• Journal of the Korean Geotechnical Society
• /
• v.39 no.4
• /
• pp.5-17
• /
• 2023

The advancement in large-scale underground excavation in urban areas necessitates monitoring and predicting technologies that can pre-emptively mitigate risk factors at construction sites. Traditionally, two methods predict the deformation of retaining walls induced by excavation: empirical and numerical analysis. Recent progress in artificial intelligence technology has led to the development of a predictive model using machine learning techniques. This study developed a model for predicting the deformation of a retaining wall under construction using a boosting-based algorithm and an ensemble model with outstanding predictive power and efficiency. A database was established using the data from the design-construction-maintenance process of the underground retaining wall project in a manifold manner. Based on these data, a learning model was created, and the performance was evaluated. The boosting and ensemble models demonstrated that wall deformation could be accurately predicted. In addition, it was confirmed that prediction results with the characteristics of the actual construction process can be presented using data collected from ground measurements. The predictive model developed in this study is expected to be used to evaluate and monitor the stability of retaining walls under construction.

• Journal of the Korean Geotechnical Society
• /
• v.22 no.11
• /
• pp.151-158
• /
• 2006

Centrifuge tests have shown that a uniformly placed sand layer will first initiate liquefaction near the surface and that liquefaction will progress downward during shaking. This appears to be in conflict with the overburden stress effect on soil liquefaction (i.e., $K_0$ effect) observed in laboratory testing. This discrepancy can be explained by stress-induced densification at depth which overcomes the effect of confining stress on liquefaction resistance. Stress densification occurs in centrifuge model tests but its effect has generally not been considered when preparing or evaluating centrifuge models. A new centrifuge model preparation method is proposed by considering stress-induced densification upon spin-up. The proposed method can be used to explore $K_0$ effects. The method is supported in this study by numerical predictions.

• Composites Research
• /
• v.19 no.6
• /
• pp.8-15
• /
• 2006

In this study, computational rotor dynamic analyses of a composite roller used for large LCD panel manufacturing process have been conducted. The present computational method is based on the general finite element method with rotating gyroscopic effects of rotor systems. General purpose commercial finite element code, SAMCEF which has special rotordynamics analysis module is applied. For the purpose of numerical verification, comparison study for a benchmark dual rotor model with support bearings is also presented. Detailed finite element models for composite roller with optimized lamination angles are constructed and analyzed considering gravity effect in order to investigate vibration characteristics in actual operation environment. As results of the present study, rotor stability diagrams and mass unbalance responses are presented for different rotating conditions.

• Journal of the Korea Society of Computer and Information
• /
• v.14 no.8
• /
• pp.1-9
• /
• 2009

In this paper, make a study decision problem called an optimal release policies after testing a software system in development phase and transfer it to the user. When correcting or modifying the software, because of the possibility of introducing new faults when correcting or modifying the software, infinite failure non-homogeneous Poisson process models presented and propose an optimal release policies of the life distribution applied fixed shape parameter distribution which can capture the increasing/decreasing nature of the failure occurrence rate per fault. In this paper, discuss optimal software release policies which minimize a total average software cost of development and maintenance under the constraint of satisfying a software reliability requirement. In a numerical example, after trend test applied and estimated the parameters using maximum likelihood estimation of inter-failure time data, make out estimating software optimal release time

• Nuclear Engineering and Technology
• /
• v.55 no.4
• /
• pp.1382-1399
• /
• 2023

Pressure relief valve (PRV) is one of the important control valves used in nuclear power plants, and its sealing performance is crucial to ensure the safety and function of the entire pressure system. For the sealing performance improving purpose, an explicit function that accounts for all design parameters and can accurately describe the relationship between the multi-design parameters and the seal performance is essential, which is also the challenge of the valve seal design and/or optimization work. On this basis, a surrogate model-based design optimization is carried out in this paper. To obtain the basic data required by the surrogate model, both the Finite Element Model (FEM) and the Computational Fluid Dynamics (CFD) based numerical models were successively established, and thereby both the contact stresses of valve static sealing and dynamic impact (between valve disk and nozzle) could be predicted. With these basic data, the polynomial chaos expansion (PCE) surrogate model which can not only be used for inputs-outputs relationship construction, but also produce the sensitivity of different design parameters were developed. Based on the PCE surrogate model, a new design scheme was obtained after optimization, in which the valve sealing stress is increased by 24.42% while keeping the maximum impact stress lower than 90% of the material allowable stress. The result confirms the ability and feasibility of the method proposed in this paper, and should also be suitable for performance design optimizations of control valves with similar structures.

• Structural Engineering and Mechanics
• /
• v.86 no.4
• /
• pp.547-571
• /
• 2023

To deeply probe the actual earthquake level and fragility of typical reinforced concrete (RC) structures under multiple intensity grades, considering diachronic measurement building stock samples and actual observations of representative catastrophic earth shocks in China from 1990 to 2010, RC structures were divided into traditional RC structures (TRCs) and bottom reinforced concrete frame seismic wall masonry (BFM) structures, and the empirical damage characteristics and mechanisms were analysed. A great deal of statistics and induction were developed on the historical experience investigation data of 59 typical catastrophic earthquakes in 9 provinces of China. The database and fragility matrix prediction model were established with TRCs of 4,122.5284×104 m² and 5,844 buildings and BFMs of 5,872 buildings as empirical seismic damage samples. By employing the methods of structural damage probability and statistics, nonlinear prediction of seismic vulnerability, and numerical and applied functional analysis, the comparison matrix of actual fragility probability prediction of TRC and BFM in multiple intensity regions under the latest version of China's macrointensity standard was established. A novel nonlinear regression prediction model of seismic vulnerability was proposed, and prediction models considering the seismic damage ratio and transcendental probability parameters were constructed. The time-varying vulnerability comparative model of the sample database was developed according to the different periods of multiple earthquakes. The new calculation method of the average fragility prediction index (AFPI) matrix parameter model has been proposed to predict the seismic fragility of an areal RC structure.

• Asia-pacific Journal of Multimedia Services Convergent with Art, Humanities, and Sociology
• /
• v.8 no.3
• /
• pp.57-67
• /
• 2018

The ensemble is a unified approach used for getting better performance by using multiple algorithms in machine learning. In this paper, we introduce boosting and bagging, which have been widely used in ensemble techniques, and design a method using support vector regression, radial basis function network, Gaussian process, and multilayer perceptron. In addition, our experiment was performed by adding a recurrent neural network and MOHID numerical model. The drifter data used for our experimental verification consist of 683 observations in seven regions. The performance of our ensemble technique is verified by comparison with four algorithms each. As verification, mean absolute error was adapted. The presented methods are based on ensemble models using bagging, boosting, and machine learning. The error rate was calculated by assigning the equal weight value and different weight value to each unit model in ensemble. The ensemble model using machine learning showed 61.7% improvement compared to the average of four machine learning technique.

• Journal of the Korean Society of Food Culture
• /
• v.25 no.6
• /
• pp.779-787
• /
• 2010

The principal objective of this study was to determine the optimal mixing conditions for three amounts of onion powder, sugar, and butter to prepare onion powder cookies. The experimental design was based on the central composite design methodology of response surface, which included 16 experimental points including two replicates for onion powder, sugar, and butter. The mechanical and sensory properties of the cookies were measured, and these values were applied to the mathematical models. A canonical form and perturbation plot showed the influence of each ingredient on the mixed final product. The results of the spread ratio did not show significant results, but hardness increased with increasing quantities of onion powder and sugar but decreased with butter (p<0.01). The color lightness "L" value increased with increasing quantities of sugar and butter but decreased with added onion powder. In contrast, the redness color "a" value increased with increasing quantities of onion powder and sugar. Sugar did not affect the yellowness color "b" value, but the color b value increased with increasing onion powder and sugar. The results of a sensory evaluation using the predicted model showed significant values for flavor (p<0.01), texture (p<0.05), taste (p<0.05), and overall quality (p<0.01). As a result, the optimum formulation by numerical and graphical methods was calculated as 12.58 g onion powder, 35 g sugar, and 52.38 g butter.

• Structural Engineering and Mechanics
• /
• v.85 no.4
• /
• pp.433-443
• /
• 2023

The current paper discusses the dynamic and stability responses of cross-ply composite laminated plates by employing a refined quasi-3D trigonometric shear deformation theory. The proposed theory takes into consideration shear deformation and thickness stretching by a trigonometric variation of in-plane and transverse displacements through the plate thickness and assures the vanished shear stresses conditions on the upper and lower surfaces of the plate. The strong point of the new formulation is that the displacements field contains only 4 unknowns, which is less than the other shear deformation theories. In addition, the present model considers the thickness extension effects (ε_z≠0). The presence of the Winkler-Pasternak elastic base is included in the mathematical formulation. The Hamilton's principle is utilized in order to derive the four differentials' equations of motion, which are solved via Navier's technique of simply supported structures. The accuracy of the present 3-D theory is demonstrated by comparing fundamental frequencies and critical buckling loads numerical results with those provided using other models available in the open literature.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.26 no.5C
• /
• pp.359-368
• /
• 2006

After construction, time-variant seepage and long-term underground motion are representative factors to understand the abnormal behavior of tunnels. In this study, numerical models have been developed to analyze the behavior of tunnels associated with seepage and long-term underground motion. Possible scenarios have been investigated to establish causes-and-results mechanisms. Various parameters such as permeability of tunnel filter, seepage condition, water table, long-term rock mass load, size of damaged zone due to excessive blasting have been investigated. These are divided into two sub-parts depending on the tunnel type and major loading mechanisms depending on the types. For the soft ground tunnels, the behavior associated with seepage conditions has been studied and the effect of permeability change in tunnel-filter and the effect of water-table change which are seldom measurable are investigated in detail. For the rock mass tunnels, tunnel behavior associated with the visco-plastic behavior of rock mass has been studied and the long-term rock mass loads as a result of relaxation and creep have been considered.