• 대한기계학회논문집A
• /
• 제20권4호
• /
• pp.2752-2759
• /
• 1996

This paper presents crack growth analysis approach on the basis of neural networks, a branch of cognitive science to high temperature low cycle fatigue that shows strong nonlinearity in material behavior. As the number of data patterns on crack growth increase, pattern classification occurs well and two point representation scheme with gradient of crack growth curve simulates crack growth rate better than one point representation scheme. Optimal number of learning data exists and excessive number of learning data increases estimated mean error with remarkable learning time J-da/dt relation predicted by neural networks shows that test condition with unlearned data is simulated well within estimated mean error(5%).

• Journal of the Korean Data and Information Science Society
• /
• 제17권2호
• /
• pp.269-278
• /
• 2006

This paper presents the new hybrid data mining technique using error pattern, modeling of improving classification accuracy. The proposed method improves classification accuracy by combining two different supervised learning methods. The main algorithm generates error pattern modeling between the two supervised learning methods(ex: Neural Networks, Decision Tree, Logistic Regression and so on.) The Proposed modeling method has been applied to the simulation of 10,000 data sets generated by Normal and exponential random distribution. The simulation results show that the performance of proposed method is superior to the existing methods like Logistic regression and Discriminant analysis.

• 한국정밀공학회지
• /
• 제20권2호
• /
• pp.146-153
• /
• 2003

Ultrasonic inspection of defects has been focused on the existence of defect in structural material and need has much time and expenses in inspecting all the coordinates (x, y) on material surface. Neural networks can have an application to coordinates (x, y) of defects by multi-point inspection method. Ultrasonic inspection modeling is optimized by neural networks Neural networks has trained training example of absolute and relative coordinate of defects, and defect pattern. This method can predict coordinates (x, y) of defects within engineering estimated mean error $\psi$.

• Journal of Biosystems Engineering
• /
• 제39권4호
• /
• pp.310-317
• /
• 2014

Purpose: This study was conducted to analyze the air flow characteristics in a plant factory with different inlet and outlet locations using computational fluid dynamics (CFD). Methods: In this study, the flow was assumed to be a steady-state, incompressible, and three-dimensional turbulent flow. A realizable k-${\varepsilon}$ turbulent model was applied to show more reasonable results than the standard model. A CFD software was used to perform the numerical simulation. For validation of the simulation model, a prototype plant factory ($5,900mm{\times}2,800mm{\times}2,400mm$) was constructed with two inlets (${\Phi}250mm$) and one outlet ($710mm{\times}290mm$), located on the top side wall. For the simulation model, the average air current speed at the inlet was $5.11m{\cdot}s^{-1}$. Five cases were simulated to predict the airflow pattern in the plant factory with different inlet and outlet locations. Results: The root mean square error of measured and simulated air current speeds was 13%. The error was attributed to the assumptions applied to mathematical modelling and to the magnitude of the air current speed measured at the inlet. However, the measured and predicted airflow distributions of the plant factory exhibited similar patterns. When the inlets were located at the center of the side wall, the average air current speed in the plant factory was increased but the spatial uniformity was lowered. In contrast, if the inlets were located on the ceiling, the average air current speed was lowered but the uniformity was improved. Conclusions: Based on the results of this study, it was concluded that the airflow pattern in the plant factory with multilayer cultivation shelves was greatly affected by the locations of the inlet and the outlet.

• 한국도로학회논문집
• /
• 제19권2호
• /
• pp.35-44
• /
• 2017

PURPOSES: This study suggests a specific methodology for the prediction of road surface temperature using vehicular ambient temperature sensors. In addition, four kind of models is developed based on machine learning algorithms. METHODS : Thermal Mapping System is employed to collect road surface and vehicular ambient temperature data on the defined survey route in 2015 and 2016 year, respectively. For modelling, all types of collected temperature data should be classified into response and predictor before applying a machine learning tool such as MATLAB. In this study, collected road surface temperature are considered as response while vehicular ambient temperatures defied as predictor. Through data learning using machine learning tool, models were developed and finally compared predicted and actual temperature based on average absolute error. RESULTS : According to comparison results, model enables to estimate actual road surface temperature variation pattern along the roads very well. Model III is slightly better than the rest of models in terms of estimation performance. CONCLUSIONS : When correlation between response and predictor is high, when plenty of historical data exists, and when a lot of predictors are available, estimation performance of would be much better.

• Structural Monitoring and Maintenance
• /
• 제9권1호
• /
• pp.81-105
• /
• 2022

The use of concrete filled steel tube (CFST) column is widely accepted due to its property of high axial load carrying capacity, more ductility and more resistant to earthquake specially using in bridges and high-rise buildings. The initial imperfection (δ) that produces during casting or fixing causes the reduction in load carrying capacity, this is the reason, experimental capacity is always less then theoretical one. In this research, the effect of δ on load carrying capacity and behavior of concrete filled steel tube (CFST) column have been investigated by numerically simulation of large number of models with different δ and other geometric parameters that include length (L), width (B), steel tube thickness (t), f'_c and f_y. Finite element analysis software ANSYS v18 is used to develop model of SCFST column to evaluate strength capacity, buckling and failure pattern of member which is applied during experimental study under cyclic axial loading. After validation of results, 42 models with different parameters are evaluated to develop empirical equation predicting axial load carrying capacity for different value of δ. Results indicate that empirical equation shows the 0 to 9% error for finite element analysis Forty-two models in comparison with ANSYS results, respectively. Empirical equation can be used for predicting the axial capacity of early estimating the axial capacity of SCFT column including 𝛿.

• Structural Engineering and Mechanics
• /
• 제86권2호
• /
• pp.181-195
• /
• 2023

To predict the rheological behaviours along with the compressive strength of self-compacting concrete that incorporates environmentally friendly ingredients as cement substitutes, a comparative evaluation of machine learning methods is conducted. To model four parameters, slump flow diameter, L-box ratio, V-funnel time, as well as compressive strength at 28 days-a complete mix design dataset from available pieces of literature is gathered and used to construct the suggested machine learning standards, SVM, MARS, and Mp5-MT. Six input variables-the amount of binder, the percentage of SCMs, the proportion of water to the binder, the amount of fine and coarse aggregates, and the amount of superplasticizer are grouped in a particular pattern. For optimizing the hyper-parameters of the MARS model with the lowest possible prediction error, a gravitational search algorithm (GSA) is required. In terms of the correlation coefficient for modelling slump flow diameter, L-box ratio, V-funnel duration, and compressive strength, the prediction results showed that MARS combined with GSA could improve the accuracy of the solo MARS model with 1.35%, 11.1%, 2.3%, as well as 1.07%. By contrast, Mp5-MT often demonstrates greater identification capability and more accurate prediction in comparison to MARS-GSA, and it may be regarded as an efficient approach to forecasting the rheological behaviors and compressive strength of SCC in infrastructure practice.

• 지구물리와물리탐사
• /
• 제10권4호
• /
• pp.241-251
• /
• 2007

본격적인 지진관측 이래 최대 규모의 내륙 지진으로 기록된 오대산지진의 관측 스펙트럼을 이용하여, 점지진원 스펙트럼 모델의 지진원 크기 및 오차의 공간적인 특성을 평가하였다. 먼저 지진원 스펙트럼을 추정하기 위해, 최근까지 국내에 축적된 지진자료를 기반으로 비교적 상세하게 추정된 추계학적 지진동모델(Boore, 2003)의 지진파 전달, 부지특성(연관희, 2007)을 이용하여 관측 자료를 보정하였다. 추정된 오대산지진의 지진원 스펙트럼을 $1-f_c$(1개의 코너주파수) Brune의 ${\omega}^2$ 지진원모델에 적합한 결과, 기존에 제시된 지진규모-응력강하량 대표모델(연관희 등, 2006)에 의해 잘 예측되었으며, 오대산지진의 지진원 스펙트럼은 최근까지 한반도 인근에서 발생한 중규모 이상의 지진원 스펙트럼으로부터 추정된 $2-f_c$(2개의 코너주파수)의 경험적인 지진원모델에 보다 잘 부합되었다. 또한 일반적으로 무작위 잡음으로 취급되는 점지진원 지진파 스펙트럼 모델링 오차에 대해 방위각에 따른 방향성과 지역별 전달특성을 평가한 결과, 오차가 완전한 무작위 특성이 아님을 확인할 수 있었다. 이러한 모델링 오차의 방향성은 이론적으로 추정된 방사패턴과도 매우 유사한 관측된 방사패턴을 나타내었으며, 지역별로는 지질학적인 경계 혹은 지진파전달의 불연속적 특성과 밀접한 관계가 있는 것으로 판단되는 주파수별로 상이한 공간적인 분포 특성을 보여주었다.

• 한국기후변화학회지
• /
• 제6권4호
• /
• pp.331-344
• /
• 2015

A long-term gridded historical data at 3 km spatial resolution has been generated for practical regional applications such as hydrologic modelling. However, overly high or low values have been found at some grid points where complex topography or sparse observational network exist. In this study, the Inverse Distance Weighting (IDW) method was applied to properly smooth the overly predicted values of Improved GIS-based Regression Model (IGISRM), called the IDW-IGISRM grid data, at the same resolution for daily precipitation, maximum temperature and minimum temperature from 2001 to 2010 over South Korea. We tested various effective distances in the IDW method to detect an optimal distance that provides the highest performance. IDW-IGISRM was compared with IGISRM to evaluate the effectiveness of IDW-IGISRM with regard to spatial patterns, and quantitative performance metrics over 243 AWS observational points and four selected stations showing the largest biases. Regarding the spatial pattern, IDW-IGISRM reduced irrational overly predicted values, i. e. producing smoother spatial maps that IGISRM for all variables. In addition, all quantitative performance metrics were improved by IDW-IGISRM; correlation coefficient (CC), Index Of Agreement (IOA) increase up to 11.2% and 2.0%, respectively. Mean Absolute Error (MAE) and Root Mean Square Error (RMSE) were also reduced up to 5.4% and 15.2% respectively. At the selected four stations, this study demonstrated that the improvement was more considerable. These results indicate that IDW-IGISRM can improve the predictive performance of IGISRM, consequently providing more reliable high-resolution gridded data for assessment, adaptation, and vulnerability studies of climate change impacts.

• 한국지능시스템학회논문지
• /
• 제16권4호
• /
• pp.389-395
• /
• 2006

본 논문에서는 지능재어기법을 이용하여 이족로봇 제어기를 설계한다. 이족로봇 제어기는 복잡성을 해결하기 위해 4개 소 그룹으로 모듈화 하고, 이 모듈들은 신경망을 이용한 계층적 모듈라 신경망 (Hierarchical Mixture of Experts; HME) 기법을 도입한다. 그리고 신경망은 직접제어기법으로 이족로봇의 역 동력학을 학습한다. HME는 나무구조의 네트워크로 입출력 집합을 학습하여 출력공간에 대한 입력공간을 재분할하는 능력을 가지고 있다. EM 알고리즘을 이용한 HME는 반복적 학습을 통하여 이족로봇의 동력학을 모델링하며 HME 의 가상오차를 생성하여 이족로봇보행시 안전한 보행을 수행할 수 있는 이족로봇의 제어기를 설계한다.