• Journal of Korean Association for Spatial Structures
• /
• v.23 no.4
• /
• pp.81-88
• /
• 2023

Numerous factors contribute to the deterioration of reinforced concrete structures. Elevated temperatures significantly alter the composition of the concrete ingredients, consequently diminishing the concrete's strength properties. With the escalation of global CO2 levels, the carbonation of concrete structures has emerged as a critical challenge, substantially affecting concrete durability research. Assessing and predicting concrete degradation due to thermal effects and carbonation are crucial yet intricate tasks. To address this, multiple prediction models for concrete carbonation and compressive strength under thermal impact have been developed. This study employs seven machine learning algorithms-specifically, multiple linear regression, decision trees, random forest, support vector machines, k-nearest neighbors, artificial neural networks, and extreme gradient boosting algorithms-to formulate predictive models for concrete carbonation and thermal impact. Two distinct datasets, derived from reported experimental studies, were utilized for training these predictive models. Performance evaluation relied on metrics like root mean square error, mean square error, mean absolute error, and coefficient of determination. The optimization of hyperparameters was achieved through k-fold cross-validation and grid search techniques. The analytical outcomes demonstrate that neural networks and extreme gradient boosting algorithms outshine the remaining five machine learning approaches, showcasing outstanding predictive performance for concrete carbonation and thermal effect modeling.

• Journal of the Society of Naval Architects of Korea
• /
• v.56 no.6
• /
• pp.488-496
• /
• 2019

The estimation of block erection work time at a dock is one of the important factors when establishing or managing the total shipbuilding schedule. In order to predict the work time, it is a natural approach that the existing block erection data would be used to solve the problem. Generally the work time per unit is the product of coefficient value, quantity, and product value. Previously, the work time per unit is determined statistically by unit load data. However, we estimate the work time per unit through work time coefficient value from series ships using machine learning. In machine learning, the outcome depends mainly on how the training data is organized. Therefore, in this study, we use 'Feature Engineering' to determine which one should be used as features, and to check their influence on the result. In order to get the coefficient value of each block, we try to solve this problem through the Ensemble learning methods which is actively used nowadays. Among the many techniques of Ensemble learning, the final model is constructed by Stacking Ensemble techniques, consisting of the existing Ensemble models (Decision Tree, Random Forest, Gradient Boost, Square Loss Gradient Boost, XG Boost), and the accuracy is maximized by selecting three candidates among all models. Finally, the results of this study are verified by the predicted total work time for one ship among the same series.

• Fire Science and Engineering
• /
• v.29 no.5
• /
• pp.1-6
• /
• 2015

Flash point is one of the most important variables used to characterize fire and explosion hazard of liquids. The lower flash point data were measured for the binary systems {methanol + 1-butanol}, {ethanol + 1-butanol} and {2-propanol + 1-butanol} at 101.3 kPa. Experiments were performed according to the standard test method (ASTM D 3278) using a SETA closed cup flash point tester. The measured flash points were compared with the predicted values calculated using the following activity coefficient models: Wilson, Non-Random Two Liquid (NRTL), and UNIversal QUAsiChemical (UNIQUAC). The measured FP data agreed well with the predicted values of Raoult's law, Wilson, NRTL and UNIQUAC models. The average absolute deviation between the predicted and measured lower FP was less than 1.14 K.

• Water Engineering Research
• /
• v.3 no.1
• /
• pp.31-44
• /
• 2002

The effect of diurnal cycle, intermittent visit of observation satellite, sensor installation, partial coverage of remote sensing, heterogeneity of soil properties and precipitation to the soil moisture estimation error were analyzed to present the global sampling strategy of soil moisture. Three models, the theoretical soil moisture model, WGR model proposed Waymire of at. (1984) to generate rainfall, and Turning Band Method to generate two dimensional soil porosity, active soil depth and loss coefficient field were used to construct sufficient two-dimensional soil moisture data based on different scenarios. The sampling error is dominated by sampling interval and design scheme. The effect of heterogeneity of soil properties and rainfall to sampling error is smaller than that of temporal gap and spatial gap. Selecting a small sampling interval can dramatically reduce the sampling error generated by other factors such as heterogeneity of rainfall, soil properties, topography, and climatic conditions. If the annual mean of coverage portion is about 90%, the effect of partial coverage to sampling error can be disregarded. The water retention capacity of fields is very important in the sampling error. The smaller the water retention capacity of the field (small soil porosity and thin active soil depth), the greater the sampling error. These results indicate that the sampling error is very sensitive to water retention capacity. Block random installation gets more accurate data than random installation of soil moisture gages. The Walnut Gulch soil moisture data show that the diurnal variation of soil moisture causes sampling error between 1 and 4 % in daily estimation.

• Journal of Ocean Engineering and Technology
• /
• v.18 no.4 s.59
• /
• pp.23-32
• /
• 2004

Specially shaped concrete blocks are used for the armor layer of rubble structure for breakers, seawalls, or other shore protection work. In this study, the hydraulic characteristics of the Modified-Tribar(MTB), which addresses the shortcomings of the Arch-Tribar, and the most widely used Tetrapod(TTP) in Korea are examined through hydraulic model tests. The MTB are much more stable than the TTP, as shown through the stability model tests under non-breaking and non-overtopping condition. The value of the stability coefficient(KD) was obtained at around 30. The model tests show that the TTP random two layers and MTB uniform 1.5 layers have similar effects, but the MTB one layer shows slightly low effects in dissipating wave energy. The TTP random two layer model is the most effective in reducing wave overtopping rate, under overtopping condition, while the MTB uniform one layer and the MTB uniform 1.5 layer models follow respectively.

• Journal of the Korean Crystal Growth and Crystal Technology
• /
• v.15 no.1
• /
• pp.27-33
• /
• 2005

In this study, the process parameters in ceramics powder compaction are optimized for getting high relative densities of ceramic products. To find optimized parameters, the analytic models of powder compaction are firstly prepared by 2-dimensional rod arrays with random green densities using a quasi-random multiparticle array. Then, using finite element method, the changes in relative densities are analyzed by varying the size of Al₂O₃ particle, the amplitude of cyclic compaction, and the coefficient of friction, which influence the relative density in cyclic compactions. After the analytic function of relative density associated process parameters are formulated by aid of the response surface method, the optimal conditions in powder compaction process are found by the grid search method. When the particle size of Al₂O₃ is 22.5 ㎛, the optimal parameters for the amplitude of cyclic compaction and the coefficient of friction are 75 MPa and 0.1103, respectively. The maximum relative density is 0.9390.

• Journal of the Korean Data and Information Science Society
• /
• v.15 no.4
• /
• pp.743-752
• /
• 2004

In this paper, we develop the Bayesian model selection procedure using the reference prior for comparing two nested model such as the independent and intraclass models using the distance or divergence between the two as the basis of comparison. A suitable criterion for this is the power divergence measure as introduced by Cressie and Read(1984). Such a measure includes the Kullback -Liebler divergence measures and the Hellinger divergence measure as special cases. For this problem, the power divergence measure turns out to be a function solely of $\rho$, the intraclass correlation coefficient. Also, this function is convex, and the minimum is attained at $\rho=0$. We use reference prior for $\rho$. Due to the duality between hypothesis tests and set estimation, the hypothesis testing problem can also be solved by solving a corresponding set estimation problem. The present paper develops Bayesian method based on the Kullback-Liebler and Hellinger divergence measures, rejecting $H_0:\rho=0$ when the specified divergence measure exceeds some number d. This number d is so chosen that the resulting credible interval for the divergence measure has specified coverage probability $1-{\alpha}$. The length of such an interval is compared with the equal two-tailed credible interval and the HPD credible interval for $\rho$ with the same coverage probability which can also be inverted into acceptance regions of $H_0:\rho=0$. Example is considered where the HPD interval based on the one-at- a-time reference prior turns out to be the shortest credible interval having the same coverage probability.

• Tunnel and Underground Space
• /
• v.32 no.6
• /
• pp.586-597
• /
• 2022

In this study, a model was developed for the estimating the locational thickness information of the upper clay layer to be used for the consolidation vulnerability evaluation in the Nakdong river estuary. To estimate ground layer thickness information, we developed four spatial estimation models using machine learning algorithms, which are RF (Random Forest), SVR (Support Vector Regression) and GPR (Gaussian Process Regression), and geostatistical technique such as Ordinary Kriging. Among the 4,712 borehole data in the study area collected for model development, 2,948 borehole data with an upper clay layer were used, and Pearson correlation coefficient and mean squared error were used to quantitatively evaluate the performance of the developed models. In addition, for qualitative evaluation, each model was used throughout the study area to estimate the information of the upper clay layer, and the thickness distribution characteristics of it were compared with each other.

• International Journal of Concrete Structures and Materials
• /
• v.9 no.2
• /
• pp.159-172
• /
• 2015

Estimation of the residual strength of corroded reinforced concrete beams has been studied from experimental and theoretical perspectives. The former is arduous as it involves casting beams of various sizes, which are then subjected to various degrees of corrosion damage. The latter are static; hence cannot be generalized as new coefficients need to be re-generated for new cases. This calls for dynamic models that are adaptive to new cases and offer efficient generalization capability. Computational intelligence techniques have been applied in Construction Engineering modeling problems. However, these techniques have not been adequately applied to the problem addressed in this paper. This study extends the empirical model proposed by Azad et al. (Mag Concr Res 62(6):405-414, 2010), which considered all the adverse effects of corrosion on steel. We proposed four artificial neural networks (ANN) models to predict the residual flexural strength of corroded RC beams using the same data from Azad et al. (2010). We employed two modes of prediction: through the correction factor ($C_f$) and through the residual strength ($M_{res}$). For each mode, we studied the effect of fixed and random data stratification on the performance of the models. The results of the ANN models were found to be in good agreement with experimental values. When compared with the results of Azad et al. (2010), the ANN model with randomized data stratification gave a $C_f$-based prediction with up to 49 % improvement in correlation coefficient and 92 % error reduction. This confirms the reliability of ANN over the empirical models.

• Journal of Forest and Environmental Science
• /
• v.39 no.4
• /
• pp.195-202
• /
• 2023

In this study, we sought to compare and evaluate the accuracy and predictive performance of machine learning algorithms for estimating the growth of individual Larix kaempferi trees in Gangwon Province, Korea. We employed linear regression, random forest, XGBoost, and LightGBM algorithms to predict tree growth using monitoring data organized based on different thinning intensities. Furthermore, we compared and evaluated the goodness-of-fit of these models using metrics such as the coefficient of determination (R²), mean absolute error (MAE), and root mean square error (RMSE). The results revealed that XGBoost provided the highest goodness-of-fit, with an R² value of 0.62 across all thinning intensities, while also yielding the lowest values for MAE and RMSE, thereby indicating the best model fit. When predicting the growth volume of individual trees after 3 years using the XGBoost model, the agreement was exceptionally high, reaching approximately 97% for all stand sites in accordance with the different thinning intensities. Notably, in non-thinned plots, the predicted volumes were approximately 2.1 m³ lower than the actual volumes; however, the agreement remained highly accurate at approximately 99.5%. These findings will contribute to the development of growth prediction models for individual trees using machine learning algorithms.