• Proceedings of the Korean Society for Noise and Vibration Engineering Conference
• /
• 2004.05a
• /
• pp.366-371
• /
• 2004

For the reduction and efficient management of railway noise, first of all prediction of railway noise is necessarily requisted. At home and abroad many studies for prediction of raiiway nearby noise have been accomplished. But it is impossible to predict easily and exactly for the Korean Railway, because the acoustic powers for each rolling stock operated in Korea have not been built yet. So in this study, prediction model equation for environmental noise for Korean rolling stock Mugungwha was suggested using SEL of engine and rolling noise component separately. In this prediction model, the number of car, distance from the rail can be considered. Finally for the validation of prediction nlodel equation, the predicted Leq was compared to the measured Leq.

• Transactions of the Korean Society for Noise and Vibration Engineering
• /
• v.21 no.5
• /
• pp.461-467
• /
• 2011

This study aims to create a numerical analysis model which can investigate the dynamic interaction between pantograph and overhead contact wire used for a high-speed railway vehicle, and validate the simulation results according to EN 50318 standard. Finite element analysis models of pantograph and overhead contact line are created using SAMCEF, a commercial FE analysis program. The mean, standard deviation, maximum and minimum values of contact forces are obtained. The simulation results are validated according to EN 50318, and the possibility of simulating the collecting characteristic of an actual pantograph system by using the developed model is discussed.

• Transactions of the Korean Society of Mechanical Engineers
• /
• v.19 no.7
• /
• pp.1597-1603
• /
• 1995

A prediction model on forward slip has been developed for presetting rolling speed of each finish mill stand in the continuous hot strip roduction. Those factors such as neutral point, friction coefficient, volume fractions undergoing width spread, shape of deformation zone at each side of entry and delivery of the rolls were taken into account. To reduce the speed unbalance between adjacent stands a refining method of adjusting friction coefficient has also been developed. On-line application of the model showed a good agreement in rolling speeds between the predictions and the actual measurements, and gave an outstanding improvement in the travelling stability of strip passing through the finishing mill train.

• Journal of Welding and Joining
• /
• v.31 no.3
• /
• pp.44-48
• /
• 2013

Artificial neural network (ANN) model is applied to predict arc welding process window for automotive steel plate. Target weldment was various automotive steel plate combination with lap fillet joint. The accuracy of prediction was evaluated through comparison experimental result to ANN simulation. The effect of ANN variables on the accuracy is investigated such as number of hidden layers, perceptrons and transfer function type. A static back propagation model is established and tested. The result shows comparatively accurate predictability of the suggested ANN model. However, it restricts to use nonlinear transfer function instead of linear type and suggests only one single hidden layer rather than multiple ones to get better accuracy. In addition to this, obvious fact is affirmed again that the more perceptrons guarantee the better accuracy under the precondition that there are enough experimental database to train the neural network.

• Journal of Information Processing Systems
• /
• v.8 no.2
• /
• pp.301-314
• /
• 2012

In this paper, two new approaches to align English-Arabic sentences in bilingual parallel corpora based on the Multi-Class Support Vector Machine (MSVM) and the Hidden Markov Model (HMM) classifiers are presented. A feature vector is extracted from the text pair that is under consideration. This vector contains text features such as length, punctuation score, and cognate score values. A set of manually prepared training data was assigned to train the Multi-Class Support Vector Machine and Hidden Markov Model. Another set of data was used for testing. The results of the MSVM and HMM outperform the results of the length based approach. Moreover these new approaches are valid for any language pairs and are quite flexible since the feature vector may contain less, more, or different features, such as a lexical matching feature and Hanzi characters in Japanese-Chinese texts, than the ones used in the current research.

• Journal of the Korean Society for Railway
• /
• v.3 no.2
• /
• pp.43-50
• /
• 2000

The corrugated panels are the prime candidate structure for the floor, roof and wall of Korean high speed train. The equivalent continuum modeling approach panels can be used for the efficient design and evaluation of their structural characteristics. The equivalent continuum models, derived from the true complex corrugated panels, should have the same structural behavior as the original structures have. This paper briefly reviews three representative continuum modeling methods: the static analysis method and two plate-models based on modal analysis methods (MAM). These methods are evaluated through some numerical examples by comparing the natural frequencies and static deflections. It is observed that the plate-model based on Rayleigh-Ritz method seems to provide the best results when used in conjunction with the cantilever-type boundary conditions. The equivalent elastic constants of various corrugated panels, depending on the changes in their configurations, are tabulated for efficient use in structural design.

• Proceedings of the KSR Conference
• /
• 2003.10c
• /
• pp.265-271
• /
• 2003

System engineering is one of the most important research topics in railway system for developing new railway system or improving existed system. The system engineering methods have been applied to innovate railway system. The system engineering activities, which are requirement analysis, functional analysis, system synthesis and analysis, sometimes requires longtime and tiresome works to fix some ideas level into some concrete forms. The system engineering using objected oriented method relieves the hard works of system engineering and clarifies the system engineering objects from its ambiguities. In this paper, we presented requirement model, analysis model and design model using objected oriented approach and showed the consistency of the system engineering work with an example of Automatic Train Control System.

• Phonetics and Speech Sciences
• /
• v.9 no.2
• /
• pp.95-101
• /
• 2017

This paper proposes a new method to train Deep Neural Network (DNN)-based acoustic models for speech recognition of native and foreign speakers. The proposed method consists of determining multi-set state clusters with various acoustic properties, training a DNN-based acoustic model, and recognizing speech based on the model. In the proposed method, hidden nodes of DNN are shared, but output nodes are separated to accommodate different acoustic properties for native and foreign speech. In an English speech recognition task for speakers of Korean and English respectively, the proposed method is shown to slightly improve recognition accuracy compared to the conventional multi-condition training method.

• KIEE International Transactions on Power Engineering
• /
• v.5A no.3
• /
• pp.235-243
• /
• 2005

Line constants of the catenary system are estimated. The harmonic current that the Korean Train Express (KTX) injects into the catenary is measured to precisely analyze the harmonic effects. The Korean high-speed railway system is modeled by estimated and measured results. The system model is applied for predicting the harmonic effects. The simulation results from the system model are compared to field test data concerning the total harmonic distortion (THD). The reliability of the system model is verified.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.7 no.2
• /
• pp.182-187
• /
• 2006

This paper proposes a method for boundary recognition of named entity using hidden markov model and ontology information of biological named entity. We uses smoothing method using 31 feature information of word and hierarchical information to alleviate sparse data problem in HMM. The GENIA corpus version 2.1 was used to train and to experiment the proposed boundary recognition system. The experimental results show that the proposed system outperform the previous system which did not use ontology information of hierarchical information and smoothing technique. Also the system shows improvement of execution time of boundary recognition.