• Geomechanics and Engineering
• /
• v.18 no.6
• /
• pp.595-603
• /
• 2019

A modified model combining Kriging and Monte Carlo method (MC) is proposed for probabilistic estimation of tunnel face stability in this paper. In the model, a novel uniform design is adopted to train the Kriging, instead of the existing active learning function. It has advantage of avoiding addition of new training points iteratively, and greatly saves the computational time in model training. The kinematic approach of limit analysis is employed to define the deterministic computational model of face failure, in which the Hoek-Brown failure criterion is introduced to account for the nonlinear behaviors of rock mass. The trained Kriging is used as a surrogate model to perform MC with dramatic reduction of calls to actual limit state function. The parameters in Hoek-Brown failure criterion are considered as random variables in the analysis. The failure probability is estimated by direct MC to test the accuracy and efficiency of the proposed probabilistic model. The influences of uncertainty level, correlation relationship and distribution type of random variables are further discussed using the proposed approach. In summary, the probabilistic model is an accurate and economical alternative to perform probabilistic stability analysis of tunnel face excavated in spatially random Hoek- Brown media.

• The Bulletin of The Korean Astronomical Society
• /
• v.44 no.2
• /
• pp.43.1-43.1
• /
• 2019

In this study, we apply a deep learning model to denoising solar magnetograms. For this, we design a model based on conditional generative adversarial network, which is one of the deep learning algorithms, for the image-to-image translation from a single magnetogram to a denoised magnetogram. For the single magnetogram, we use SDO/HMI line-of-sight magnetograms at the center of solar disk. For the denoised magnetogram, we make 21-frame-stacked magnetograms at the center of solar disk considering solar rotation. We train a model using 7004 paris of the single and denoised magnetograms from 2013 January to 2013 October and test the model using 1432 pairs from 2013 November to 2013 December. Our results from this study are as follows. First, our model successfully denoise SDO/HMI magnetograms and the denoised magnetograms from our model are similar to the stacked magnetograms. Second, the average pixel-to-pixel correlation coefficient value between denoised magnetograms from our model and stacked magnetogrmas is larger than 0.93. Third, the average noise level of denoised magnetograms from our model is greatly reduced from 10.29 G to 3.89 G, and it is consistent with or smaller than that of stacked magnetograms 4.11 G. Our results can be applied to many scientific field in which the integration of many frames are used to improve the signal-to-noise ratio.

• Journal of Korean Society for Quality Management
• /
• v.51 no.3
• /
• pp.363-379
• /
• 2023

Purpose: The main objective of this research is to construct an AI-based Composite Supplementary Index (ACSI) model to achieve accurate predictions of the Composite Index of Business Indicators. By incorporating various economic indicators as independent variables, the ACSI model enables the prediction and analysis of both the leading index (CLI) and coincident index (CCI). Methods: This study proposes an AI-based Composite Supplementary Index (ACSI) model that leverages diverse economic indicators as independent variables to forecast leading and coincident economic indicators. To evaluate the model's performance, advanced machine learning techniques including MLP, RNN, LSTM, and GRU were employed. Furthermore, the study explores the potential of employing deep learning models to train the weights associated with the independent variables that constitute the composite supplementary index. Results: The experimental results demonstrate the superior accuracy of the proposed composite supple- mentary index model in predicting leading and coincident economic indicators. Consequently, this model proves to be highly effective in forecasting economic cycles. Conclusion: In conclusion, the developed AI-based Composite Supplementary Index (ACSI) model successfully predicts the Composite Index of Business Indicators. Apart from its utility in management, economics, and investment domains, this model serves as a valuable indicator supporting policy-making and decision-making processes related to the economy.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2008.05a
• /
• pp.579-584
• /
• 2008

A novel nondestructive testing (NDT) system, which is able to detect a crack with high speed and high spatial resolution, is urgently required for inspecting small cracks on express train wheels. This paper proposes an improved signal processing circuits, which uses the multiple amplifying circuits and the crack indicating pulse output system of the previous scan-type magnetic camera. Hall sensors are arrayed linearly, and the wheel is rotated with static speed in the vertical direction to sensor array direction. Each Hall voltages are amplified, converted and immediately operated by using, amplifying circuits, analog-to-digital converters and $\mu$-processor, respectively. The operated results, ${\partial}V_H/{\partial}t$, are compared with a standard value, which indicates a crack existence. If the ${\partial}V_H/{\partial}t$ is larger than standard value, the pulse signal is output, and indicates the existence of crack. The effectiveness of the novel method was verified by examine using cracks on the wheel specimen model.

• Journal of the Korean Society for Railway
• /
• v.15 no.4
• /
• pp.357-363
• /
• 2012

This paper presents a new operation method for the single phase PWM(Pulse Width Modulation) converter train. Recently, the trains adopting the PWM converter have become the majority in the electric locomotives since there are distinct advantages over the predecessors, which can be operated at near unity power factor. However, a slight modification of the control scheme makes this kind of vehicles run in the region of leading power factor. Although this feature seems to be of no significant use by itself, the leading phase operation can improve the voltage profile and the line loss of the feeding systems is decreased by compensating the reactive power loss along the line when it considered together with the feeding systems. This method is even more economical and efficient comparing with the installation of SVC that is mainly used for this purpose since the train can become a movable compensator. With the conditions and some essential formula for the leading phase operation, a new power factor control algorithm has been proposed to implement this scheme. The results of simulation through SIMULINK model show that the proposed method is suitable enough for practical use.

• Journal of Navigation and Port Research
• /
• v.30 no.3 s.109
• /
• pp.181-187
• /
• 2006

In the wave spectrum distribution based on linear wave theory, the appearance of a giant wave whose wave height reaches to 30m has been considered next to almost impossible in a real sea However since more than 10 giant waves were observed in a recent investigation of global wave distribution which was carried out by the analysis of SAR imagines for three weeks, the existence of the giant waves is being recognized and it is considered the cause of many unknown marine disasters. The change of wave height distribution concerning a formation of wave train, nonlinear wave to wave interaction and so on were raised as the causes of the appearance of the giant waves, but the occurrence mechanism of the giant waves hasn't been cleared yet. In present study, we investigated appearance circumstances of the giant waves in real sea and its occurrence mechanism was analyzed based on linear and nonlinear wave focusing theories. Also, through a development of numerical model of the nonlinear $schr\"{o}dinger$ equation, the formations of the giant wave from progressive wave train were reproduced.

• Journal of computational fluids engineering
• /
• v.17 no.1
• /
• pp.36-43
• /
• 2012

When a high-speed train passes an underground station, large pressure waves are generated due to the piston effect. These pressure waves can cause the problems of vibration and noise as well as the ear discomfort of passengers at the underground station. This work numerically analyzed the pressure wave generation and propagation in an high-speed railway underground station, and the optimal location for vent shafts was studied to improve the passenger comfort by reducing the magnitude of the pressure wave and its rate of change. The evolution of pressure field in the underground station was calculated using a CFD(Computational Fluid Dynamics) software(Fluent), where the axis-symmetric two-dimensional model verified by Wu was used. And this study is applied to modelling of the underground station and the tunnel from Daegok station A-line of GTX(Great Train Express). From the result, we can have a conclusion that the role of vent shafts respectively were different according to the position in and out the underground station. Also Vent shaft in the underground station widely reduced pressure magnitude. And vent shaft out underground station reduced initial pressure peak value. Double vent shafts installed at tunnel toward station entrance and inside of the tunnel are the most efficient to reduce pressure. and pressure reduction increases according to the number of vent shaft.

• Journal of the Korean Society for Railway
• /
• v.13 no.4
• /
• pp.412-418
• /
• 2010

This paper presents the methods to acquire the Safety Certificate from Independent Safety Assessment based on the IEC standard62279 which is commonly applied to railway system for Automatic Train Control(ATC) system in accordance with Urban Maglev project. This also shows approach methods and relative activities for project life- cycle to accomplish and ensure the system requirements of ATC system, RAMS and S/W quality activities. Furthermore, the key tasks conducted with ISA are noted in detail. These kind of activities for software quality of ATC system to obtain S afety Certificate could be a CASE model to improve the quality of domestic railway system and products, and also contribute to the growth of railway business and toward the achievement of overseas' railway signaling markets.

• Journal of the Korean Society for Railway
• /
• v.12 no.5
• /
• pp.732-737
• /
• 2009

Wind tunnel testing on the real-scale pantograph for high-speed train has been conducted to investigate the aerodynamic characteristic of the pantograph at high-speed. The mid-scale subsonic wind tunnel of Korea Airforce Acamedy with 3.5m width, 2.45m height, and 8.8m length test section has been employed. The test model has been supported above 50cm height from the bottom of test section using vertical strut to eliminate the boundary layer generated from the bottom of the test section. The height of the pantograph has been varied in three cases, in both of the normal running and reverse running modes. The resultant lift forces of the pantograph to catenary system in all the cases have been measured and the relation between the test conditions and the lift forces have been extensively analyzed.

• Journal of the Korean Society for Railway
• /
• v.11 no.3
• /
• pp.300-310
• /
• 2008

Through this study, a conceptual design for the next generation high-speed EMU has been derived to meet the crash worthiness requirements of the Korean rollingstock safety regulation. The crashworthiness regulations require some performance requirements for two heavy collision accident scenarios; a train-to-train collision at the relative speed of 36 km/h, and a collision against a standard deformable obstacle of 15 ton at 110km/h. The complete train set will be composed of 2TC-6M with 13 ton axle load, which is different from KTX with the power car of 17 ton axle load. Using theoretical and numerical analyses, a crashworthy conceptual design was derived in terms of mean crush forces and energy absorptions for principal crushable structures and devices. The derived conceptual design was evaluated and improved using one dimensional dynamic simulations for the bar-spring-damper-mass model. It is shown from the simulation results that the suggested conceptual design can easily satisfy domestic crashworthiness requirements.