• The Korean Journal of Applied Statistics
• /
• v.26 no.6
• /
• pp.915-922
• /
• 2013

Quantile regression can estimate multiple conditional quantile functions of the response, and as a result, it provide comprehensive information of the relationship between the response and the predictors. However, when estimating several conditional quantile functions separately, two or more estimated quantile functions may cross or overlap and consequently violate the basic properties of quantiles. In this paper, we propose a new stepwise method to estimate multiple non-crossing quantile functions using constraints on the kernel coefficients. A simulation study are presented to demonstrate satisfactory performance of the proposed method.

• 한국신재생에너지학회:학술대회논문집
• /
• 2006.06a
• /
• pp.281-286
• /
• 2006

본 연구의 목적은 차세대 대체에너지로 각광받는 풍력발전 중에서 육상발전보다 여러 가지 이점이 있는 한국형 해상풍력터빈 블레이드의 최적형상설계를 위한 알고리즘을 구현하는 것이다. 블레이드 단면 익형의 양력과 항력 분포는 XFOIL을 이용하여 예측하였다. 첫 번째 수준의 설계변수인 각각의 블레이드 지름과 축 회전수에서 익형의 공력변수들과 최소에너지손실 조건을 이용하여 두 번째 설계변수인 각 블레이드 단면에서의 시위길이와 피치각 분포를 최적화하였다. 그리고 성능결과를 바탕으로 반응면을 구성하고, 확률적 방법을 이용하여 타당성 있는 설계공간까지 첫 번째 설계변수를 이동시키고 구배최적화 기법을 통해 각각의 제약함수를 만족하면서 목적함수를 죄대로 하는 최적블레이드 형상을 구현하였다. 설계된 최적형상에 대해 탈설계점 해석을 수행하여 성능을 구하였다.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.38A no.6
• /
• pp.459-464
• /
• 2013

In this paper, we introduce a modulation code design problem where best selection of two-dimensional codewords are determined to reduce two-dimensional (2D) intersymbol interference (ISI) and interpage interference (IPI). Codeword selection problem is formulated as a quadratic integer programming model that minimizes intra- and inter-symbol differences subject to uniform symbol usage and minimal Hamming distance violations. Second integer programming model detects the occurrence of isolated pixel pattern in the selected codewords. The proposed models are applied to 4-level and 2-level 6/8 codes.

• The Korean Journal of Applied Statistics
• /
• v.33 no.5
• /
• pp.569-578
• /
• 2020

By estimating conditional quantile functions of the response, quantile regression (QR) can provide comprehensive information of the relationship between the response and the predictors. In addition, kernel quantile regression (KQR) estimates a nonlinear conditional quantile function in reproducing kernel Hilbert spaces generated by a positive definite kernel function. However, it is infeasible to use the KQR in analysing a massive data due to the limitations of computer primary memory. We propose a divide and conquer based KQR (DC-KQR) method to overcome such a limitation. The proposed DC-KQR divides the entire data into a few subsets, then applies the KQR onto each subsets and derives a final estimator by aggregating all results from subsets. Simulation studies are presented to demonstrate the satisfactory performance of the proposed method.

• Computational Structural Engineering
• /
• v.3 no.1
• /
• pp.83-95
• /
• 1990

Many structural optimization problems are solved by numerical algorithms since these are complicated and nonlinear. To provide a wider base and popular it to structual design optimization, reliable, accurate and superlinearly convergent nonlinear programming algorithm with active-set strategy have been developed. One of these is RQP(recursive quadratic programming method). This algorithm has several parameters and its performance is influenced by variations of these key parameters. Therefore, an RQP algorithm is selected to enhance its numerical performances by choosing proper parameters. The paper persents these influences on its numerical performance. For comparison of performances, a structural design software for minimum weight of truss subjected to displacement, stress, and lower and upper bounds on design variables is also implemented.

• Journal of the Computational Structural Engineering Institute of Korea
• /
• v.33 no.4
• /
• pp.217-224
• /
• 2020

In this study, a framework for optimizing the opening in an outrigger wall is proposed. To solve a constrained bounded optimization problem, an in-house finite element program and SQP algorithm in Python SciPy library are utilized. The openings of the outrigger wall are located according to the strut-tie behavior of the outrigger wall deep beam. A linear interpolation method is used to obtain differentiable continuous functions required for optimization, whereas a database is used for the efficiency of the optimization program. By comparing the result of the two-variable optimization through the moving path of the search algorithm, it is confirmed that the algorithm efficiently determines the optimized result. When the size of each opening is set to individual variables rather than the same width of all openings, the value of the objective function is minimized to obtain better optimization results. It was confirmed that the optimization time can be effectively reduced when using the database in the optimization process.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.19 no.4
• /
• pp.85-92
• /
• 2018

Reductions of the electricity charge are achieved by demand management of the load. The demand management method of the load using ESS involves peak shifting, which shifts from a high demand time to low demand time. By shifting the load, the peak load can be lowered and the energy charge can be saved. Electricity charges consist of the energy charge and the basic charge per contracted capacity. The energy charge and peak load are minimized by Linear Programming (LP) and Quadratic Programming (QP), respectively. On the other hand, each optimization method has its advantages and disadvantages. First, the LP cannot separate the efficiency of the ESS. To solve these problems, the charge and discharge efficiency of the ESS was separated by Mixed Integer Linear Programming (MILP). Nevertheless, both methods have the disadvantages that they must assume the reduction ratio of peak load. Therefore, QP was used to solve this problem. The next step was to optimize the formula combination of QP and LP to minimize the electricity charge. On the other hand, these two methods have disadvantages in that the charge and discharge efficiency of the ESS cannot be separated. This paper proposes an optimization method according to the situation by analyzing quantitatively the advantages and disadvantages of each optimization method.

• 한국신재생에너지학회:학술대회논문집
• /
• 2007.06a
• /
• pp.432-436
• /
• 2007

본 연구의 목적은 3차원 풍력터빈 블레이드 최적형상설계를 위한 실용적이고 효율적인 설계 과정을 구현하는 것이다. 국내 연안의 해상풍력에 적용하기 위해서 통계적 모델을 이용하여 풍황 자료를 분석하였다. 설계에 관련된 많은 수의 설계변수를 효과적으로 관리하기 위해서 설계과정은 운용조건 최적화와 블레이드 형상설계의 2단계로 구성하였다. 실험계획법에 의해 추출된 각 운용조건점은 형상설계를 위한 입력값으로 제공된다. 형상설계 단계에서는 최소에너지손실 조건과 결합된 BEMT를 이용하여 각 블레이드 단면에서의 시위길이와 피치각 분포를 최적화하였다. 블레이드 단면 익형은 NREL S830을 이용하였고, 익형의 공력성능은 XFOIL을 이용하여 예측하였다. 설계된 블레이드 형상의 성능해석을 수행하고 그 결과를 바탕으로 반응면을 구성하였다. 좀 더 나은 성능을 가진 블레이드 형상을 찾기 위해서 초기설계공간에서 확률적 방법을 이용하여 타당성 있는 설계공간까지 운용조건 설계변수를 이동시키고 구배최적화 기법을 통해 각각의 제약함수를 만족하면서 연평균발생에너지를 최대로 하는 최적블레이드 형상을 구현하였다. 제시된 최적설계과정은 풍력터빈블레이드 개발에 실용적이고 신뢰성 있는 설계툴로서 사용이 가능하다.

• New & Renewable Energy
• /
• v.3 no.3
• /
• pp.63-71
• /
• 2007

본 연구의 목적은 3차원 풍력터빈 블레이드 최적형상설계를 위한 실용적이고 효율적인 설계과정을 구현하는 것이다. 국내 연안의 해상풍력에 적용하기 위해서 통계적 모델을 이용하여 풍황자료를 분석하였다. 설계에 관련된 많은 수의 설계변수를 효과적으로 관리하기 위해서 설계과정은 운용조건 최적화와 블레이드 형상설계의 2단계로 구성하였다. 실험계획법에 의해 추출된 각 운용조건 설계점은 형상설계를 위한 입력 값으로 제공된다. 형상설계 단계에서는 최소에너지손실 조건과 결합된 BEMT를 이용하여 각 블레이드 단면에서의 시위길이와 피치각 분포를 최적화하였다. 블레이드 단면 익형은 NREL S830을 이용하였고, 익형의 공력성능은 XFOIL을 이용하여 예측하였다. 설계된 블레이드 형상의 성능해석을 수행하고 그 결과를 바탕으로 반응면을 구성하였다. 좀 더 나은 성능을 가진 블레이드 형상을 찾기 위해서 초기설계공간에서 확률적 방법을 이용하여 타당성 있는 설계공간까지 운용조건 설계변수를 이동시키고 구배최적화 기법을 통해 각각의 제약함수를 만족하면서 연간에너지생산량을 최대로 하는 최적블레이드 형상을 구현하였다. 제시된 최적설계과정은 풍력터빈블레이드 개발에 실용적이고 신뢰성 있는 설계툴로서 사용이 가능하다.

• Journal of Korean Society of Transportation
• /
• v.24 no.5 s.91
• /
• pp.45-56
• /
• 2006

In order to construct an information pool on the production characteristics and efficiency of Korean railroad industry, various alternative approaches have to be applied. In this paper we present an empirical application of the distance function to measure the technical efficiency and the production characteristics of Korean railroad industry, The distance function firstly introduced by Shephard (1953) provides the advantage that it does not need information about prices, so it can accommodate the multiple output nature of the railway only using the quantifies as data. This is of great relevance in the context of the public sector such as railroad industry where there are often distinct control mechanisms on input prices. Also the distance function allows us to obtain a measure of technical efficiency as well as a measure of production characteristics. From annual data on Korean railroad industry during 1964-2004, multiple output distance function is estimated using quadratic programming model. The resulting technical efficiency estimates has tended to be improved over the period $1980{\sim}2004$. The indirect Morishima elasticities of substitution indicate that the substitutabilities for labor are relatively very low or impossible. The average scale elasticity is 2.7 which means that increasing the scale by 1per cent will result in an output increase by 2.7 percent. This result indicates that economies of scale are present in the Korean railroad industry.