• 한국군사과학기술학회지
• /
• 제14권4호
• /
• pp.548-555
• /
• 2011

This paper presents a new method of measuring the ground's gradient using LNS(land navigation system) navigation data. When a vehicle equipped with LNS arrives at any place, LNS provides its navigation data which contain the information on vehicle's motion. We developed some formulas which can explain correlation between the vehicle's motion and ground's gradient. The proposed method using those formulas is shown to be accurate and convenient.

• 설비공학논문집
• /
• 제22권11호
• /
• pp.773-780
• /
• 2010

The dispersion of plume which is emitted from a chimney is governed by a lot of factors： wind, local terrain, turbulence intensity of atmosphere, and temperature, etc. In this study, we numerically investigate the plume dispersions for various altitudinal temperature gradients and wind speeds. The normal atmosphere has the temperature decrease of $0.6^{\circ}C/100m$, however, actually the real atmosphere has the various altitudinal temperature profiles according to the meteorological factors. A previous study focused on this atmospheric temperature gradient which induces a large scale vertical flow motion in the atmosphere thus makes a peculiar plume dispersion characteristics. In this paper, the effects of the atmospheric temperature gradient as well as the wind speed are investigated concurrently. The results for the developing processes in the atmosphere and the affluent's concentrations at the ambient and ground level are compared under the various altitudinal temperature gradients and wind speeds.

• 한국정밀공학회:학술대회논문집
• /
• 한국정밀공학회 2010년도 춘계학술대회 논문집
• /
• pp.377-378
• /
• 2010

• 한국수자원학회논문집
• /
• 제55권11호
• /
• pp.903-911
• /
• 2022

물을 공급하기 위한 자원 중 하나인 지하수는 다양한 자연적 요인에 의해 수위의 변동이 발생한다. 최근, 인공신경망을 이용하여 지하수위의 변동을 예측하는 연구가 진행되었다. 기존에는 인공신경망 연산자 중 학습에 영향을 미치는 Optimizer로 경사하강법(Gradient Descent, GD) 기반 Optimizer를 사용하였다. GD 기반 Optimizer는 초기 상관관계 의존성과 해의 비교 및 저장 구조 부재의 단점이 존재한다. 본 연구는 GD 기반 Optimizer의 단점을 개선하기 위해 GD와 화음탐색법(Harmony Search, HS)를 결합한 새로운 Optimizer인 Gradient Descent combined with Harmony Search(GDHS)를 개발하였다. GDHS의 성능을 평가하기 위해 다층퍼셉트론(Multi Layer Perceptron, MLP)을 이용하여 이천율현 관측소의 지하수위를 학습 및 예측하였다. GD 및 GDHS를 사용한 MLP의 성능을 비교하기 위해 Mean Squared Error(MSE) 및 Mean Absolute Error(MAE)를 사용하였다. 학습결과를 비교하면, GDHS는 GD보다 MSE의 최대값, 최소값, 평균값 및 표준편차가 작았다. 예측결과를 비교하면, GDHS는 GD보다 모든 평가지표에서 오차가 작은 것으로 평가되었다.

• 한국재료학회지
• /
• 제17권5호
• /
• pp.239-243
• /
• 2007

The evaluation and comparison have been made for the EMI noise which was included in the signal from the sensors in the acoustic emission testing for the bottom plate of ground tank at full. The EMI signal has been classified into two types. One is the signal with very short AE count, and this signal possibly can be filtered by front end filter setting of the channel count with low level of 4 and high level of $10^8$. The other EMI signal occurred from CH 1, CH 3 and CH 10, and had high and constant duration with high energy and count (maximun duration > $10^5\;{\mu}s$), and has characteristic gradient of accumulation amplitude distribution. This signal should be removed in the AE signal evaluation by filtering, because this may affect to the total gradient.

• 한국군사과학기술학회지
• /
• 제15권1호
• /
• pp.86-92
• /
• 2012

When missile is launched, a launcher needs to be leveled with accuracy to avoid the systems's instability. In general, a launcher is leveled by adjusting the stroke of leveling jacks; however, it is still challenge to control the leveling jacks fast and accurately. This paper thus proposed an innovative algorithm for compensating ground inclination of a missile launcher to expand operational field of a missile launcher. Using two inclinometers attached on a launcher, a base jack for leveling is selected and the mixed gradient where launcher stands on can be estimated. Due to the limited stroke, the launcher can compensate its ground inclination within maximum stroke margin. Then, the ground inclination of a launcher can be compensated by calculated angle using weighting factors. The effectiveness of proposed algorithm is proved with a prototype missile launcher.

• Geomechanics and Engineering
• /
• 제37권5호
• /
• pp.475-498
• /
• 2024

The prediction of the susceptibility of soil to liquefaction using a limited set of parameters, particularly when dealing with highly unbalanced databases is a challenging problem. The current study focuses on different ensemble learning classification algorithms using highly unbalanced databases of results from in-situ tests; standard penetration test (SPT), shear wave velocity (V_s) test, and cone penetration test (CPT). The input parameters for these datasets consist of earthquake intensity parameters, strong ground motion parameters, and in-situ soil testing parameters. liquefaction index serving as the binary output parameter. After a rigorous comparison with existing literature, extreme gradient boosting (XGBoost), bagging, and random forest (RF) emerge as the most efficient models for liquefaction instance classification across different datasets. Notably, for SPT and V_s-based models, XGBoost exhibits superior performance, followed by Light gradient boosting machine (LightGBM) and Bagging, while for CPT-based models, Bagging ranks highest, followed by Gradient boosting and random forest, with CPT-based models demonstrating lower G_mean(error), rendering them preferable for soil liquefaction susceptibility prediction. Key parameters influencing model performance include internal friction angle of soil (ϕ) and percentage of fines less than 75 µ (F₇₅) for SPT and V_s data and normalized average cone tip resistance (q_c) and peak horizontal ground acceleration (a_max) for CPT data. It was also observed that the addition of V_s measurement to SPT data increased the efficiency of the prediction in comparison to only SPT data. Furthermore, to enhance usability, a graphical user interface (GUI) for seamless classification operations based on provided input parameters was proposed.

• 한국지구물리탐사학회:학술대회논문집
• /
• 한국지구물리탐사학회 2006년도 공동학술대회 논문집
• /
• pp.9-14
• /
• 2006

자기쌍극자 모멘트의 깊이, 방향, 크기 등에 관한 평가는 자기탐사자료로부터 폭발물과 기타 자성체를 구분하는데 유용한 정보를 제공한다. 이러한 평가는 지질학적 잡음, 자기분산체, 주변 쌍극자기장 중첩 등의 이유로 방해를 받을 수 있다. 임의의 극성을 갖는 단일 혹은 다중 쌍극자 이상체의 효과적 계산을 위하여, 역산내부 필터 및 배경 자기장의 구배 평가를 포함하는 개선된 역산법을 개발하였다. 관측값들은 보간하여 격자화하였으며, 관측점으로부터 가장 가까운 계산점만을 사용하도록 표시하였다. 이러한 자료에 역산내부 필터를 적용하기 위하여는 빈간격 필터가 필요하다. 게다가 상당히 빈 곳이 많은 자료나 조사지 가장자리 및 구석 부분 자료들을 처리하기 위해서는 역산내부 필터를 수정하여야 한다. 이러한 목적으로 가장자리에 적용가능한 빈간격 구배제거 필터를 고안하고 시험하였다. 한국 속초의 청초호와 미국 매릴랜드의 육군 애벌딘 무기시험장에서 기록한 자기탐사자료에 적용한 결과를 소개한다.

• 한국지하수토양환경학회지:지하수토양환경
• /
• 제21권3호
• /
• pp.64-81
• /
• 2016

To analyze the influence of various groundwater flow rates (specific discharge) on BHE system with balanced and unbalanced energy loads under assuming same initial temperature (15℃) of ground and groundwater, numerical modeling using FEFLOW was used for this study. When groundwater flow is increased from 1 × 10⁻⁷ to 4 × 10⁻⁷m/s under balanced energy load, the performance of BHE system is improved about 26.7% in summer and 22.7% at winter time in a single BHE case as well as about 12.0~18.6% in summer and 7.6~8.7% in winter time depending on the number of boreholes in the grid, their array type, and bore hole separation in multiple BHE system case. In other words, the performance of BHE system is improved due to lower avT in summer and higher avT in winter time when groundwater flow becomes larger. On the contrary it is decreased owing to higher avT in summer and lower avT in winter time when the numbers of BHEs in an array are increased, Geothermal plume created at down-gradient area by groundwater flow is relatively small in balanced load condition while quite large in unbalanced load condition. Groundwater flow enhances in general the thermal efficiency by transferring heat away from the BHEs. Therefore it is highly required to obtain and to use adequate informations on hydrogeologic characterristics (K, S, hydraulic gradient, seasonal variation of groundwater temperature and water level) along with integrating groundwater flow and also hydrogeothermal properties (thermal conductivity, seasonal variation of ground temperatures etc.) of the relevant area for achieving the optimal design of BHE system.

• Steel and Composite Structures
• /
• 제44권1호
• /
• pp.49-63
• /
• 2022

This study aims to develop ensemble machine learning (ML) models for estimating the peak floor acceleration and maximum top drift of steel moment frames. For this purpose, random forest, adaptive boosting, gradient boosting regression tree (GBRT), and extreme gradient boosting (XGBoost) models were considered. A total of 621 steel moment frames were analyzed under 240 ground motions using OpenSees software to generate the dataset for ML models. From the results, the GBRT and XGBoost models exhibited the highest performance for predicting peak floor acceleration and maximum top drift, respectively. The significance of each input variable on the prediction was examined using the best-performing models and Shapley additive explanations approach (SHAP). It turned out that the peak ground acceleration had the most significant impact on the peak floor acceleration prediction. Meanwhile, the spectral accelerations at 1 and 2 s had the most considerable influence on the maximum top drift prediction. Finally, a graphical user interface module was created that places a pioneering step for the application of ML to estimate the seismic demands of building structures in practical design.