Tae Soo Kwon
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Tae Soo Kwon has a total of 24 co-authors. Here are the top co-authors by number of shared publications:
Hyun Seung Jung
Korea Univ Sci & Technol, Dept Robot & Virtual Engn, Daejeon, South Korea
4 shared publications- Jin-Sung Kim
Department of Electronic Engineering, Sun Moon University, Asan, South Korea
3 shared publications H. S. Jung
Korea Railroad Research Institute
1 shared publication- Hoon Huh
KAIST
1 shared publication - Hoyong Lee
Korea Railroad Research Institute
1 shared publication - Hyun Seung Jung
Railroad Accident Research Department, Korea Railroad Research Institute, Uiwang, Republic of Korea
1 shared publication
Latest Publications
- Open Access
Two-Stage Multi-Objective Optimization for Improving the Aerodynamic Characteristics of High-Speed Train Nose Shape
An optimal high-speed train nose design was formulated to reduce aerodynamic drag, mitigate tunnel micro-pressure waves, and improve crosswind safety. Using the vehicle modeling function, the EMU-320 nose shape was derived and applied as the base model for the optimal design. Following the initial optimization stage aimed at reducing aerodynamic drag, the second stage of optimization was conducted, using the results of the first stage as constraints, to further reduce tunnel micro-pressure waves and enhance crosswind safety. In the first stage, the aerodynamic drag was reduced by 8.7% due to the pointed nose shape. In the second stage, a Pareto front of optimal shapes was derived to reduce tunnel micro-pressure waves and improve crosswind safety, ensuring that the aerodynamic drag did not exceed the optimum achieved in the first stage by more than 1.5%. This two-stage multi-objective optimization is expected to be effectively utilized in the optimal design of high-speed train shapes that meet the intended purposes.
Open AccessTwo-Stage Multi-Objective Optimization for Improving the Aerodynamic Characteristics of High-Speed Train Nose Shape
An optimal high-speed train nose design was formulated to reduce aerodynamic drag, mitigate tunnel micro-pressure waves, and improve crosswind safety. Using the vehicle modeling function, the EMU-320 nose shape was derived and applied as the base model for the optimal design. Following the initial optimization stage aimed at reducing aerodynamic drag, the second stage of optimization was conducted, using the results of the first stage as constraints, to further reduce tunnel micro-pressure waves and enhance crosswind safety. In the first stage, the aerodynamic drag was reduced by 8.7% due to the pointed nose shape. In the second stage, a Pareto front of optimal shapes was derived to reduce tunnel micro-pressure waves and improve crosswind safety, ensuring that the aerodynamic drag did not exceed the optimum achieved in the first stage by more than 1.5%. This two-stage multi-objective optimization is expected to be effectively utilized in the optimal design of high-speed train shapes that meet the intended purposes.
- Open Access
Real-Time Hybrid Deep Learning-Based Train Running Safety Prediction Framework of Railway Vehicle
Train running safety is considered one of the key criteria for advanced highway trains and bogies. While a number of existing research studies have focused on its measurement and monitoring, this study proposes a new and effective train running a safety prediction framework. The wheel derail coefficient, wheel rate of load reduction, and wheel lateral pressure are considered the decision variables for the safety framework. Data for actual measured rail conditions and vibration-based signals are used as the input data. However, advanced trains and bogies are influenced more by their inertial structures and mechanisms than by railway conditions and external environments. In order to reflect their inertial influences, past data of output variables are used as recurrent data. The proposed framework shares advantages of a general deep neural network and a recurrent neural network. To prove the effectiveness of the proposed hybrid deep-learning framework, numerical analyses using an actual measured train-railway model and transit simulation are conducted and compared with the existing deep learning architectures.
Open AccessReal-Time Hybrid Deep Learning-Based Train Running Safety Prediction Framework of Railway Vehicle
Train running safety is considered one of the key criteria for advanced highway trains and bogies. While a number of existing research studies have focused on its measurement and monitoring, this study proposes a new and effective train running a safety prediction framework. The wheel derail coefficient, wheel rate of load reduction, and wheel lateral pressure are considered the decision variables for the safety framework. Data for actual measured rail conditions and vibration-based signals are used as the input data. However, advanced trains and bogies are influenced more by their inertial structures and mechanisms than by railway conditions and external environments. In order to reflect their inertial influences, past data of output variables are used as recurrent data. The proposed framework shares advantages of a general deep neural network and a recurrent neural network. To prove the effectiveness of the proposed hybrid deep-learning framework, numerical analyses using an actual measured train-railway model and transit simulation are conducted and compared with the existing deep learning architectures.
- 30 September 2018
- Published by The Korean Society of Mechanical Engineers in Transactions of the Korean Society of Mechanical Engineers - A
- Vol. 42 (9) , 837-845
Comparison of Crashworthiness with Application of the Crumple Zone Crushing Curve for Existing Urban Railways
- 30 September 2018
- Published by The Korean Society of Mechanical Engineers in Transactions of the Korean Society of Mechanical Engineers - A
- Vol. 42 (9) , 837-845
Comparison of Crashworthiness with Application of the Crumple Zone Crushing Curve for Existing Urban Railways
- 1 October 2015
- Published by The Korean Society of Mechanical Engineers in Transactions of the Korean Society of Mechanical Engineers - A
- Vol. 39 (10) , 1053-1061
Deformation Behavior of Curling Strips on Tearing Tubes
- 1 October 2015
- Published by The Korean Society of Mechanical Engineers in Transactions of the Korean Society of Mechanical Engineers - A
- Vol. 39 (10) , 1053-1061
Deformation Behavior of Curling Strips on Tearing Tubes
- 1 October 2015
- Published by The Korean Society of Mechanical Engineers in Transactions of the Korean Society of Mechanical Engineers - A
- Vol. 39 (10) , 1063-1068
Study on 3-D Simulation for Overriding Evaluation of Urban Train
- 1 October 2015
- Published by The Korean Society of Mechanical Engineers in Transactions of the Korean Society of Mechanical Engineers - A
- Vol. 39 (10) , 1063-1068
Study on 3-D Simulation for Overriding Evaluation of Urban Train
- 1 September 2015
- Published by The Korean Society of Mechanical Engineers in Transactions of the Korean Society of Mechanical Engineers - A
- Vol. 39 (9) , 885-892
Study on Computational Simulation of a Metro Collision Accident and Improvement of Passive Safety
- 1 September 2015
- Published by The Korean Society of Mechanical Engineers in Transactions of the Korean Society of Mechanical Engineers - A
- Vol. 39 (9) , 885-892
Study on Computational Simulation of a Metro Collision Accident and Improvement of Passive Safety
- 15 May 2011
- Published by Springer Nature in International Journal of Automotive Technology
- Vol. 12 (3) , 383-389
Effect of punch angle on energy absorbing characteristics of tube-type crash elements
- 15 May 2011
- Published by Springer Nature in International Journal of Automotive Technology
- Vol. 12 (3) , 383-389
Effect of punch angle on energy absorbing characteristics of tube-type crash elements
- 9 May 2011
- Published by Springer Nature
- p. 647-654
Evaluation of Crash Energy Absorption Capacity of a Tearing Tube
- 9 May 2011
- Published by Springer Nature
- p. 647-654
Evaluation of Crash Energy Absorption Capacity of a Tearing Tube
- 19 August 2008
- Published by Springer Nature
- p. 239-245
A Conceptual Framework of the Cooperative Analyses in Computer-Aided Engineering
- 19 August 2008
- Published by Springer Nature
- p. 239-245
A Conceptual Framework of the Cooperative Analyses in Computer-Aided Engineering