• Title/Summary/Keyword: multi-train

Search Result 345, Processing Time 0.037 seconds

Nose Shape Optimization of the High-Speed Train for the Speed-up in Tunnel (터널 주행속도 향상을 위한 고속열차 전두부 형상 최적화)

  • Ku, Yo-Cheon;Yun, Su-Hwan;Rho, Joo-Hyun;Kim, Kyu-Hong;Lee, Dong-Ho;Kwon, Hyeok-Bin
    • Proceedings of the KSR Conference
    • /
    • 2008.06a
    • /
    • pp.2207-2212
    • /
    • 2008
  • The next generation of Korean high-speed train under development will be designed for the maximum operating speed of 350km/h and maximum speed of 400km/h. This high-speed operation may cause the noise and vibration problems around tunnel exit due to the higher micro-pressure wave than present level. In this study, the nose shape optimization was conducted for the countermeasure against these problems. Axi-symmetric solver was used for numerical simulation, and response surface was used for efficiency of optimization process. Also the multi-step optimization was conducted to find out more accurate optimal shape. Through these analysis and optimization, it was found out that the optimal nose shapes for minimization of micro-pressure wave are definitely different along the nose length variation. And the mechanism of micro-pressure wave reduction was closely investigated by the analysis of generation process of compression wave in tunnel. The results are expected to be used as design guideline for performance improvement of the next generatin of Korean high-speed train.

  • PDF

Process Design of Multi-Step Wire Drawing using Artificial Neural Network (인공신경망을 이용한 다단 인발 공정 설계)

  • Kim, Dong-Hwan;Kim, Dong-Jin;Kim, Byeong-Min
    • Transactions of Materials Processing
    • /
    • v.7 no.2
    • /
    • pp.127-138
    • /
    • 1998
  • Process design of multi-step wire drawing process, conducted by means of finite element analysis and ANN(Artificial Neural Network) has been considered. The investigated problem involves the ade-quate selection of the drawing die angle and the correspondent reduction rate in the condition of desired initial and final diameter. Combinations of the process parameters which are used in finite ele-ment simulation are selected by using the orthogonal array. Also the orthogonal array. Also the orthogonal array and the results of finite element simulation which are related to the process energy are used as train data of ANN. In this study it is shown that the application of new technique using ANN and Othogonal array table to the process design of metal forming process is useful method.

  • PDF

Shifting Algorithm and Response Characteristics of Torque Split Multi-Pass CVT (토크 분배방식 다경로 CVT의 변속 알고리듬과 응답특성)

  • 성덕환;김현수
    • Transactions of the Korean Society of Mechanical Engineers
    • /
    • v.18 no.11
    • /
    • pp.2817-2824
    • /
    • 1994
  • A torque split type multi-pass CVT(MPC) system consiting of CVT and planetary gear train with 4 clutches was suggested to overcome the inherent inferior acceleration performance of CVT. Also, a shifting algorithm of MPC was suggested for the two driving modes : (1) power mode and (2) economy mode. By using the shifting algorithm and the MPC vehicle dynamic model, numerical simulations were performed to estimate the performance of the MPC vehicle. Simulation results showed that comparing the performance of the conventional 4-speed automatic transmission, an improvement in acceleration can be obtained by MPC for the power mode and 31% improvement in fuel economy for the economy mode.

Hydrological Modelling of Water Level near "Hahoe Village" Based on Multi-Layer Perceptron

  • Oh, Sang-Hoon;Wakuya, Hiroshi
    • International Journal of Contents
    • /
    • v.12 no.1
    • /
    • pp.49-53
    • /
    • 2016
  • "Hahoe Village" in Andong region is an UNESCO World Heritage Site. It should be protected against various disasters such as fire, flooding, earthquake, etc. Among these disasters, flooding has drastic impact on the lives and properties in a wide area. Since "Hahoe Village" is adjacent to Nakdong River, it is important to monitor the water level near the village. In this paper, we developed a hydrological modelling using multi-layer perceptron (MLP) to predict the water level of Nakdong River near "Hahoe Village". To develop the prediction model, error back-propagation (EBP) algorithm was used to train the MLP with water level data near the village and rainfall data at the upper reaches of the village. After training with data in 2012 and 2013, we verified the prediction performance of MLP with untrained data in 2014.

The study on efficient transport system in Circle Yellow-Sea region using rail & sea multi transport system (철도-해운 복합운송 시스템을 이용한 환황해권 수송 효율화 연구)

  • Han, Ji-Young;Yoo, Jae-Kyun;Lee, Yoon-Mi
    • Proceedings of the KSR Conference
    • /
    • 2010.06a
    • /
    • pp.389-396
    • /
    • 2010
  • After analyzing network of the region of western sea, which is the center of Circle Yellow-Sea economic region, and Circle Bo-Hai and the delta of a long river economic region, which are belong to three major economic region of China, as an efficient strategy, rail & sea multi-transport system of Korea-China joint SOC strategy is suggested. Rail & Sea multi-transport system, which is the links of railroads and shipping transport, can be subdivided into train-ferry, which is the transport of loaded trains into a vessel, and transshipment, which is transshipment of containers from railroads to vessels. And, the way of railroads transport through a tunnel under the sea is also suggested.

  • PDF

A Study on the Optimum Design of Multi-Object Dynamic System for the Rail Vehicle (철도차량 동적 진동특성을 고려한 다목적함수 최적설계)

  • Park, Chan-Kyoung;Lee, Kwang-Ki;Kim, Ki-Hwan;Hyun, Seung-Ho;Park, Choon-Soo
    • Proceedings of the Korean Society for Noise and Vibration Engineering Conference
    • /
    • 2000.06a
    • /
    • pp.894-899
    • /
    • 2000
  • Optimization of 26 design variables selected from suspension characteristics for Korean High Speed Train (KHST) is performed according to the minimization of 58 responses which represent running safety and ride comfort for KHST and analyzed by using the each response surface model from stochastic design experiments. Sensitivity of design variables is also analyzed through the response surface model which ineffective design prameters to the performance index are screened by using stepwise regression method. The response surface models are used for optimizing design variables through simplex algorism. Values of performance index simulated by optimized design parameters are totally lower than those by initial design parameters. It shows that this method is effective for optimizing multi-design variables to multi-object function.

  • PDF

Process Design of Multi-Step Drawing using Artificial Neural Network (신경망을 이용한 다단 인발의 공정설계)

  • 김동환;김동진;김병민;최재찬
    • Proceedings of the Korean Society for Technology of Plasticity Conference
    • /
    • 1997.03a
    • /
    • pp.144-147
    • /
    • 1997
  • Process design of multi-step wire drawing process, conducted by means of finite element analysis and ANN(Artificial Neural Network), has been considered. The investigated problem involves the adequate selection of the drawing die angle and the correspondent reduction rate sequence in the condition of desired initial and final diameter. Combinations of the process parameters which are used in finite element simulation are selected by using orthogonal array. Also the orthogonal array and the results of finite element simulation which are related to the process energy are used as train data of ANN. In this study, it is shown that the new technique using ANN is useful method in application to the wide range of metal forming process.

  • PDF

The Use of MSVM and HMM for Sentence Alignment

  • Fattah, Mohamed Abdel
    • 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.

A Study on Development of Multi-step Neural Network Predictive Controller (다단 신경회로망 예측제어기 개발에 관한 연구)

  • Bae, Geun-Shin;Kim, Jin-Su;Lee, Young-Jin;Lee, Kwon-Soon
    • Proceedings of the KIEE Conference
    • /
    • 1996.11a
    • /
    • pp.62-64
    • /
    • 1996
  • Neural network as a controller of a nonlinear system and a system identifier has been studied during the past few years. A well trained neural network identifier can be used as a system predictor. We proposed the method to design multi-step ahead predictor and multi-step predictive controller using neural network. We used the input and out put data of B system to train the NNP and used the forecasted approximat system output from NNP as B input of NNC. In this paper we used two-step ahead predictive controller to test B heating controll system and compared with PI controller.

  • PDF

Flight Simulation Training Device Operating Standards for MPL Training Programs in South Korea

  • Lee, Jang Ryong;Kwon, Moonjin;Kwon, Hanjoon
    • Journal of the Korean Society for Aviation and Aeronautics
    • /
    • v.29 no.3
    • /
    • pp.117-121
    • /
    • 2021
  • The Multi-crew Pilot License (MPL) is a new pilot qualification introduced by ICAO to train co-pilots for transport aircraft based on efficient and stable competency to respond to changes in the operating environment and technology. ICAO and the European Union Aviation Safety Agency (EASA) require a minimum flight of 240 hours for MPL qualification training, and allow the use of flight simulation training devices (FSTDs) for most of the training, specifying the performance requirements for FSTDs. As South Korea is also preparing for the operation of the MPL training program, it is essential to establish the operating standards for FSTDs required for MPL training. This study aims to identify the international standards for FSTDs related to MPL training, and to compare them with the current operating standards for FSTDs in South Korea for presenting a standard (draft) that can be used when introducing domestic MPL training programs in the future.