• Journal of Mechanical Science and Technology
• /
• v.20 no.8
• /
• pp.1169-1182
• /
• 2006

Robust design technology has been applied to versatile engineering problems to ensure consistency in product performance. Since 1980s, the concept of robust design has been introduced to numerical optimization field, which is called the robust optimization. The robustness in the robust optimization is determined by a measure of insensitiveness with respect to the variation of a response. However, there are significant difficulties associated with the calculation of variations represented as its mean and variance. To overcome the current limitation, this research presents an implementation of the approximate statistical moment method based on kriging metamodel. Two sampling methods are simultaneously utilized to obtain the sequential surrogate model of a response. The statistics such as mean and variance are obtained based on the reliable kriging model and the second-order statistical approximation method. Then, the simulated annealing algorithm of global optimization methods is adopted to find the global robust optimum. The mathematical problem and the two-bar design problem are investigated to show the validity of the proposed method.

• Communications for Statistical Applications and Methods
• /
• v.25 no.6
• /
• pp.619-631
• /
• 2018

Functional data analysis continues to attract interest because advances in technology across many fields have increasingly permitted measurements to be made from continuous processes on a discretized scale. Particulate matter is among the most harmful air pollutants affecting public health and the environment, and levels of PM10 (particles less than 10 micrometers in diameter) for regions of California remain among the highest in the United States. The relatively high frequency of particulate matter sampling enables us to regard the data as functional data. In this work, we investigate the dominant modes of variation of PM10 using functional data analysis methodologies. Our analysis provides insight into the underlying data structure of PM10, and it captures the size and temporal variation of this underlying data structure. In addition, our study shows that certain aspects of size and temporal variation of the underlying PM10 structure are associated with changes in large-scale climate indices that quantify variations of sea surface temperature and atmospheric circulation patterns.

• 제어로봇시스템학회:학술대회논문집
• /
• 2000.10a
• /
• pp.391-391
• /
• 2000

Manufacturing process generally exhibits major or minor variations due to deviation of raw materials, equipment degradation, controller malfunction, and so on. Extensive research based on multivariate statistical process control has been done to monitor the unstable states and indicate a corrective action. A prototype of intelligent operation support system ("ISYS-MSPC") has been developed as a tool that supports the enhanced operation to guarantee the high productivity and a uniform high quality product. This system has been applied to the industrial batch and continuous processes and its performance has been validated .

• Proceedings of the Korean Fiber Society Conference
• /
• 2003.10b
• /
• pp.291-292
• /
• 2003

Although the tensile strength of textile materials are determined by that of their components, it is well known that the tensile strength of fiber bundles and yams is not accurately predicted from that of single-fibers by simple averaging methods or mathematical calculations, because of variations in their strength. Therefore, there have been attempts to interpret the bundle strength from that of its elements by the stochastical approach. (omitted)

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.31 no.4A
• /
• pp.323-329
• /
• 2011

Most current design codes of concrete structures adopt the partial safety factor format to assure the proper safety margin or reliability against various limit states as a practical design tool. The safety factors, load and resistance factors and so on, are determined based on the theory of structural reliability, which takes into account the statistical uncertainties of both loads and resistances. The establishment of statistical models for load and resistance should be preceded the application of reliability theory. In this paper, especially the influence of the statistical variations of resistance models, which are described in terms of strength of concrete, strength of reinforcements and sectional dimensions and so on, are examined and the probabilistic models for resistance of reinforced concrete members were developed. The statistical data were collected on local tests and experiments in Korea and the Monte Carlo simulation (MCS) technique was used. The results of this paper may be useful and valuable in calibration of design code in this country.

• The Korean Journal of Applied Statistics
• /
• v.23 no.3
• /
• pp.457-469
• /
• 2010

The government real estate policy has repeatedly relaxed and reinforced controls under the mutually contradictory targets. Switching over the supporting policy after the IMF crisis to the regulating policy from 2003, the government housing policy began to generate ill effects due to various regulations. This stud carefully investigates and statistically tests the transmissions of variations in the housing prices between the metropolitan areas in the early stage of the preceding administration, under the effect of the supporting scheme, and those in the late stage, under the effect of the restricting scheme. The distinctive feature between the two periods is found to be much simplified interrelationships of the price variations in the latter period. Consolidated leading role of capital sphere, by concentrated economic strength, suggest the obvious imbalance between variations in the metropolis housing prices.

• Geomechanics and Engineering
• /
• v.22 no.4
• /
• pp.339-348
• /
• 2020

The uncertain geotechnical properties of frozen soil are important evidence for the design, operation and maintenance of the frozen ground. The complex geological, environmental and physical effects can lead to the spatial variations of the frozen soil, and the uncertain mechanical properties are the key factors for the uncertain analysis of frozen soil engineering. In this study, the elastic modulus, strength and Poisson ratio of warm frozen soil were measured, and the statistical characteristics under different temperature conditions are obtained. The autocorrelation distance (ACD) and autocorrelation function (ACF) of uncertain mechanical properties are estimated by random field (RF) method. The results show that the mean elastic modulus and mean strength decrease with the increase of temperature while the mean Poisson ratio increases with the increase of temperature. The average values of the ACD for the elastic modulus, strength and Poisson ratio are 0.64m, 0.53m and 0.48m, respectively. The standard deviation of the ACD for the elastic modulus, strength and Poisson ratio are 0.03m, 0.07m and 0.03m, respectively. The ACFs of elastic modulus, strength and Poisson ratio decrease with the increase of ratio of local average distance and scale of fluctuation. The ACF of uncertain mechanical properties is different when the temperature is different. This study can improve our understanding of the spatial autocorrelation variations of uncertain geotechnical properties and provide a basis and reference for the uncertain settlement analysis of frozen soil foundation.

• Radiation Oncology Journal
• /
• v.31 no.1
• /
• pp.41-47
• /
• 2013

Purpose: To describe the early experience of analyzing variations and time trends in bladder volume of the rectal cancer patients who received bladder ultrasound scan. Materials and Methods: We identified 20 consecutive rectal cancer patients who received whole pelvic radiotherapy (RT) and bladder ultrasound scan between February and April 2012. Before simulation and during the entire course of treatment, patients were scanned with portable automated ultrasonic bladder scanner, 5 times consecutively, and the median value was reported. Then a radiation oncologist contoured the bladder inner wall shown on simulation computed tomography (CT) and calculated its volume. Results: Before simulation, the median bladder volume measured using simulation CT and bladder ultrasound scan was 427 mL (range, 74 to 1,172 mL) and 417 mL (range, 147 to 1,245 mL), respectively. There was strong linear correlation (R = 0.93, p < 0.001) between the two results. During the course of treatment, there were wide variations in the bladder volume and every time, measurements were below the baseline with statistical significance (12/16). At 6 weeks after RT, the median volume was reduced by 59.3% to 175 mL. Compared to the baseline, bladder volume was reduced by 38% or 161 mL on average every week for 6 weeks. Conclusion: To our knowledge, this study is the first to prove that there are bladder volume variations and a reduction in bladder volume in rectal cancer patients. Moreover, our results will serve as the basis for implementation of bladder training to patients receiving RT with full bladder.

• The Korean Journal of Applied Statistics
• /
• v.24 no.2
• /
• pp.239-251
• /
• 2011

The need for statistical analysis to discern the existence and the type of international business comovement has increased as business and economic variations in one country is directly transmitted to business and financial market conditions in another without a long lag. This study performs the statistical tests for th locomotive hypothesis to understand the structural character of the long-run mechanism among Korea-US current and future business movements and the domestic stock market. The U.S. future business prospect, rather than the US current and the domestic current and future business conditions, appears to signi cantl a ect the domestic stock market movement.

• The Korean Journal of Applied Statistics
• /
• v.26 no.3
• /
• pp.401-411
• /
• 2013

This study investigates the controversial chickens-eggs dilemma and empirically performs statistical tests to examine if there exists a causality between them. Granger and Hsiao tests are applied to both level and stationary variables to identify the lead-lag relationships. Each of these test is found to have the robust result where the causality runs from eggs to chickens; in addition, the explanatory power of one variable in variations of the other appears to remain time invariant. The outcome is proved to be valid as the hypothesis test for no structural change in their relationship fails to be rejected.