• Journal of the Semiconductor & Display Technology
• /
• v.19 no.3
• /
• pp.77-81
• /
• 2020

In this paper, we create scaffold defect classification models using machine learning based data. We extract the characteristic from collected scaffold external images using USB camera. SVM, KNN, MLP algorithm of machine learning was using extracted features. Classification models of three type learned using train dataset. We created scaffold defect classification models using test dataset. We quantified the performance of defect classification models. We have confirmed that the SVM accuracy is 95%. So the best performance model is using SVM.

• Korean Journal of Air-Conditioning and Refrigeration Engineering
• /
• v.18 no.2
• /
• pp.103-111
• /
• 2006

To optimize the ventilation and smoke control systems in subway equipped with platform screen door, the technology to analyze the unsteady tunnel flow caused by running of train should be developed. The development of model experiment and numerical analysis technique with relation to unsteady flow of subway were presented. The pressure and air velocity changes in 1/20-scaling experiment unit were measured and results were comparied to those of 3-D unsteady numerical analysis applied with sharp interface method. The experimental and numerical results were quantitatively similar and it would be reasonable to apply sharp interface method to analyze the unsteady flow in subway equipped with platform screen door.

• Proceedings of the KSR Conference
• /
• 1999.05a
• /
• pp.238-247
• /
• 1999

A study on the static type simulator will include an instructor's station, two cabs for ISA with visual and sound system, and realistic and accurate model of the trains operation. The simulator is easy to extend and maintenance using structured the S/W. The training of new drives requires that the environment of the cab, controls placement, etc. must highly realistic so that driver can readily transfer his training experience to the real world. The simulator detailed software model and extensive scenario design capability allows both for a wide variety of scenarios and accurately modeled response covering most aspects of brakes, rules, and faults.

• Proceedings of the KSR Conference
• /
• 2008.06a
• /
• pp.849-854
• /
• 2008

For the running safety assessment of Saemaul train passing through curves, an analysis model for multibody system has been developed. By using this model and ADAMS/Rail, sensitivity analyses depending on the variation of parameters related to the derailment coefficients have been conducted. According to the increase of running speed, the derailment coefficient and unload ratio were increased. At high speed, the derailment coefficient and unload ratio of left wheel showed higher than right wheel. If the cant increased, the derailment coefficient and unload ratio increased. but decreased based on the balance cant value by the curvature and running speed.

• Proceedings of the KSR Conference
• /
• 2008.06a
• /
• pp.813-819
• /
• 2008

For the wear characteristics assessment of Saemaul train passing through curves, an analysis model for multi-car system has been developed. By using this model and ADAMS/Rail, sensitivity analyses have been conducted for the wear characteristics by changing the related parameters. According to the increase of running speed, the wear number, the sliding mean and friction coefficient were increased. At high speed, the wear number, the sliding mean and friction coefficient of left wheel showed higher than right wheel. If the cant increased, the wear number the sliding mean and friction coefficient increased. but decreased based on the balance cant value by the curvature and running speed.

• Proceedings of the KSR Conference
• /
• 1998.05a
• /
• pp.502-509
• /
• 1998

The scheme to reduce jerking phenomena in one push-pull type trainset was proposed. To simulate the jerking between coaches, dynamic analysis model was made. This model could analyze longitudinal dynamic behavior between locomotives and coaches caused by spring and damping characteristics of couplers and center pivots; characteristic curves of traction and braking. To validate the analysis results, tests were conducted in the same driving and braking condition. Comparison of longitudinal acceleration between simulation and test results shows a good agreement. To minimize the jerking phenomena, lots of dynamic simulations were conducted with varying driving/braking effort curve. From the results of simulations, an efficient and economic way to reduce jerking phenomena was found to be to reduce slope of tractive effort curve and synchronize braking time between locomotives and coaches. Test results show that this way could reduce the jerking Phenomena. To express jerkins Phenomena quantitatively, maximum peak to peak values of acceleration were used.

• Proceedings of the KSR Conference
• /
• 2001.05a
• /
• pp.123-128
• /
• 2001

Numerical simulation is conducted to clarify the heat transfer and fluid flow characteristics of brake shoe for freight car. High order up-wind scheme for governing equations, k-epsilon turbulent model and SIMPLEC algorithm based on finite volume method are used to solve the physical shoe model. The governing equations are solved by TDMA(Tri-Diagonal Matrix Algorithm) with line-by-line method and block correction. From the results of simulation, the characteristics of cooling pattern is strongly affected by the velocity of train and the material of shoe. The face lift of shoe affects on the temperature distribution of rear surface of shoe as well as the front surface of that. Due to the grooves in shoe, it will be expected to cool the frictional heat and result in the reduction of maintenance efforts.

• Proceedings of the KSR Conference
• /
• 2004.10a
• /
• pp.1559-1565
• /
• 2004

Railway system is consisted of various resources such as rail-line, signal, and railcar. It is necessary to efficiently utilize these limited and expensive resources as much as possible up to given line capacity. So far, we treat the line capacity as the criteria for evaluating investment alternatives or for restricting train frequencies, and this criteria is calculated statical and experimental numerical formula. But, line capacity has special attribute that changes dynamically according to operational conditions, so there is a need of new line capacity estimation system. In this paper, we present an improved systematic line capacity model. The proposed model has three main components ; TPS(tain performance simulator), PES (parameter evaluation simulator), LCS(line capacity simulator). The concept of each sub-component is described, including the evaluation method of capacity parameters. And capacity parameter evaluation and estimation results using sample line section data are presented.

• Journal of the Korean Society for Railway
• /
• v.6 no.1
• /
• pp.15-20
• /
• 2003

The computer simulation techniques were adopted to evaluate the effects of seating positions of passenger under various accident scenarios. The baseline of computer simulation model was tuned by the sled impact tests which conducted under the upright and standard seating positions. This study shows the effect of relative velocity between occupant and struck vehicle while occupant is impacted to a front seat's seatback. Although, base on the current accident scenarios, The KHST is performed well enough to protect average adult male occupants. However, Results from the tests indicate small size occupant or higher impact speed may cause sever neck and femur injuries.

• Journal of the Korean Society of Safety
• /
• v.24 no.6
• /
• pp.124-131
• /
• 2009

In any form of construction work, it is essential that accidents be prevented at every stage, from foundation preparation to build completion. For this, it is necessary to use models that can assess risk and provide instructions for safe work processes so that the risk of accidents is reduced. Currently, however, very few models can perform these tasks. In this paper, we present a model that assesses risk quantitatively by analyzing the risk factors involved in each stage of construction, such as foundation work, temporary work, structural work, equipment work, and finishing work. The model performs assessment based on examples of accidents and by investigating actual conditions during construction. In addition, we present in this paper a safety management system developed to assess risk during construction and to effectively train laborers.