• Journal of the Computational Structural Engineering Institute of Korea
• /
• v.36 no.6
• /
• pp.391-398
• /
• 2023

In this paper, a penalized maximum likelihood estimation (PMLE) method that applies a penalty to increase the accuracy of a basis-screening-based Kriging model (BSKM) is introduced. The maximum order and set of basis functions used in the BSKM are determined according to their importance. In this regard, the cross-validation error (CVE) for the basis functions is employed as an indicator of importance. When constructing the Kriging model (KM), the maximum order of basis functions is determined, the importance of each basis function is evaluated according to the corresponding maximum order, and finally the optimal set of basis functions is determined. This optimal set is created by adding basis functions one by one in order of importance until the CVE of the KM is minimized. In this process, the KM must be generated repeatedly. Simultaneously, hyper-parameters representing correlations between datasets must be calculated through the maximum likelihood evaluation method. Given that the optimal set of basis functions depends on such hyper-parameters, it has a significant impact on the accuracy of the KM. The PMLE method is applied to accurately calculate hyper-parameters. It was confirmed that the accuracy of a BSKM can be improved by applying it to Branin-Hoo problem.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.28 no.11
• /
• pp.1760-1767
• /
• 2004

Sequential sampling approaches of a metamodel that sampling points are updated sequentially become a significant consideration in metamodeling technique. Sequential sampling design is more effective than classical space filling design of all-at-once sampling because sequential sampling design is to add new sampling points by means of distance between sampling points or precdiction error obtained from metamodel. However, though the extremum points can strongly reflect the behaviors of responses, the existing sequential sampling designs are inefficient to approximate extremum points of original model. In this research, new sequential sampling approach using the sensitivity of Kriging model is proposed, so that new approach reflects the behaviors of response sequentially. Various sequential sampling designs are reviewed and the performances of the proposed approach are compared with those of existing sequential sampling approaches by using mean squared error. The accuracy of the proposed approach is investigated against optimization results of test problems so that superiority of the sensitivity approach is verified.

• Journal of Ocean Engineering and Technology
• /
• v.34 no.5
• /
• pp.316-324
• /
• 2020

This paper presents comparative studies of reliability analysis and meta-modeling using the sampling method of Monte Carlo simulation for the structure design of an automatic ocean salt collector (AOSC). The thickness sizing variables of structure members are considered as random variables. Probabilistic performance functions are selected from strength performances evaluated via the finite element analysis of an AOSC. The sampling methods used in the comparative studies are simple random sampling and Sobol sequences with varied numbers of sampling. Approximation methods such as the Kriging model is applied to the meta-model generation. Reliability performances such as the probability failure and distribution are compared based on the variation of the sampling method of Monte Carlo simulation. The meta-modeling accuracy is evaluated for the Kriging model generated from the Monte Carlo simulation and Sobol sequence results. It is discovered that the Sobol sequence method is applicable to not only to the reliability analysis for the structural design of marine equipment such as the AOSC, but also to Kriging meta-modeling owing to its high numerical efficiency.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.30 no.4 s.247
• /
• pp.465-472
• /
• 2006

Recently, the regulations of the government and the concerns of people have rise to the interest in noise pollution levels as compared to other vehicles. In this area, many researchers have studied to reduce this noise in the field of automotive engineering. This paper proposes an optimal design scheme to reduce the noise of the intake system by adapting Kriging with two meta-heuristic techniques. For this, as a measuring tool for the performance of the intake system, the performance prediction software, was used. Then, the length and radius of each component of the current intake system are selected as input variables and the orthogonal arrays is adapted as a space-filling design. With these simulated data, we can estimate a correlation parameter in Kriging by solving the nonlinear problem with a genetic algorithm and find an optimal level for the intake system by optimizing Kriging estimated with simulated annealing. We notice that this optimal design scheme gives noticeable results and is a preferable way to analyze the intake system. Therefore, an optimal design for the intake system is proposed by reducing the noise of its system.

• The Korean Journal of Applied Statistics
• /
• v.18 no.2
• /
• pp.271-280
• /
• 2005

Kriging methods as traditional spatial data analysis methods and geographical weighted regression models as statistical analysis methods are compared. In this paper, we apply data from the Ministry of Environment to spatial analysis for practical study. We compare these methods to performance with monthly carbon monoxide observations taken at 116 measuring area of air pollution in 1999.

• Transactions of the Korean Society of Mechanical Engineers B
• /
• v.34 no.7
• /
• pp.703-714
• /
• 2010

This paper describes the design optimization of a rotating rectangular channel with staggered arrays of pin-fins by Kriging metamodeling technique. Two non-dimensional variables, the ratio of the height to the diameter of the pin-fins and the ratio of the spacing between the pin-fins to the diameter of the pin-fins are chosen as the design variables. The objective function that is a linear combination of heat transfer and friction loss related terms with a weighting factor is selected for the optimization. To construct the Kriging model, objective function values at 20 training points generated by Latin hypercube sampling are evaluated by a three-dimensional Reynolds-averaged Navier-Stokes (RANS) analysis method with the SST turbulence model. The Kriging model predicts the objective function value that agrees well with the value calculated by the RANS analysis at the optimum point. The objective function is reduced by 11% by the optimization of the channel.

• Journal of Korea Water Resources Association
• /
• v.50 no.10
• /
• pp.681-690
• /
• 2017

This study estimated the daily maximum snow depth using the Artificial Neural Network (ANN) model in Korean Peninsula. First, the optimal ANN model structure was determined through the trial-and-error approach. As a result, daily precipitation, daily mean temperature, and daily minimum temperature were chosen as the input data of the ANN. The number of hidden layer was set to 1 and the number of nodes in the hidden layer was set to 10. In case of using the observed value as the input data of the ANN model, the cross validation correlation coefficient was 0.87, which is higher than that of the case in which the daily maximum snow depth was spatially interpolated using the Ordinary Kriging method (0.40). In order to investigate the performance of the ANN model for estimating the daily maximum snow depth of the ungauged area, the input data of the ANN model was spatially interpolated using Ordinary Kriging. In this case, the correlation coefficient of 0.49 was obtained. The performance of the ANN model in mountainous areas above 200m above sea level was found to be somewhat lower than that in the rest of the study area. This result of this study implies that the ANN model can be used effectively for the accurate and immediate estimation of the maximum snow depth over the whole country.

• Transactions of Materials Processing
• /
• v.29 no.5
• /
• pp.241-250
• /
• 2020

In this study, the methodology of the springback prediction of automotive parts applied 3rd generation AHSS was investigated using the response surface model analysis based on a regression model, and the meta model analysis based on a Kriging model. To design the learning data set for constructing the springback prediction models, and the experimental design was conducted at three levels for each processing variable using the definitive screening designs method. The hat-shaped member, which is the basic shape of the member parts, was selected and the springback values were measured for each processing type and processing variable using the finite element analysis. When the nonlinearity of the variables is small during the hat-shaped member forming, the response surface model and the meta model can provide the same processing parameter. However, the accuracy of the springback prediction of the meta model is better than the response surface model. Even in the case of the simple shape parts forming, the springback prediction accuracy of the meta model is better than that of the response surface model, when more variables are considered and the nonlinearity effect of the variables is large. The efficient global optimization algorithm-based Kriging is appropriate in resolving the high computational complexity optimization problems such as developing automotive parts.

• Transactions of the Society of Information Storage Systems
• /
• v.2 no.3
• /
• pp.169-177
• /
• 2006

In this study, we present the optimization of a head slider using kriging method in order to reduce lift-off force during unloading process with satisfying reliable flying attitude in steady state. To perform an optimization process efficiently, a simplified lift-off force model, which is a function of air bearing suction force and flying attitudes, is created by kriging method. The EMDIOS, which is the process integration and design optimization software developed by iDOT, is used to automatically wrap the analysis with the optimization and efficiently implements the repetitive works between analyzer and optimizer. An optimization problem is formulated to reduce the lift-off force during unloading process while satisfying the flying attitude in reliable range over the entire recording band and reducing the probability of contact between slider and disk. The simulation result shows that the amplitude of lift-off force of optimized L/UL slider is reduced about 62%, compared with that of initial slider model. It is demonstrated by the dynamics L/UL simulation that the optimum slider incorporated with the suspension is not only smoothly loaded onto disk but also properly unloaded onto the ramp.

• Computers and Concrete
• /
• v.27 no.4
• /
• pp.305-317
• /
• 2021

The bond between the concrete and bar is a main factor affecting the performance of the reinforced concrete (RC) members, and since the steel corrosion reduces the bond strength, studying the bond behavior of concrete and GFRP bars is quite necessary. In this research, a database including 112 concrete beam test specimens reinforced with spliced GFRP bars in the splitting failure mode has been collected and used to estimate the concrete-GFRP bar bond strength. This paper aims to accurately estimate the bond strength of spliced GFRP bars in concrete beams by applying three soft computing models including multivariate adaptive regression spline (MARS), Kriging, and M5 model tree. Since the selection of regularization parameters greatly affects the fitting of MARS, Kriging, and M5 models, the regularization parameters have been so optimized as to maximize the training data convergence coefficient. Three hybrid model coupling soft computing methods and genetic algorithm is proposed to automatically perform the trial and error process for finding appropriate modeling regularization parameters. Results have shown that proposed models have significantly increased the prediction accuracy compared to previous models. The proposed MARS, Kriging, and M5 models have improved the convergence coefficient by about 65, 63 and 49%, respectively, compared to the best previous model.