSOMBE Conference
• /
• v.1997 no.05
• /
• pp.398-401
• /
• 1997

The EMG signal of spinal cord injured patient is very feeble because that the information from central nervous system is not sufficiently transmitted to molter neuron or muscle fiber. Therefore the observer can not observe contraction and relaxation movement of muscle from the raw EMG signal. In this paper, we propose the muscle contraction and relaxation pattern analysis method of spinal cord injured patient whose EMG signal is composed of the sum of motor unit action potential train with additive white Gaussian noise and impulsive noise. From the EMG model, we denoise impulsive noise using median filter which is a kind of nonlinear filter and the output of median filter is transformed to wavelet transform domain for denoising additive white Gaussian noise using threshold level removal technique. As a result, we can obtain the clear contraction and relaxation pattern.