• Journal of the Korean Society for Railway
• /
• v.20 no.2
• /
• pp.196-202
• /
• 2017

A very long test track is required for high-speed operation test of the real-scale Linear Synchronous Motor (LSM) for ultra-high-speed trains. The required length results in huge construction cost and economic loss if any error occurs during development. Therefore, validation study of the LSM design technology using a low-cost small-scale model must be carried out in the early research stages. It is possible to deduce an optimal winding method for the armature and determine the mechanical properties of the LSM through a performance tester that applies a rotary-type small-scale LSM model. In addition, it is possible to utilize previous research on LSM control systems. Therefore, a basic design model, comprising a rotary-type LSM tester that meets the requirements for the propulsion of 600km/h-class ultra-high-speed trains, is derived in this study. Finally, an optimal model, which has a stable structure under the condition of 1500rpm or more high-speed rotation, is derived by electromagnetic and mechanical stiffness analysis.

• Journal of Software Assessment and Valuation
• /
• v.17 no.2
• /
• pp.47-57
• /
• 2021

Neuromorphic technology is proposed to complement the shortcomings of existing artificial intelligence technology by mimicking the human brain structure and computational process with hardware. NA-IDE has also been proposed for developing neuromorphic hardware-based IoT applications. To implement an SNN model in NA-IDE, commonly used input data must be transformed for use in the SNN model. In this paper, we implemented a neural coding method encoder component that converts image data into a spike train signal and uses it as an SNN input. The decoder component is implemented to convert the output back to image data when the SNN model generates a spike train signal. If the decoder component uses the same parameters as the encoding process, it can generate static data similar to the original data. It can be used in fields such as image-to-image and speech-to-speech to transform and regenerate input data using the proposed encoder and decoder.

• The Journal of the Convergence on Culture Technology
• /
• v.8 no.3
• /
• pp.469-475
• /
• 2022

To train the model of the deep learning-based single-speaker TTS system, a speech DB of tens of hours and a lot of training time are required. This is an inefficient method in terms of time and cost to train multi-speaker or personalized TTS models. The voice cloning method uses a speaker encoder model to make the TTS model of a new speaker. Through the trained speaker encoder model, a speaker embedding vector representing the timbre of the new speaker is created from the small speech data of the new speaker that is not used for training. In this paper, we propose a multi-speaker TTS system to which voice cloning is applied. The proposed TTS system consists of a speaker encoder, synthesizer and vocoder. The speaker encoder applies the d-vector technique used in the speaker recognition field. The timbre of the new speaker is expressed by adding the d-vector derived from the trained speaker encoder as an input to the synthesizer. It can be seen that the performance of the proposed TTS system is excellent from the experimental results derived by the MOS and timbre similarity listening tests.

• Wind and Structures
• /
• v.37 no.4
• /
• pp.303-314
• /
• 2023

In this study, two steady RANS turbulence models (SST k-ω and Realizable k-ε) and four unsteady turbulence models (URANS SST k-ω and Realizable k-ε, SST-SAS, and SST-IDDES) are evaluated with respect to their capacity to predict crosswind characteristics on high-speed trains (HSTs). All of the numerical simulations are compared with the wind tunnel values and LES results to ensure the accuracy of each turbulence model. Specifically, the surface pressure distributions, time-averaged aerodynamic coefficients, flow fields, and computational cost are studied to determine the suitability of different models. Results suggest that the predictions of the pressure distributions and aerodynamic forces obtained from the steady and transient RANS models are almost the same. In particular, both SAS and IDDES exhibits similar predictions with wind tunnel test and LES, therefore, the SAS model is considered an attractive alternative for IDDES or LES in the crosswind study of trains. In addition, if the computational cost needs to be significantly reduced, the RANS SST k-ω model is shown to provide relatively reasonable results for the surface pressures and aerodynamic forces. As a result, the RANS SST k-ω model might be the most appropriate option for the expensive aerodynamic optimizations of trains using machine learning (ML) techniques because it balances solution accuracy and resource consumption.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.16 no.12
• /
• pp.8187-8194
• /
• 2015

To accelerate a heavy roller coaster train with over 1G force, a lot of thrust is required and linear synchronous motor(LSM) as propulsion method is suitable for this kind of system. To increase the propulsion efficiency of LSM, precise and real-time position information of vehicle is required for accurate phase control. However, the discontinuous position information with relatively long time interval is usually transmitted from the hall-sensors on the track every magnet length. In this paper, the basic motor model based on traditional dq-axis equations is described and the motor dynamic model is produced by considering the cogging force and friction loss. To improve the position accuracy, the position estimator is also proposed for LSM control system. Simulations were performed to check the characteristics of the torque control system which includes the position estimator based on the motor model. Simulation results based on the linearized model show that this control system has an enough bandwidth and phase margin and the executed algorithm achieves an ideal effect to follow the real-time position signal. Therefore, the feasibility of position estimator is also confirmed.

• Journal of the Korea institute for structural maintenance and inspection
• /
• v.28 no.4
• /
• pp.37-47
• /
• 2024

This study proposes a track maintenance quantity estimation model that considers evolution of rail fatigue damage and ballast settlement based on actual maintenance data from the Gyeongbu high-speed railway, and revises the existing life cycle cost (LCC) model for railway track. Using this model, maintenance quantities and life cycle costs based on different track quality levels are evaluated and discussed. According to the results, it is confirmed that applying the track maintenance quantity estimation model that accounts for rail fatigue damage and ballast settlement allows us to reasonably estimate maintenance costs close to the actual data. The track quality coefficient significantly influences both rail and ballast maintenance quantities, with ballast maintenance having a greater impact than rail maintenance. Additionally, as train speed increases, both rail and ballast maintenance quantities rise. Moreover, a higher track quality coefficient leads to a steeper increase in maintenance quantities with increasing train speed. Consequently, LCC also exhibits a faster growth rate over time with higher track quality coefficients and faster train speeds, resulting from an increased proportion of maintenance costs.

• Proceedings of the Korean Geotechical Society Conference
• /
• 2006.03a
• /
• pp.1159-1164
• /
• 2006

In this paper an artificial neural network model is developed to estimate the unconfined compression strength of Deep Cement Mixing(DCM) treated soil. A database which consists of a number of unconfined compression test result compiled from 9 clay sites is used to train and test of the artificial neural network model. Developed neural network model requires water content of soil, unit weight of soil, passing percent of #200 sieve, weight of cement, w-c ratio as input variables. It is found that the developed artificial neural network model can predict more precise and reliable unconfined compression strength than the conventional empirical models.

• Journal of Institute of Control, Robotics and Systems
• /
• v.3 no.4
• /
• pp.398-405
• /
• 1997

This article presents a new model which is called Periodic Square-Wave(PSW) to describe the material flow of the periodic processes involving intermediate buffer. The material flows incoming into and outgoing from the intermediate buffer are assumed to be periodic square shaped. PSW model gives the same result as that of Economic Production Quantity(EPQ) model for determining optimal lot size of single stage batch storage system. However, for batch storage serial train system, PSW model gives a different optimal solution of about 6 % reduced total cost. PSW model provides the more accurate information on inventory and production system than the classical approach by maintaining simplicity and increasing computational burden.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2007.05a
• /
• pp.1910-1914
• /
• 2007

This paper employs a relatively new technique of Artificial Neural Network (ANN) to forecast water demand of Daegu city. The ANN model used in this study is a single hidden layer hierarchy model. About seventeen sets of historical water demand records and the values of their socioeconomic impact factors are used to train the model. Also other regression and time serious models are investigated for comparison purpose. The results present the ANN model can better perform the issue of urban water demand forecasting, and obtain the correlation coefficient of $R^2$ with a value of 0.987 and the relative difference less than 4.4% for this study.

• Journal of Industrial Technology
• /
• v.20 no.B
• /
• pp.95-103
• /
• 2000

A model trains must have similitude with its original model not only in shape but also in motion. Motion characteristics of a model train under considerations are maximum velocity in straight and circular tracks and stopping distance. Equations of motions are derived to obtain maximum speed and stopping distance based on the Newton's Second Law and the energy principal. To accurately predict traction and resistance force between wheel and rail. wheel slip, or creepage, is taken into consideration. To verify the equations of motion, various experiments have been carried out including measurement of gear efficiency, location of mass center, rolling resistance force, traction force, slip, maximum velocity and stopping distance. This paper addresses how the experiments are setup and carried out in detail. Also the results of experiments are compared with the analytical prediction, which showed good agreements with each other.