• Steel and Composite Structures
• /
• v.37 no.2
• /
• pp.193-209
• /
• 2020

In this paper, the efficiency of five Machine Learning (ML) methods consisting of Deep Learning (DL), Support Vector Machine (SVM), Random Forest (RF), Decision Tree (DT), and Gradient Tree Booting (GTB) for regression and classification of the Ultimate Load Factor (ULF) of nonlinear inelastic steel frames is compared. For this purpose, a two-story, a six-story, and a twenty-story space frame are considered. An advanced nonlinear inelastic analysis is carried out for the steel frames to generate datasets for the training of the considered ML methods. In each dataset, the input variables are the geometric features of W-sections and the output variable is the ULF of the frame. The comparison between the five ML methods is made in terms of the mean-squared-error (MSE) for the regression models and the accuracy for the classification models, respectively. Moreover, the ULF distribution curve is calculated for each frame and the strength failure probability is estimated. It is found that the GTB method has the best efficiency in both regression and classification of ULF regardless of the number of training samples and the space frames considered.

• Journal of Wetlands Research
• /
• v.8 no.2
• /
• pp.75-81
• /
• 2006

In this study, runoff simulation was carried out in order to derive operational improvement of small urban storm water pumping station under heavy storm rainfall conditions. The flood inflow hydrograph of Guri city heavy storm in July, 2001 was successfully simulated by HEC-HMS, a GIS-based runoff simulation model. For the runoff simulation, ArcView, as an effective GIS tool, was used to provide input data of the model such as land use data, soil distribution data and SCS runoff curve number.

• Steel and Composite Structures
• /
• v.39 no.2
• /
• pp.149-158
• /
• 2021

In this research paper, the free vibrational response of laminated composite plates is investigated using a non-polynomial refined shear deformation theory (NP-RSDT). The most interesting feature of this theory is the parabolic distribution of transverse shear deformations while ensuring the conditions of nullity of shear stresses at the free surfaces of the plate without requiring the Shear correction factor "Ks". A fourth-nodded isoparametric element with four degrees of freedom per node is employed for laminated composite plates. The numerical analysis of simply supported square anti-symmetric cross-ply and angle-ply laminated plate is carried out using a special discretization based on four-node finite element method which four degrees of freedom per node. Several numerical results are presented to show the effect of the coupling parameters of the plate such as the modulus ratios, the thickness ratio and the plate layers number on adimensional eigen frequencies. All numerical results presented using the current finite element method (FEM) is presented in 3D curve form.

• Steel and Composite Structures
• /
• v.46 no.5
• /
• pp.673-687
• /
• 2023

In this study, the weight and the connections type layout of low-rise eccentrically braced frame (EBF) have been optimized based on performance-based design method. For this purpose, two objective functions were defined based on two different aspects on rigid connections, in one of which minimization and in the other one, maximization of the number of rigid connections was considered. These two objective functions seek to increase the area under the pushover curve, in addition to the reduction of the weight and selection of the optimum connections type layout. The performance of these objective functions was investigated in optimal design of a three-story eccentrically braced frame, using two meta-heuristic algorithms: Enhanced Colliding Bodies Optimization (ECBO) and Enhanced Vibrating Particles System (EVPS). Then, the reliability indices of the optimal designs for both objective functions were calculated for the story lateral drift limits using Monte-Carlo Simulation (MCS) method. Based on the reliability assessment results of the optimal designs and taking the three levels of safety into account, the final designs were selected and their specifications were compared.

• Steel and Composite Structures
• /
• v.47 no.5
• /
• pp.601-613
• /
• 2023

Numerous methods have been proposed in predicting formability of sheet metals based on microstructural and macro-scale properties of sheets. However, there are limited number of papers on the optimization problem to increase formability of sheet metals. In the present study, we aim to use novel optimization algorithms in neural networks to maximize the formability of sheet metals based on tensile curve and texture of aluminum sheet metals. In this regard, experimental and numerical evaluations of effects of texture and tensile properties are conducted. The texture effects evaluation is performed using Taylor homogenization method. The data obtained from these evaluations are gathered and utilized to train and validate an artificial neural network (ANN) with different optimization methods. Several optimization method including grey wolf algorithm (GWA), chimp optimization algorithm (ChOA) and whale optimization algorithm (WOA) are engaged in the optimization problems. The results demonstrated that in aluminum alloys the most preferable texture is cube texture for the most formable sheets. On the other hand, slight differences in the tensile behavior of the aluminum sheets in other similar conditions impose no significant decreases in the forming limit diagram under stretch loading conditions.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.6 no.1
• /
• pp.107-118
• /
• 2003

The purpose of this study is to assess the hydrological impact on a watershed from long-term land cover changes. Gyeongan-cheon watershed($558.2km^2$) was selected and WMS(watershed modeling system) HEC-1 model was adopted as an evaluation tool. To identify land cover changes, five Landsat images(1980/2/15, 1986/4/15, 1990/4/26, 1996/4/26, 2000/5/17) were selected and analyzed using maximum likelihood method. As a result, urban areas have increased by 5.6% and forest areas have decreased by 6.1% between 1980 and 2000. SCS curve number increased by 9.8. To determine model parameters and evaluate HEC-1 model, five storm events(1998/5/2, 1998/8/23, 1998/9/30, 1999/5/3, 2000/7/29) were used. The simulated stream flow agreed well with the observed one with relative errors ranging from 9% to 36%. For 254 mm daily rainfall of 30 years frequency, due to the increase of urban areas peak flow increased by $455m^3/sec$ and the time of peak flow reduced about four hours for 20 years land cover changes.

• Steel and Composite Structures
• /
• v.18 no.6
• /
• pp.1369-1389
• /
• 2015

In order to investigate the behaviour of lying multi-stud connectors in cable-pylon anchorage zone, twenty-four push-out tests are carried out with different stud numbers and diameters. The effect of concrete block width and tensile force on shear strength is investigated using the developed and verified finite element model. The results show that the shear strength of the lying multi-stud connectors is reduced in comparison with the lying single-stud connector. The reduction increases with the increasing of the number of studs in the vertical direction. The influence of the stud number on the strength reduction of the lying multi-stud connectors is decreased under combined shear and tension loads compared with under pure shear. Yet, due to multi-stud effect, they still can't be ignored. The concrete block width has a non-negligible effect on the shear strength of the lying multi-stud connectors and therefore should be chosen properly when designing push-out specimens. No obvious difference is observed between the strength reductions of the studs with 22 mm and 25 mm diameters. The shear strengths obtained from the tests are compared with those predicted by AASHTO LRFD and Eurocode 4. Eurocode 4 generally gives conservative predictions of the shear strength, while AASHTO LRFD overestimates the shear strength. In addition, the lying multi-stud connectors with the diameters of 22 m and 25 mm both exhibit adequate ductility according to Eurocode 4. An expression of load-slip curve is proposed for the lying multi-stud connectors and shows good agreement with the test results.

• Journal of Korean Society for Geospatial Information Science
• /
• v.21 no.3
• /
• pp.37-46
• /
• 2013

Similarity measure of catchments is essential for regionalization studies, which provide in depth analysis in hydrological response and flood estimations at ungauged catchments. However, this similarity measure is often biased to the selected catchments and is not clearly explained in hydrological sense. This study applied a type of hydrological similarity distance measure-Flood Estimation Handbook to 25 Geum River catchments, Korea. Three Catchment Characteristics, Area(A)-Annual precipitation(SAAR)-SCS Curve Number(CN), are used in Euclidian distance measures. Furthermore, six index of Flow Duration Curve are applied to clustering analysis of SPSS. The catchments' grouping of hydrological similarity measures suggests three groups (H1, H2 and H3) and the four catchments are not grouped in this study. The clustering analysis of FDC provides four Groups; F1, F2, F3 and F4. The six catchments (out of seven) of H1 are grouped in F1, while Sangyeogyo is grouped in F2. The four catchments (out of six) of H2 are also grouped in F2, while Cheongju and Guryong are grouped in F1. The catchments of H3 are categorized in F1. The authors examine the results (H1, H2 and H3) of similarity measure based on catchment physical descriptors with results (F1 and F2) of clustering based on catchment hydrological response. The results of hydrological similarity measures are supported by clustering analysis of FDC. This study shows a potential of hydrological catchment similarity measures in Korea.

• Journal of Korea Water Resources Association
• /
• v.38 no.5 s.154
• /
• pp.391-399
• /
• 2005

The purpose of this study is to evaluate hydrological impact by the land cover change of typhoon damage. For the typhoon RUSA (rainfall 1,402 mm) occurred in 2002 (August $31\;{\sim}$ September 1), satellite images of Landsat 7 ETM+ of September 29, 2000 and Landsat 5 TM of September 11, 2002 were selected, and each land cover was classified for Namdae-cheon watershed $192.7km^2$ located in the middle-eastern part of Korea Peninsula. SCS unit hydrograph for watershed runoff and Muskingum for streamflow routing of WMS HEC-1 was adopted. 30m resolution DEM & hydrological soil group using 1:50,000 soil map were prepared. The model was calibrated using three available data of storm events of 1985 to 1988 based on 1985 land cover condition. To predict the streamflow change by damaged land cover condition, rainfall of 50 years to 500 years frequency were generated using 2nd quantile of Huff method. The damaged land cover condition treated as bare soil surface increased streamflow of $50.1\;m^3/sec$ for 50 years rainfall frequency and $67.6\;m^3/sec$ for 500 years rainfall frequency based on AMC-I condition. There may be some speedy treatment by the government for the next coming typhoon damage.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2009.05a
• /
• pp.997-1001
• /
• 2009

GIS 기반의 HEC-HMS를 이용하여 유량자료가 있는 소하천인 정자천 유역을 대상으로 장기 강우 유출 분석을 하였다. 일반적으로 홍수량 산정은 단기해석으로 분석하나 평 갈수기와 홍수기 때의 하천 유황이 다르기 때문에 매개변수가 불일치할 것이라 생각되고, 이에 대한 보정이 필요한지 판단이 필요하다. 이를 위해 장기 연속모의를 통하여 매개변수의 보정 필요성을 검토하였다. 연구는 수치지도를 조합하여 ARC-VIEW로부터 Map파일 및 Basin파일을 생성하였고, 토지이용도와 토양도를 ARC-VIEW를 이용하여 CN value를 추출하였다. 계산조건중 손실량 산정방법은 SCS Curve Number법으로 하였고, 단위도 방법은 Clark UH법, 하도추적방법은 Muskingum방법, 기저유량산정방법은 Constant monthly로 설정하였다. 유역면적, 도달시간자료, 저류상수 값 등의 추출은 GIS기법을 이용하여 추출하였다. HEC-HMS의 장기 연속모의(Continuous Simulation)로 얻어진 Element Graph를 보면 대략적인 형태가 일치하나 2006년도에 대한 모의에서는 홍수기의 결과만 일치하는 것으로 보이고, 2007년도에 대한 모의에서는 평 갈수기와 홍수기의 그래프 형태가 유사하게 나타났다. 실측 유량보다 유량 값이 약간 크게 산출되어 홍수량 산정에서 볼 때 안정성에 무리가 없다고 판단되지만, 평 갈수기 기간에서 볼 때 연마다 하천의 매개변수가 일치하지 않는다고 생각되며, 홍수 후 유역의 변화로 매개변수가 변화한 것이라 생각된다. 향후 정자천유역의 보다 많은 강우사상과 실측유량을 통해 HEC-HMS의 유출량을 비교 분석하면 보다 더 정확한 해석이 가능할 것이며, 홍수가 빈번한 지역의 경우 유수지의 검토와 저수지의 시간당 방류량을 알 수 있다면 오차의 범위를 줄일 수 있다고 생각된다. 더 나아가 우리나라에 적합한 매개변수와 GIS 프로그램이 개발된다면 보다 쉽고 정확한 해석이 가능할 것이라고 생각된다.