• Journal of the Korean Society for Precision Engineering
• /
• v.14 no.4
• /
• pp.110-118
• /
• 1997

Multi-layer neural networks with error back-propagation algorithm have a great potential for identifying nonlinear systems with unknown characteristics. However, because they have a demerit that the speed of convergence is too slow, various methods for improving the training characteristics of backpropagition networks have been proposed. In this paper, a fuzzy division method is proposed to improve the convergence speed, which can find out an effective fuzzy division by the tuning of membership function and independently train each neural network after dividing the network model into several parts. In the simulations, the proposed method showed that the optimal fuzzy partitions could be found from the arbitray initial ones and that the convergence speed was faster than the traditional method without the fuzzy division.

• Proceedings of the KSR Conference
• /
• 2010.06a
• /
• pp.1596-1602
• /
• 2010

The government have plans to improve the railway transport capacity and transport hub for the sustainable national transport and logistics system. Specially, there are much efforts to improve transportation capacity such as high speed transportation of rail freight, enlargement of BT train, development of double stack train, etc. between railway transport hubs. If the transport capacity between railway logistics hubs is increased as planned, we must increase the handling capacity of railway hub terminals. But there are limits to enlarge the terminal infrastructure because of investment scale, location circumstances and urban development plans. To ensure the capacity, with the minimum required enlargement of infrastructure, it is necessary to extremely increase the efficiency of terminal operations. For improving the efficiency, we have to introduce the efficient terminal operation systems based on u-IT and operation optimize technologies. In this paper, we analyse the issues and problems of railway terminals(including ICD) and suggest the concept of intelligent railway terminal and the construction components of technology.

• Journal of the Korea Safety Management & Science
• /
• v.12 no.4
• /
• pp.175-181
• /
• 2010

The government have plans to improve the railway transport capacity and transport hub for the sustainable national transport and logistics system. Specially, there are much efforts to improve transportation capacity such as high speed transportation of rail freight, enlargement of BT train, development of double stack train, etc. between railway transport hubs. If the transport capacity between railway logistics hubs is increased as planned, we must increase the handling capacity of railway hub terminals. But there are limits to enlarge the terminal infrastructure because of investment scale, location circumstances and urban development plans. To ensure the capacity, with the minimum required enlargement of infrastructure, it is necessary to extremely increase the efficiency of terminal operations. For improving the efficiency, we have to introduce the efficient terminal operation systems based on u-IT and operation optimize technologies. In this paper, we analyse the issues and problems of railway terminals(including ICD) and suggest the concept of intelligent railway terminal and the construction components of technology.

• Proceedings of the KSR Conference
• /
• 2011.10a
• /
• pp.3201-3207
• /
• 2011

This paper reviewed wave propagation of train vibration based on the study of high speed railway soft ground section with pile slab construction. In a filed of railway, concrete track has been adapted in a railway construction. And in order to maintain its track, soil improving method was required to control residual settlement. Within many soft ground settlement prevention techniques, pile slab method has an effect of minimizing residual settlement of soft ground. This is possible using support embankment load method by construct pile slab or cap the upper soft ground. This paper reviewed vibration wave characteristic of soft ground section with pile slab using numerical analysis application through finite element analysis. Pile slab method is established between high stiffened soft ground and embankment this creates a possibility of vibration block or slab amplification. Thus analyzed of wave propagation was done with roadbed and structure property to confirm application performance of pile slab method of high speed railway structure.

• Tunnel and Underground Space
• /
• v.17 no.2 s.67
• /
• pp.152-164
• /
• 2007

Recently as increasing the amounts of cargoes and passengers, it is necessary to improving railway capacity and speed. So the constructions of improving the existing railway line have been advanced. Sometimes the new railway tunnel is built to adjacent the existing railway line. Furthermore the new tunnel might be built near the existing facility within the tunnel width. In this case, it should be analyzed the influence of existing tunnel and if it is necessary, it should be taken the appropriate counterplan. The major analysis contents are follows. One is the influence on the existing tunnel by a blasting and train vibration and the other is stability problem of the existing tunnel by excavation of new tunnel. Therefore, we peformed the following analysis. Refer to a domestic and foreign standard and paper, the permitting level of blasting vibration is decided and the excavation plan of the new tunnel are designed. The numerical analysis is performed about the stability of the existing tunnel and new tunnel. The influence of the train vibration on tunnel is analyzed by the empirical equation.

• Structural Engineering and Mechanics
• /
• v.75 no.4
• /
• pp.507-518
• /
• 2020

With the rapid development of rail transit, rail transit noise needs to be paid more and more attention. In order to accurately and effectively analyze the characteristics of low-frequency noise, a prediction model of vibration of box girder was established based on the hybrid FE-SEA method. When the train speed is 140 km/h, 200 km/h and 250 km/h, the vibration and noise of the box girder induced by the vertical wheel-rail interaction in the frequency range of 20-500 Hz are analyzed. Detailed analysis of the energy level, sound pressure contribution, modal analysis and vibration loss power of each slab at the operating speed of 140 km /h. The results show that: (1) When the train runs at a speed of 140km/h, the roof contributes more to the sound pressure at the far sound field point. Analyzing the frequency range from 20 to 500 Hz: The top plate plays a very important role in controlling sound pressure, contributing up to 70% of the sound pressure at peak frequencies. (2) When the train is traveling at various speeds, the maximum amplitude of structural vibration and noise generated by the viaduct occurs at 50 Hz. The vibration acceleration of the box beam at the far field point and near field point is mainly concentrated in the frequency range of 31.5-100 Hz, which is consistent with the dominant frequency band of wheel-rail force. Therefore, the main frequency of reducing the vibration and noise of the box beam is 31.5-100 Hz. (3) The vibration energy level and sound pressure level of the box bridge at different speeds are basically the same. The laws of vibration energy and sound pressure follow the rules below: web

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.59 no.4
• /
• pp.686-692
• /
• 2010

This paper analyzes the effect of the STATCOM on the improvement of the Fault Ride Through (FRT) capability of the fixed speed wind turbines(FSWTs). The steady-state models of the wind farm components, such as induction generator, capacitor bank, and the STATCOM, are developed based on the simplified equivalent circuit. Especially, the STATCOM is modeled as a controllable current source and a method that analytically determines the magnitude of the injection current is developed. For the quasi-steady-state(QSS) analysis, the steady-state model of the generator and STATCOM are merged with the dynamic model of drive train. The QSS simulation with the STATCOM shows that the STATCOM can enhance the FRT performance by improving the $W_r-T_e$ characteristics of the FSWTs.

• Journal of the Korean Institute of Illuminating and Electrical Installation Engineers
• /
• v.27 no.7
• /
• pp.95-100
• /
• 2013

In this paper, we propose an active controller for high-speed pantograph in order to improve the transient response. Electrical power is delivered from a catenary to the train via a pantograph and thus it is very important to regulate the contact force between catenary and pantograph. By regarding the catenary displacement as an unknown disturbance input and analyzing the frequency response from the disturbance to contract force. we present an active controller that utilizes the lead compensator and resonant controller. It is shown by the computer simulation that the substantial improvement in transient response can be achieved by the proposed controller.

• Journal of Korea Multimedia Society
• /
• v.24 no.11
• /
• pp.1552-1559
• /
• 2021

Convolution neural networks (CNNs) show notable performance in image processing and are used as representative core models. CNNs extract and learn features from large amounts of train dataset. In general, it has a structure in which a convolution layer and a fully connected layer are stacked. The core of CNN is the convolution layer. The size of the kernel used for feature extraction and the number that affect the depth of the feature map determine the amount of weight parameters of the CNN that can be learned. These parameters are the main causes of increasing the computational complexity and memory usage of the entire neural network. The most computationally expensive components in CNNs are fully connected and spatial convolution computations. In this paper, we propose a Fourier Convolution Neural Network that performs the operation of the convolution layer in the Fourier domain. We work on modifying and improving the amount of computation by applying the fast fourier transform method. Using the MNIST dataset, the performance was similar to that of the general CNN in terms of accuracy. In terms of operation speed, 7.2% faster operation speed was achieved. An average of 19% faster speed was achieved in experiments using 1024x1024 images and various sizes of kernels.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.19 no.12
• /
• pp.887-895
• /
• 2018

This paper presents a braking model that can be used to design the safety distance of a train control system and a train braking system to increase the volume of traffic. For the braking model, a train set (electric multiple unit composed 6 cars) was tested. The factors that can affect the braking characteristics include the friction coefficient, braking pressure, and regenerative braking. The braking pressure was classified into service and emergency braking and reflected the characteristics of the vehicle. The external force acting on the running railway car was tested in accordance with KS R 9217, and the running resistance of the train is presented in the form of a polynomial. The dynamic behavior of the train running on a straight flat line was simulated using UM 8.3. The results were validated with experimental data, and the results were reasonable. With the validated model, a stopping distance was determined according to the initial braking speed and compared with the deceleration braking model. In addition, a safety distance for the train control system could be changed according to the frictional coefficient limits. These results are expected to be useful for analyzing the dynamic behavior of trains, and for analyzing various railway environments and improving the braking performance.